[go: up one dir, main page]

WO2024202467A1 - Object detection device, object detection method, and recording medium - Google Patents

Object detection device, object detection method, and recording medium Download PDF

Info

Publication number
WO2024202467A1
WO2024202467A1 PCT/JP2024/002171 JP2024002171W WO2024202467A1 WO 2024202467 A1 WO2024202467 A1 WO 2024202467A1 JP 2024002171 W JP2024002171 W JP 2024002171W WO 2024202467 A1 WO2024202467 A1 WO 2024202467A1
Authority
WO
WIPO (PCT)
Prior art keywords
object detection
dimensional information
target
reflected wave
detection device
Prior art date
Application number
PCT/JP2024/002171
Other languages
French (fr)
Japanese (ja)
Inventor
剛志 柴田
耕介 木下
健全 劉
Original Assignee
日本電気株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電気株式会社 filed Critical 日本電気株式会社
Publication of WO2024202467A1 publication Critical patent/WO2024202467A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
    • G01V3/12—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with electromagnetic waves

Definitions

  • the present invention relates to an object detection device, an object detection method, and a program.
  • Patent Document 1 As an example of a device for detecting objects buried underground, there is the device described in Patent Document 1.
  • This device is for detecting landmines.
  • the sensor head is provided with a transmitter and a receiver.
  • the transmitter transmits electromagnetic wave impulses toward the ground where a landmine is to be detected, and the receiver receives the reflected waves from the landmine.
  • This device then generates information showing the three-dimensional structure of the landmine based on the time until the reflected waves are received, the level of the reflected waves, and the position of the sensor head, and displays this information on the display.
  • Patent Document 2 also describes an investigation device having an electromagnetic wave sensor and a movement mechanism for moving the electromagnetic wave sensor within a two-dimensional plane.
  • the position of the electromagnetic wave sensor is detected by a position detection means.
  • the investigation device uses the reception information received by the electromagnetic wave sensor and the position information detected by the position detection means as input information, and generates two-dimensional image information for each investigation depth.
  • one example of the objective of the present invention is to provide an object detection device, an object detection method, and a program that require less effort when investigating even when the area to be investigated is large.
  • a three-dimensional information generating means generates three-dimensional information indicating the possibility of a target object being present for a plurality of first points included in a three-dimensional space corresponding to a target area by processing reflected wave information indicating reflected waves of electromagnetic waves irradiated to the target area; a two-dimensional information generating means for generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in a predetermined plane by projecting the three-dimensional information onto the predetermined plane; a detection means for detecting a target region, which is a region in which the target object exists, of the target region by processing the two-dimensional information;
  • An object detection device is provided, comprising:
  • a computer includes: generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area; generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane; An object detection method is provided, which processes the two-dimensional information to detect a target region within the target region, the target region being a region in which the target object exists.
  • a computer includes: generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area; generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane;
  • a program is provided that processes the two-dimensional information to detect a target region, which is a region in which the target object exists, from the target region.
  • an object detection device it is possible to provide an object detection device, an object detection method, and a program that require less effort when investigating a large area.
  • FIG. 1 is a diagram showing an overview of an object detection device according to a first embodiment.
  • FIG. 1 is a diagram for explaining a usage environment of an object detection device.
  • FIG. 2 is a diagram illustrating an example of a functional configuration of a measurement device.
  • FIG. 2 is a diagram illustrating an example of a functional configuration of an object detection device.
  • 11 is a diagram for explaining an example of a process performed by a two-dimensional information generating unit;
  • FIG. 2 is a diagram illustrating an example of a hardware configuration of an object detection device.
  • 4 is a flowchart illustrating an example of a process performed by the object detection device.
  • FIG. 11 is a diagram illustrating an example of a functional configuration of an object detection device according to a second embodiment.
  • First Embodiment 1 is a diagram showing an overview of an object detection device 10 according to the first embodiment.
  • the object detection device 10 includes a three-dimensional information generator 120, a two-dimensional information generator 130, and a detector 140.
  • the three-dimensional information generating unit 120 processes the reflected wave information to generate three-dimensional information.
  • the reflected wave information indicates the reflected waves of the electromagnetic waves irradiated to the target area.
  • the three-dimensional information indicates the possibility that a target object exists at a plurality of first points included in the three-dimensional space that indicates the target area.
  • the two-dimensional information generating unit 130 generates two-dimensional information by projecting the three-dimensional information onto a specified plane.
  • the two-dimensional information indicates the possibility that a target object exists at each of a number of second points included within this plane.
  • the detection unit 140 detects the area in which the target object exists within the target area by processing the two-dimensional information.
  • this area will be referred to as the target area.
  • the above-mentioned two-dimensional information can be regarded as an image. Therefore, the detection unit 140 can use various image processing methods. Therefore, according to the object detection device 10, even if the reflected wave information contains a lot of noise, the target area can be detected with high accuracy. Therefore, even if the area to be investigated is wide, the effort required for the investigation is small.
  • the object detection device 10 is described in detail below.
  • FIG. 2 is a diagram for explaining the environment in which the object detection device 10 is used.
  • the object detection device 10 is used together with a measurement device 20.
  • the measuring device 20 is a device that can be remotely controlled.
  • the measuring device 20 may be, for example, an air vehicle such as a drone, or may be a self-propelled device.
  • the measuring device 20 can move automatically or by remote control.
  • the target area to be investigated for the presence or absence of a target object is, for example, the ground and the underground below it. In this case, the target object is present on the ground or underground.
  • the measuring device 20 generates reflected wave information while moving through an area to be investigated for the presence or absence of a target object, and transmits this reflected wave information to the object detection device 10, for example, via a wireless communication network. This transmission is performed, for example, in real time, but may also be performed in a batch manner.
  • the object detection device 10 detects the target area by processing the reflected wave information received from the measurement device 20.
  • the object detection device 10 may perform the processing in a batch manner, or in real time, that is, each time reflected wave information is received from the measurement device 20.
  • FIG. 3 is a diagram showing an example of the functional configuration of the measuring device 20.
  • the measuring device 20 has an electromagnetic wave emitting unit 210, an electromagnetic wave receiving unit 220, a reflected wave information generating unit 230, and a communication unit 240.
  • the measuring device 20 has a movement mechanism for moving the measuring device 20 and a movement control unit for controlling this.
  • the electromagnetic wave emitting unit 210 irradiates electromagnetic waves toward the target area.
  • the electromagnetic waves are, for example, millimeter waves, and an example of the wavelength is 0.3 GHz or more and 300 GHz or less.
  • the band of the electromagnetic waves irradiated by the electromagnetic wave emitting unit 210 is not limited to millimeter waves.
  • the transmission method used by the electromagnetic wave emitting unit 210 is, for example, any of FMCW (Frequency Modulated Continuous Wave), pulse, CW (Continuous Wave) Doppler, two-frequency CW, and pulse compression, but may be other than these.
  • the electromagnetic wave receiving unit 220 receives reflected waves of the electromagnetic waves emitted by the electromagnetic wave transmitting unit 210.
  • These reflected waves are electromagnetic waves that have been reflected, for example, by objects on the ground's surface or objects underground. In other words, if there is an object in the target area that reflects electromagnetic waves, the strength of the reflected waves will be high. Objects that reflect electromagnetic waves are often made primarily of metal.
  • multiple, for example two, electromagnetic wave receiving units 220 are provided. These multiple electromagnetic wave receiving units 220 are spaced apart from each other, and receive reflected waves of electromagnetic waves emitted by the same electromagnetic wave emitting unit 210. In this way, the object detection device 10 can detect the target area with higher accuracy.
  • the reflected wave information generating unit 230 generates reflected wave information using the reception results from the electromagnetic wave receiving unit 220.
  • the reflected wave information includes, for example, time series information on the intensity of the reflected wave. This time series information includes a combination of the date and time the reflected wave was received and the intensity of the reflected wave at that time. If multiple electromagnetic wave receiving units 220 are provided, the reflected wave information generating unit 230 generates reflected wave information separately for each of the multiple electromagnetic wave receiving units 220.
  • the reflected wave information generating unit 230 also generates location information indicating the location of the measuring device 20. This location information may be generated using, for example, GPS, or may be generated using other methods, such as SLAM (Simultaneous Localization and Mapping). The reflected wave information generating unit 230 then adds to the reflected wave information the location information of the measuring device 20 at the time the reflected wave was received.
  • location information may be generated using, for example, GPS, or may be generated using other methods, such as SLAM (Simultaneous Localization and Mapping).
  • SLAM Simultaneous Localization and Mapping
  • the communication unit 240 communicates with external devices. As one example, the communication unit 240 transmits the reflected wave information generated by the reflected wave information generation unit 230 to the object detection device 10. This transmission may be in batches as described above, or in real time. As another example, the communication unit 240 receives information for controlling the movement of the measuring device 20, such as route information indicating the route along which the measuring device 20 should move. In this case, the movement control unit of the measuring device 20 controls the movement mechanism of the measuring device 20 to move the measuring device 20 according to the received route information.
  • the position information may be information separate from the reflected wave information.
  • the position information is time-series information on the position of the measuring device 20. This time-series information includes a combination of a date and time and the position of the measuring device 20 at that date and time.
  • the communication unit 240 also transmits the position information to the object detection device 10.
  • FIG. 4 is a diagram showing an example of the functional configuration of the object detection device 10.
  • the object detection device 10 also includes a communication unit 110 and a storage unit 150.
  • the communication unit 110 communicates with an external device, for example, the measuring device 20. For example, when the communication unit 110 receives reflected wave information from the measuring device 20, it stores this reflected wave information in the storage unit 150. When position information is transmitted from the measuring device 20, the communication unit 110 also stores this position information in the storage unit 150.
  • the three-dimensional information generating unit 120 generates three-dimensional information by processing the reflected wave information.
  • the reflected wave information includes a time series signal of the intensity of the reflected wave and the position of the measuring device 20.
  • the three-dimensional information generating unit 120 calculates the distance from the electromagnetic wave receiving unit 220 to the reflection point that is the origin of the reflected wave by performing FFT (Fast Fourier Transform) multiple times on the reflected wave that constitutes this time series signal. If there are multiple electromagnetic wave receiving units 220, the three-dimensional information generating unit 120 performs this processing for each electromagnetic wave receiving unit 220.
  • FFT Fast Fourier Transform
  • the three-dimensional information generating unit 120 then integrates multiple distances based on the reflected waves measured by different electromagnetic wave receiving units 220 at the same timing to calculate an estimate of the intensity of the reflected wave for at least one first point included in the three-dimensional space corresponding to the target area.
  • the three-dimensional information generating unit 120 performs this process on the reflected waves measured at multiple timings to calculate an estimate of the intensity of the reflected waves for each of the multiple first points, and uses these as three-dimensional information.
  • this estimate can be considered as a value indicating the possibility that a target object exists at the first point.
  • this value will be referred to as the first value.
  • the method of generating the three-dimensional information for example the method of generating the first value, is not limited to this example.
  • the two-dimensional information generating unit 130 generates two-dimensional information by projecting three-dimensional information onto a predetermined plane.
  • this predetermined plane will be referred to as the projection plane.
  • the angle that the projection plane makes with respect to the ground surface of the target area is 10° or less. In other words, it is preferable that the projection plane is horizontal to the ground surface of the target area.
  • the two-dimensional information generating unit 130 identifies a plurality of first points corresponding to the second point. For example, the two-dimensional information generating unit 130 regards a plurality of first points that overlap with the second point when viewed from a direction perpendicular to the projection surface as the first points corresponding to the second point. Next, the two-dimensional information generating unit 130 identifies a first value corresponding to each of the identified plurality of first points, and uses the first value to generate a second value indicating the possibility that the target object exists at the second point.
  • the second value may be the maximum value or the average value of the plurality of first values.
  • the second value may be the first value corresponding to the first point closest to the ground surface among the first points whose first values exceed the reference value.
  • the two-dimensional information generating unit 130 then regards the second value for each second point as two-dimensional information.
  • the two-dimensional information can be regarded as black and white image data.
  • the detection unit 140 detects the target region by processing the two-dimensional information as described with reference to FIG. 1.
  • the detection unit 140 detects the target region by performing a predetermined image processing on the two-dimensional information.
  • This image processing is, for example, YOLO, SSD (Single Shot MultiBox Detector), or Faster-RCNN (Regions with Convolutional Neural Networks), but may be other than these.
  • the object detection device 10 may detect the target area using at least one of geological information of the target area and weather information at the time the reflected waves were generated. For example, the geology of a particular area within the target area may be more conducive to generating reflected waves. Also, depending on the weather, water or snow may accumulate on the surface of the target area, affecting the reflected waves. The object detection device 10 takes this effect into account when selecting the target area.
  • At least one of the three-dimensional information generating unit 120 and the two-dimensional information generating unit 130 multiplies a parameter corresponding to the geology of the location by a first value or a second value, and then generates three-dimensional information or two-dimensional information.
  • This parameter is set in advance.
  • At least one of the three-dimensional information generating unit 120 and the two-dimensional information generating unit 130 multiplies a parameter corresponding to the weather at the time of measurement by a first value or a second value, and then generates three-dimensional information or two-dimensional information. This parameter is also set in advance.
  • geological information and weather information are input to the information processing device 10 by, for example, a user of the information processing device 10, but the information processing device 10 may also obtain the information from a database in which the information processing device 10 stores the information.
  • FIG. 6 is a diagram showing an example of the hardware configuration of the object detection device 10.
  • the object detection device 10 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input/output interface 1050, and a network interface 1060.
  • the bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, input/output interface 1050, and network interface 1060 to transmit and receive data to and from each other.
  • the method of connecting the processor 1020 and other components to each other is not limited to a bus connection.
  • the processor 1020 is a processor realized by a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), etc.
  • Memory 1030 is a main storage device realized by RAM (Random Access Memory) or the like.
  • the storage device 1040 is an auxiliary storage device realized by a removable medium such as a HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, or a ROM (Read Only Memory), and has a recording medium.
  • the recording medium of the storage device 1040 stores program modules that realize each function of the object detection device 10 (e.g., the communication unit 110, the three-dimensional information generation unit 120, the two-dimensional information generation unit 130, and the detection unit 140).
  • the processor 1020 loads each of these program modules onto the memory 1030 and executes them, thereby realizing each function corresponding to the program module.
  • the storage device 1040 also functions as a memory unit 150.
  • the input/output interface 1050 is an interface for connecting the object detection device 10 to various input/output devices.
  • the network interface 1060 is an interface for connecting the object detection device 10 to a network.
  • This network is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network).
  • the method for connecting the network interface 1060 to the network may be a wireless connection or a wired connection.
  • the object detection device 10 may communicate with the measurement device 20 via the network interface 1060.
  • FIG. 7 is a flowchart showing an example of processing performed by the object detection device 10.
  • the object detection device 10 performs processing in a batch manner.
  • the communication unit 110 repeatedly acquires reflected wave information from the measurement device 20 and stores it in the memory unit 150.
  • the three-dimensional information generating unit 120 reads out reflected wave information of the target area to be processed this time from the storage unit 150 (step S110), and generates three-dimensional information by processing the read reflected wave information (step S120).
  • the two-dimensional information generating unit 130 processes the three-dimensional information to generate two-dimensional information (step S130).
  • the detection unit 140 detects the target area by processing the two-dimensional information.
  • the target area is data showing an area on a two-dimensional plane where the target object is likely to exist (step S140).
  • the detection unit 140 may use information in which the coordinates of the second point are linked to the probability (reliability) that the target object exists at these coordinates as information indicating the target area.
  • the probability used here is a second value, but may also be a value obtained by processing the second value.
  • the detection unit 140 may also generate information in which the probability (reliability) that the target object exists at each coordinate on the projection surface is linked to this coordinate.
  • the detection unit 140 may display a screen showing the target area on a display device. This display device may be part of the object detection device 10 or may be external to the object detection device 10.
  • the two-dimensional information generating unit 130 of the object detection device 10 generates two-dimensional information using the three-dimensional information generated by the three-dimensional information generating unit 120.
  • This two-dimensional information can be considered as image data.
  • the detection unit 140 then processes this two-dimensional information to detect the target area. Therefore, according to the object detection device 10, even if the reflected wave information contains a lot of noise, the target area can be detected with high accuracy. Therefore, even if the area to be investigated is large, less effort is required during the investigation.
  • Second Embodiment Fig. 8 is a diagram showing an example of the functional configuration of the object detection device 10 according to the second embodiment, and corresponds to Fig. 4 of the first embodiment.
  • the object detection device 10 according to this embodiment has the same configuration as the object detection device 10 according to the first embodiment, except for the following points.
  • the object detection device 10 includes a reflected wave information processing unit 160.
  • the reflected wave information processing unit 160 processes the reflected wave information using a model generated using machine learning.
  • the detection unit 140 detects the target area using the two-dimensional information generated by the two-dimensional information generation unit 130 and the processing results by the reflected wave information processing unit 160.
  • the reflected wave information processing unit 160 has a Fourier transform unit 162, a feature extraction unit 164, and an identification unit 166.
  • the Fourier transform unit 162 generates a frequency signal by performing a Fourier transform on the reflected wave information.
  • An example of this frequency signal is a spectrogram or a mel spectrogram, but is not limited to these.
  • the feature extraction unit 164 extracts features by processing the frequency signal generated by the Fourier transform unit 162 using a first model.
  • the feature extraction unit 164 selects data from the frequency signal that corresponds to a first point included in the three-dimensional information.
  • the first point included in the three-dimensional information is linked to the generation timing of the reflected wave information corresponding to the first point. Therefore, the feature extraction unit 164 can select a frequency signal that corresponds to this generation timing.
  • the feature extraction unit 164 then inputs this frequency signal to a first model generated by machine learning, thereby extracting features.
  • the first model is generated, for example, by machine learning using the frequency signal as an explanatory variable and the features as a target variable. Note that an example of machine learning used here is a convolutional neural network, but is not limited to this.
  • the identification unit 166 detects regions that may be the target region by processing the features extracted by the feature extraction unit 164 using a second model.
  • the second model is, for example, a classifier using a fully connected deep learning network. If the input feature is determined to be abnormal by this classifier (for example, if the likelihood of being the target region is equal to or greater than a reference value), the identification unit 166 determines that a first point corresponding to the input feature is a region where a target object exists, i.e., the target region. The first point is then projected onto a projection surface in the same manner as the two-dimensional information generation unit 130, thereby identifying the target region in the two-dimensional information. At this time, it is preferable that the identification unit 166 also associates the likelihood (reliability) of being the target region with each coordinate on the projection surface that is the basis of the two-dimensional information.
  • the detection unit 140 then detects the destination region using the method shown in the first embodiment, and detects the final destination region by integrating this destination region with the destination region detected using the identification unit 166. For example, the detection unit 140 may calculate a weighted average of the reliability for each coordinate calculated using the method shown in the first embodiment and the reliability for each coordinate generated by the identification unit 166, and determine the region where this average is equal to or greater than a threshold as the final destination region. The detection unit 140 may also determine the union or intersection of the destination region calculated using the method shown in the first embodiment and the destination region generated by the identification unit 166 as the final destination region.
  • this embodiment requires less effort when investigating a wide area.
  • the presence of the reflected wave information processing unit 160 increases the accuracy of detecting the target area.
  • a three-dimensional information generating means for generating three-dimensional information indicating the possibility of the presence of a target object for a plurality of first points included in a three-dimensional space corresponding to a target area by processing reflected wave information indicating reflected waves of electromagnetic waves irradiated to the target area; a two-dimensional information generating means for generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in a predetermined plane by projecting the three-dimensional information onto the predetermined plane; a detection means for detecting a target region, which is a region in which the target object exists, of the target region by processing the two-dimensional information;
  • An object detection device comprising: 2.
  • the object detection device wherein the frequency of the electromagnetic wave is 0.3 GHz or more and 300 GHz or less. 3.
  • An object detection device, wherein the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic wave and a receiving means for receiving the reflected wave. 4.
  • the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
  • the two-dimensional information generating means generates, for each of the second points, identifying a plurality of the first points corresponding to the second point;
  • An object detection device that identifies the first value corresponding to each of the identified first points, and uses the first value to generate a second value indicating a possibility that the target object is present at the second point.
  • a reflected wave information processing means processes the reflected wave information using a model generated by machine learning, The detection means further detects the target region using the processing results of the model. 6.
  • the reflected wave information processing means generating a frequency signal by performing a Fourier transform on the reflected wave information; Processing the frequency signal with a first said model to extract features;
  • the object detection apparatus detects regions that may be the target regions by processing the extracted features using a second model. 7.
  • the target area is the ground and the subsurface therebelow; An object detection device, wherein the target object is present on the ground or underground. 8.
  • An object detection device, wherein the angle between the specified plane and the ground is 10° or less.
  • the computer generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area; generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane; an object detection method for detecting a target region, which is a region of the target region in which the target object exists, by processing the two-dimensional information; 10.
  • the object detection method wherein the frequency of the electromagnetic wave is 0.3 GHz or more and 300 GHz or less. 11.
  • the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic wave and a receiving means for receiving the reflected wave.
  • the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
  • the computer for each of the second points, identifying a plurality of the first points corresponding to the second point;
  • a method for object detection comprising: identifying a first value corresponding to each of the identified first points; and using the first value to generate a second value indicating a possibility that the target object is present at the second point. 13.
  • the computer includes: Processing the reflected wave information using a model generated using machine learning; Further, the object detection method includes detecting the target region using the processing results of the model. 14. In the object detection method according to claim 13, The computer includes: generating a frequency signal by performing a Fourier transform on the reflected wave information; Processing the frequency signal with a first said model to extract features; and processing the extracted features with a second said model to detect regions that may be said regions of interest. 15. In the object detection method according to any one of claims 9 to 14, the target area is the ground and the subsurface therebelow; An object detection method, wherein the target object is present on the ground or underground. 16. In the object detection method according to claim 15, An object detection method, wherein the angle between the predetermined plane and the ground is 10° or less.
  • the computer On the computer: generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area; generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane; A program for detecting a target region, which is a region in which the target object exists, within the target region by processing the two-dimensional information. 18. In the program according to 17 above, The program, wherein the frequency of the electromagnetic waves is 0.3 GHz or more and 300 GHz or less. 19.
  • the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic waves and a receiving means for receiving the reflected waves.
  • the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points; the computer, for each of the second points, identifying a plurality of the first points corresponding to the second points; A program that identifies the first value corresponding to each of the identified first points, and generates a second value indicating a possibility that the target object is present at the second point using the first value. 21.
  • the computer includes: Processing the reflected wave information using a model generated using machine learning; and a program for detecting the target region using the processing results of the model. 22.
  • the computer includes: generating a frequency signal by performing a Fourier transform on the reflected wave information; Processing the frequency signal with a first said model to extract features; and processing the extracted features using a second said model to detect regions that may be the regions of interest.
  • the target area is the ground and the subsurface therebelow; The target object is present on the ground or underground.
  • the angle between the predetermined plane and the ground is 10° or less. 25.
  • a recording medium having the program according to any one of claims 17 to 24 recorded thereon.
  • Object detection device 20 Measuring device 110 Communication unit 120 Three-dimensional information generation unit 130 Two-dimensional information generation unit 140 Detection unit 150 Storage unit 160 Reflected wave information processing unit 162 Fourier transform unit 164 Feature extraction unit 166 Identification unit 210 Electromagnetic wave transmission unit 220 Electromagnetic wave reception unit 230 Reflected wave information generation unit 240 Communication unit

Landscapes

  • Remote Sensing (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • General Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Environmental & Geological Engineering (AREA)
  • Geology (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geophysics (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

This object detection device comprises: a three-dimensional information generation unit; a two-dimensional information generation unit; and a detection unit. The three-dimensional information generation unit generates three-dimensional information by processing reflected wave information. The reflected wave information indicates a reflected wave of an electromagnetic wave applied to a target region. The three-dimensional information indicates the possibility of existence of target objects at a plurality of first points included in a three-dimensional space indicating the target region. The two-dimensional information generation unit generates two-dimensional information by projecting the three-dimensional information onto a prescribed plane. The two-dimensional information indicates the possibility of existence of a target object at each of a plurality of second points included in the plane. The detection unit processes the two-dimensional information and detects a target region which is a region, of the target region, in which the target object exists.

Description

物体検出装置、物体検出方法、及び記録媒体OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND RECORDING MEDI

　本発明は、物体検出装置、物体検出方法、及びプログラムに関する。 The present invention relates to an object detection device, an object detection method, and a program.

　地中に埋設されている物体を検出する装置として、例えば特許文献１に記載の装置がある。この装置は、地雷を検知するための装置である。詳細には、センサヘッドには送信部及び受信部が設けられている。送信部は、地雷を検知しようとする地面に向けて電磁波のインパルスを送信し、受信部は、地雷からの反射波を受信する。そしてこの装置は、反射波が受信されるまでの時間、反射波の受診レベル、及びセンサヘッドの位置に基づいて、地雷の３次元構造を示す情報を生成して表示部に表示する。 As an example of a device for detecting objects buried underground, there is the device described in Patent Document 1. This device is for detecting landmines. In detail, the sensor head is provided with a transmitter and a receiver. The transmitter transmits electromagnetic wave impulses toward the ground where a landmine is to be detected, and the receiver receives the reflected waves from the landmine. This device then generates information showing the three-dimensional structure of the landmine based on the time until the reflected waves are received, the level of the reflected waves, and the position of the sensor head, and displays this information on the display.

　また特許文献２には、電磁波センサ及びこの電磁波センサを２次元平面内で移動させる移動機構を有する調査装置が記載されている。そして電磁波センサの位置は、位置検出手段によって検出される。そして調査装置は、電磁波センサで受信した受信情報と位置検出手段で検出した位置情報を入力情報として、調査深度毎の２次元の画像情報を生成する。 Patent Document 2 also describes an investigation device having an electromagnetic wave sensor and a movement mechanism for moving the electromagnetic wave sensor within a two-dimensional plane. The position of the electromagnetic wave sensor is detected by a position detection means. The investigation device uses the reception information received by the electromagnetic wave sensor and the position information detected by the position detection means as input information, and generates two-dimensional image information for each investigation depth.

国際公開２０００／０２３７６２号International Publication No. 2000/023762 特開平１０－２２１４６３号公報Japanese Patent Application Publication No. 10-221463

　上述した特許文献１及び２に記載の技術を用いた場合、調査の対象となる領域が広域の場合、領域全体を調査する際に多くの労力を要していた。本発明の目的の一例は、上述した課題を鑑み、調査の対象となる領域が広域となった場合でも調査時に必要な労力が少ない物体検出装置、物体検出方法、及びプログラムを提供することにある。 When using the technologies described in Patent Documents 1 and 2 above, if the area to be investigated is large, a lot of effort is required to investigate the entire area. In view of the above-mentioned problems, one example of the objective of the present invention is to provide an object detection device, an object detection method, and a program that require less effort when investigating even when the area to be investigated is large.

　本発明の一態様によれば、対象領域へ照射された電磁波の反射波を示す反射波情報を処理することにより、前記対象領域に対応する３次元空間に含まれる複数の第１の点について、対象物体が存在する可能性を示す３次元情報を生成する３次元情報生成手段と、
　前記３次元情報を所定の平面に投影することにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成する２次元情報生成手段と、
　前記２次元情報を処理することにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出する検出手段と、
を備える物体検出装置が提供される。 According to one aspect of the present invention, a three-dimensional information generating means generates three-dimensional information indicating the possibility of a target object being present for a plurality of first points included in a three-dimensional space corresponding to a target area by processing reflected wave information indicating reflected waves of electromagnetic waves irradiated to the target area;
a two-dimensional information generating means for generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in a predetermined plane by projecting the three-dimensional information onto the predetermined plane;
a detection means for detecting a target region, which is a region in which the target object exists, of the target region by processing the two-dimensional information;
An object detection device is provided, comprising:

　本発明の一態様によれば、コンピュータが、
　　対象領域へ照射された電磁波の反射波を示す反射波情報を処理することにより、前記対象領域を示す３次元空間に含まれる複数の第１の点毎に対象物体が存在する可能性を示す３次元情報を生成し、
　　前記３次元情報を所定の平面に投影することにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成し、
　　前記２次元情報を処理することにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出する、物体検出方法が提供される。 According to one aspect of the present invention, a computer includes:
generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area;
generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane;
An object detection method is provided, which processes the two-dimensional information to detect a target region within the target region, the target region being a region in which the target object exists.

　本発明の一態様によれば、コンピュータに、
　　対象領域へ照射された電磁波の反射波を示す反射波情報を処理することにより、前記対象領域を示す３次元空間に含まれる複数の第１の点毎に対象物体が存在する可能性を示す３次元情報を生成させ、
　　前記３次元情報を所定の平面に投影することにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成させ、
　　前記２次元情報を処理することにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出させる、プログラムが提供される。 According to one aspect of the present invention, a computer includes:
generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area;
generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane;
A program is provided that processes the two-dimensional information to detect a target region, which is a region in which the target object exists, from the target region.

　本発明の一態様によれば、調査の対象となる領域が広域となった場合でも調査時に必要な労力が少ない物体検出装置、物体検出方法、及びプログラムを提供できる。 According to one aspect of the present invention, it is possible to provide an object detection device, an object detection method, and a program that require less effort when investigating a large area.

第１の実施形態に係る物体検出装置の概要を示す図である。1 is a diagram showing an overview of an object detection device according to a first embodiment. 物体検出装置の使用環境を説明するための図である。FIG. 1 is a diagram for explaining a usage environment of an object detection device. 測定装置の機能構成の一例を示す図である。FIG. 2 is a diagram illustrating an example of a functional configuration of a measurement device. 物体検出装置の機能構成の一例を示す図である。FIG. 2 is a diagram illustrating an example of a functional configuration of an object detection device. ２次元情報生成部が行う処理の一例を説明するための図である。11 is a diagram for explaining an example of a process performed by a two-dimensional information generating unit; FIG. 物体検出装置のハードウェア構成例を示す図である。FIG. 2 is a diagram illustrating an example of a hardware configuration of an object detection device. 物体検出装置が行う処理の一例を示すフローチャートである。4 is a flowchart illustrating an example of a process performed by the object detection device. 第２の実施形態に係る物体検出装置の機能構成の一例を示す図である。FIG. 11 is a diagram illustrating an example of a functional configuration of an object detection device according to a second embodiment.

　以下、本発明の実施の形態について、図面を用いて説明する。尚、すべての図面において、同様な構成要素には同様の符号を付し、適宜説明を省略する。 Below, an embodiment of the present invention will be described with reference to the drawings. Note that in all drawings, similar components are given similar reference numerals and descriptions will be omitted where appropriate.

（第１の実施形態）
　図１は、第１の実施形態に係る物体検出装置１０の概要を示す図である。物体検出装置１０は、３次元情報生成部１２０、２次元情報生成部１３０、及び検出部１４０を備えている。 First Embodiment
1 is a diagram showing an overview of an object detection device 10 according to the first embodiment. The object detection device 10 includes a three-dimensional information generator 120, a two-dimensional information generator 130, and a detector 140.

　３次元情報生成部１２０は、反射波情報を処理することにより、３次元情報を生成する。反射波情報は、対象領域へ照射された電磁波の反射波を示す。３次元情報は、対象領域を示す３次元空間に含まれる複数の第１の点について、当該点に対象物体が存在する可能性を示す。 The three-dimensional information generating unit 120 processes the reflected wave information to generate three-dimensional information. The reflected wave information indicates the reflected waves of the electromagnetic waves irradiated to the target area. The three-dimensional information indicates the possibility that a target object exists at a plurality of first points included in the three-dimensional space that indicates the target area.

　２次元情報生成部１３０は、３次元情報を所定の平面に投影することにより、２次元情報を生成する。２次元情報は、この平面内に含まれる複数の第２の点毎に対象物体が存在する可能性を示す。 The two-dimensional information generating unit 130 generates two-dimensional information by projecting the three-dimensional information onto a specified plane. The two-dimensional information indicates the possibility that a target object exists at each of a number of second points included within this plane.

　検出部１４０は、２次元情報を処理することにより対象領域のうち対象物体が存在している領域を検出する。以下、この領域を目的領域と記載する。 The detection unit 140 detects the area in which the target object exists within the target area by processing the two-dimensional information. Hereinafter, this area will be referred to as the target area.

　上記した２次元情報は画像とみなすことができる。このため、検出部１４０は、様々な画像処理方法を用いることができる。従って、物体検出装置１０によれば、反射波情報に多くのノイズが含まれている場合でも、精度よく目的領域を検出できる。従って、調査の対象となる領域が広域となった場合でも調査時に必要な労力は少なくて済む。 The above-mentioned two-dimensional information can be regarded as an image. Therefore, the detection unit 140 can use various image processing methods. Therefore, according to the object detection device 10, even if the reflected wave information contains a lot of noise, the target area can be detected with high accuracy. Therefore, even if the area to be investigated is wide, the effort required for the investigation is small.

　以下、物体検出装置１０について詳細に説明する。 The object detection device 10 is described in detail below.

　図２は物体検出装置１０の使用環境を説明するための図である。物体検出装置１０は、測定装置２０と共に使用される。 FIG. 2 is a diagram for explaining the environment in which the object detection device 10 is used. The object detection device 10 is used together with a measurement device 20.

　測定装置２０は遠隔操作が可能な装置である。測定装置２０は、例えばドローンなどの飛行体でもよいし、自走式の装置でもよい。測定装置２０は、自動又は遠隔操作により移動可能である。また、対象物体の有無を調査すべき対象領域は、例えば地面及びその下の地中である。この場合、対象物体は、地面又は地中に存在する。 The measuring device 20 is a device that can be remotely controlled. The measuring device 20 may be, for example, an air vehicle such as a drone, or may be a self-propelled device. The measuring device 20 can move automatically or by remote control. The target area to be investigated for the presence or absence of a target object is, for example, the ground and the underground below it. In this case, the target object is present on the ground or underground.

　測定装置２０は、対象物体の有無を調査すべき領域の中を移動しながら反射波情報を生成し、この反射波情報を、物体検出装置１０に、例えば無線通信網を介して送信する。この送信は、例えばリアルタイムで行われるが、バッチ式で行われてもよい。 The measuring device 20 generates reflected wave information while moving through an area to be investigated for the presence or absence of a target object, and transmits this reflected wave information to the object detection device 10, for example, via a wireless communication network. This transmission is performed, for example, in real time, but may also be performed in a batch manner.

　物体検出装置１０は、測定装置２０から受信した反射波情報を処理することにより、目的領域を検出する。なお、物体検出装置１０は、バッチ式で処理を行ってもよいし、リアルタイムすなわち測定装置２０から反射波情報を受信する度に処理を行ってもよい。 The object detection device 10 detects the target area by processing the reflected wave information received from the measurement device 20. The object detection device 10 may perform the processing in a batch manner, or in real time, that is, each time reflected wave information is received from the measurement device 20.

　図３は、測定装置２０の機能構成の一例を示す図である。測定装置２０は、電磁波発信部２１０、電磁波受信部２２０、反射波情報生成部２３０、及び通信部２４０を有している。なお、測定装置２０は、図３に示した構成の他に、当該測定装置２０を移動させるための移動機構及びこれを制御する移動制御部を有している。 FIG. 3 is a diagram showing an example of the functional configuration of the measuring device 20. The measuring device 20 has an electromagnetic wave emitting unit 210, an electromagnetic wave receiving unit 220, a reflected wave information generating unit 230, and a communication unit 240. In addition to the configuration shown in FIG. 3, the measuring device 20 has a movement mechanism for moving the measuring device 20 and a movement control unit for controlling this.

　電磁波発信部２１０は、対象領域に向けて電磁波を照射する。この電磁波は、例えばミリ波であり、その波長の一例は０．３ＧＨｚ以上３００ＧＨｚ以下である。ただし、電磁波発信部２１０が照射する電磁波の帯域はミリ波に限定されない。電磁波発信部２１０が用いる発信方式は、例えば、ＦＭＣＷ（Ｆｒｅｑｕｅｎｃｙ　Ｍｏｄｕｌａｔｅｄ　Ｃｏｎｔｉｎｕｏｕｓ　Ｗａｖｅ）、パルス、ＣＷ（Ｃｏｎｔｉｎｕｏｕｓ　Ｗａｖｅ）ドップラー、２周波ＣＷ、及びパルス圧縮のいずれかであるが、これら以外であってもよい。 The electromagnetic wave emitting unit 210 irradiates electromagnetic waves toward the target area. The electromagnetic waves are, for example, millimeter waves, and an example of the wavelength is 0.3 GHz or more and 300 GHz or less. However, the band of the electromagnetic waves irradiated by the electromagnetic wave emitting unit 210 is not limited to millimeter waves. The transmission method used by the electromagnetic wave emitting unit 210 is, for example, any of FMCW (Frequency Modulated Continuous Wave), pulse, CW (Continuous Wave) Doppler, two-frequency CW, and pulse compression, but may be other than these.

　電磁波受信部２２０は、電磁波発信部２１０が照射した電磁波の反射波を受信する。この反射波は、電磁波が、例えば地表の物体や地中の物体によって反射されたものである。言い換えると、対象領域に電磁波を反射する物体が存在すると、反射波の強度は高くなる。電磁波を反射する物体は、主に金属によって形成されている場合が多い。 The electromagnetic wave receiving unit 220 receives reflected waves of the electromagnetic waves emitted by the electromagnetic wave transmitting unit 210. These reflected waves are electromagnetic waves that have been reflected, for example, by objects on the ground's surface or objects underground. In other words, if there is an object in the target area that reflects electromagnetic waves, the strength of the reflected waves will be high. Objects that reflect electromagnetic waves are often made primarily of metal.

　本図に示す例において、電磁波受信部２２０は複数、例えば２つ設けられている。これら複数の電磁波受信部２２０は互いに離れており、同一の電磁波発信部２１０が照射した電磁波の反射波を受信する。このようにすると、物体検出装置１０による目的領域の検出精度は高くなる。 In the example shown in this figure, multiple, for example two, electromagnetic wave receiving units 220 are provided. These multiple electromagnetic wave receiving units 220 are spaced apart from each other, and receive reflected waves of electromagnetic waves emitted by the same electromagnetic wave emitting unit 210. In this way, the object detection device 10 can detect the target area with higher accuracy.

　反射波情報生成部２３０は、電磁波受信部２２０による受信結果を用いて反射波情報を生成する。反射波情報は、例えば反射波の強度の時系列情報を含んでいる。この時系列情報は、反射波の受信日時及びその時の反射波の強度の組み合わせを含んでいる。電磁波受信部２２０が複数設けられている場合、反射波情報生成部２３０は、複数の電磁波受信部２２０別に反射波情報を生成する。 The reflected wave information generating unit 230 generates reflected wave information using the reception results from the electromagnetic wave receiving unit 220. The reflected wave information includes, for example, time series information on the intensity of the reflected wave. This time series information includes a combination of the date and time the reflected wave was received and the intensity of the reflected wave at that time. If multiple electromagnetic wave receiving units 220 are provided, the reflected wave information generating unit 230 generates reflected wave information separately for each of the multiple electromagnetic wave receiving units 220.

　また、反射波情報生成部２３０は、測定装置２０の位置を示す位置情報を生成する。この位置情報は、例えばＧＰＳを用いて生成されてもよいし、他の方法、例えばＳＬＡＭ（Ｓｉｍｕｌｔａｎｅｏｕｓ　Ｌｏｃａｌｉｚａｔｉｏｎ　ａｎｄ　Ｍａｐｐｉｎｇ）を用いて行われてもよい。そして反射波情報生成部２３０は、反射波情報に、その反射波を受信した時の測定装置２０の位置情報を加える。 The reflected wave information generating unit 230 also generates location information indicating the location of the measuring device 20. This location information may be generated using, for example, GPS, or may be generated using other methods, such as SLAM (Simultaneous Localization and Mapping). The reflected wave information generating unit 230 then adds to the reflected wave information the location information of the measuring device 20 at the time the reflected wave was received.

　通信部２４０は、外部の装置と通信する。一例として、通信部２４０は反射波情報生成部２３０が生成した反射波情報を物体検出装置１０に送信する。この送信は、上記したようにバッチ式でもよいしリアルタイムでもよい。他の例として通信部２４０は、測定装置２０の移動を制御するための情報、例えば移動すべきルートを示すルート情報を受信する。この場合、測定装置２０の移動制御部は、測定装置２０の移動機構を制御することにより、測定装置２０を、受信したルート情報に従って移動させる。 The communication unit 240 communicates with external devices. As one example, the communication unit 240 transmits the reflected wave information generated by the reflected wave information generation unit 230 to the object detection device 10. This transmission may be in batches as described above, or in real time. As another example, the communication unit 240 receives information for controlling the movement of the measuring device 20, such as route information indicating the route along which the measuring device 20 should move. In this case, the movement control unit of the measuring device 20 controls the movement mechanism of the measuring device 20 to move the measuring device 20 according to the received route information.

　なお、位置情報は、反射波情報とは別の情報であってもよい。この場合、位置情報は、測定装置２０の位置の時系列情報になる。この時系列情報は、日時とその日時における測定装置２０の位置の組み合わせを含んでいる。この場合、通信部２４０は、位置情報も物体検出装置１０に送信する。 The position information may be information separate from the reflected wave information. In this case, the position information is time-series information on the position of the measuring device 20. This time-series information includes a combination of a date and time and the position of the measuring device 20 at that date and time. In this case, the communication unit 240 also transmits the position information to the object detection device 10.

　図４は、物体検出装置１０の機能構成の一例を示す図である。物体検出装置１０は、図１に示した３次元情報生成部１２０、２次元情報生成部１３０、及び検出部１４０の他に、通信部１１０及び記憶部１５０を備えている。 FIG. 4 is a diagram showing an example of the functional configuration of the object detection device 10. In addition to the three-dimensional information generation unit 120, the two-dimensional information generation unit 130, and the detection unit 140 shown in FIG. 1, the object detection device 10 also includes a communication unit 110 and a storage unit 150.

　通信部１１０は、外部の装置、例えば測定装置２０と通信する。例えば通信部１１０は、測定装置２０から反射波情報を受信すると、この反射波情報を記憶部１５０に記憶させる。測定装置２０から位置情報が送信された場合、通信部１１０は、この位置情報も記憶部１５０に記憶させる。 The communication unit 110 communicates with an external device, for example, the measuring device 20. For example, when the communication unit 110 receives reflected wave information from the measuring device 20, it stores this reflected wave information in the storage unit 150. When position information is transmitted from the measuring device 20, the communication unit 110 also stores this position information in the storage unit 150.

　３次元情報生成部１２０は、図１を用いて説明したように、反射波情報を処理することにより３次元情報を生成する。詳細には、反射波情報には反射波の強度及び測定装置２０の位置の時系列信号が含まれている。３次元情報生成部１２０は、例えば、この時系列信号を構成する反射波に対して複数回ＦＦＴ（Ｆａｓｔ　Ｆｏｕｒｉｅｒ　Ｔｒａｎｓｆｏｒｍ）を行うことにより、電磁波受信部２２０から反射波の起点となった反射点までの距離を算出する。電磁波受信部２２０が複数ある場合、３次元情報生成部１２０は、この処理を電磁波受信部２２０別に行う。そして３次元情報生成部１２０は、同一のタイミングで異なる電磁波受信部２２０で測定された反射波に基づいた複数の距離を統合することにより、対象領域に対応する３次元空間に含まれる少なくとも一つの第１の点について、反射波の強度の推定値を算出する。そして３次元情報生成部１２０は、この処理を複数のタイミングで測定された反射波に対して行うことにより、複数の第１の点のそれぞれについて、反射波の強度の推定値を算出し、これらを３次元情報とする。なお、この推定値は、当該第１の点に対象物体が存在する可能性を示す値とみなすことができる。以下、この値を第１の値とする。ただし、３次元情報の生成方法、例えば第１の値の生成方法はこの例に限定されない。 As described with reference to FIG. 1, the three-dimensional information generating unit 120 generates three-dimensional information by processing the reflected wave information. In detail, the reflected wave information includes a time series signal of the intensity of the reflected wave and the position of the measuring device 20. For example, the three-dimensional information generating unit 120 calculates the distance from the electromagnetic wave receiving unit 220 to the reflection point that is the origin of the reflected wave by performing FFT (Fast Fourier Transform) multiple times on the reflected wave that constitutes this time series signal. If there are multiple electromagnetic wave receiving units 220, the three-dimensional information generating unit 120 performs this processing for each electromagnetic wave receiving unit 220. The three-dimensional information generating unit 120 then integrates multiple distances based on the reflected waves measured by different electromagnetic wave receiving units 220 at the same timing to calculate an estimate of the intensity of the reflected wave for at least one first point included in the three-dimensional space corresponding to the target area. The three-dimensional information generating unit 120 performs this process on the reflected waves measured at multiple timings to calculate an estimate of the intensity of the reflected waves for each of the multiple first points, and uses these as three-dimensional information. Note that this estimate can be considered as a value indicating the possibility that a target object exists at the first point. Hereinafter, this value will be referred to as the first value. However, the method of generating the three-dimensional information, for example the method of generating the first value, is not limited to this example.

　２次元情報生成部１３０は、図１を用いて説明したように、３次元情報を所定の平面に投影することにより２次元情報を生成する。以下、この所定の平面を投影面と記載する。投影面が対象領域の地面に対してなす角度は１０°以下であるのが好ましい。すなわち、投影面は、対象領域の地面に水平であるのが好ましい。 As explained with reference to FIG. 1, the two-dimensional information generating unit 130 generates two-dimensional information by projecting three-dimensional information onto a predetermined plane. Hereinafter, this predetermined plane will be referred to as the projection plane. It is preferable that the angle that the projection plane makes with respect to the ground surface of the target area is 10° or less. In other words, it is preferable that the projection plane is horizontal to the ground surface of the target area.

　図５は、２次元情報生成部１３０が行う処理の一例を説明するための図である。２次元情報生成部１３０は、第２の点に対応する複数の第１の点を特定する。例えば２次元情報生成部１３０は、投影面に直角な方向から見た場合に、第２の点と重なる複数の第１の点を、当該第２の点に対応する第１の点とする。次いで２次元情報生成部１３０は、特定された複数の第１の点それぞれに対応する第１の値を特定し、当該第１の値を用いて、当該第２の点に前記対象物体が存在する可能性を示す第２の値を生成する。第２の値は、複数の第１の値の最大値でもよいし、平均値でもよい。また、第２の値は、第１の値が基準値を超えた第１の点のうち、最も地表に近い第１の点に対応する第１の値を、第２の値としても良い。そして２次元情報生成部１３０は、第２の点毎の第２の値を、２次元情報とする。言い換えると、２次元情報は、白黒の画像データとみなすことができる。 5 is a diagram for explaining an example of the process performed by the two-dimensional information generating unit 130. The two-dimensional information generating unit 130 identifies a plurality of first points corresponding to the second point. For example, the two-dimensional information generating unit 130 regards a plurality of first points that overlap with the second point when viewed from a direction perpendicular to the projection surface as the first points corresponding to the second point. Next, the two-dimensional information generating unit 130 identifies a first value corresponding to each of the identified plurality of first points, and uses the first value to generate a second value indicating the possibility that the target object exists at the second point. The second value may be the maximum value or the average value of the plurality of first values. In addition, the second value may be the first value corresponding to the first point closest to the ground surface among the first points whose first values exceed the reference value. The two-dimensional information generating unit 130 then regards the second value for each second point as two-dimensional information. In other words, the two-dimensional information can be regarded as black and white image data.

　図４に戻る。検出部１４０は、図１を用いて説明したように、２次元情報を処理することにより目的領域を検出する。例えば検出部１４０は、２次元情報に対して所定の画像処理を行うことにより、目的領域を検出する。この画像処理は、例えば、ＹＯＬＯ、ＳＳＤ（Ｓｉｎｇｌｅ　Ｓｈｏｔ　ＭｕｌｔｉＢｏｘ　Ｄｅｔｅｃｔｏｒ）、又はＦａｓｔｅｒ－ＲＣＮＮ（Ｒｅｇｉｏｎｓ　ｗｉｔｈ　Ｃｏｎｖｏｌｕｔｉｏｎａｌ　Ｎｅｕｒａｌ　Ｎｅｔｗｏｒｋｓ）であるが、これら以外であってもよい。 Returning to FIG. 4, the detection unit 140 detects the target region by processing the two-dimensional information as described with reference to FIG. 1. For example, the detection unit 140 detects the target region by performing a predetermined image processing on the two-dimensional information. This image processing is, for example, YOLO, SSD (Single Shot MultiBox Detector), or Faster-RCNN (Regions with Convolutional Neural Networks), but may be other than these.

　なお、物体検出装置１０は、対象領域の地質情報、及び前記反射波が生成された時の天候情報の少なくとも一方を用いて目的領域を検出してもよい。例えば対象領域のうち特定の領域の地質は、反射波を生成しやすいことがあり得る。また、天候によっては対象領域の地表に水や雪がたまり、反射波に影響を与えることがあり得る。物体検出装置１０は、この影響を、目的領域を選択する際に反映させる。 The object detection device 10 may detect the target area using at least one of geological information of the target area and weather information at the time the reflected waves were generated. For example, the geology of a particular area within the target area may be more conducive to generating reflected waves. Also, depending on the weather, water or snow may accumulate on the surface of the target area, affecting the reflected waves. The object detection device 10 takes this effect into account when selecting the target area.

　例えば３次元情報生成部１２０及び２次元情報生成部１３０の少なくとも一方は、その場所の地質に応じたパラメータを第１の値又は第２の値に乗じた上で、３次元情報又は２次元情報を生成する。このパラメータは予め設定されている。また３次元情報生成部１２０及び２次元情報生成部１３０の少なくとも一方は、測定時の天候に応じたパラメータを第１の値又は第２の値に乗じた上で、３次元情報又は２次元情報を生成する。このパラメータも予め設定されている。 For example, at least one of the three-dimensional information generating unit 120 and the two-dimensional information generating unit 130 multiplies a parameter corresponding to the geology of the location by a first value or a second value, and then generates three-dimensional information or two-dimensional information. This parameter is set in advance. At least one of the three-dimensional information generating unit 120 and the two-dimensional information generating unit 130 multiplies a parameter corresponding to the weather at the time of measurement by a first value or a second value, and then generates three-dimensional information or two-dimensional information. This parameter is also set in advance.

　なお、地質情報及び天候情報は、例えば情報処理装置１０の利用者によって情報処理装置１０に入力されるが、情報処理装置１０がこれらを記憶したデータベースから取得してもよい。 Note that the geological information and weather information are input to the information processing device 10 by, for example, a user of the information processing device 10, but the information processing device 10 may also obtain the information from a database in which the information processing device 10 stores the information.

　図６は、物体検出装置１０のハードウェア構成例を示す図である。物体検出装置１０は、バス１０１０、プロセッサ１０２０、メモリ１０３０、ストレージデバイス１０４０、入出力インタフェース１０５０、及びネットワークインタフェース１０６０を有する。 FIG. 6 is a diagram showing an example of the hardware configuration of the object detection device 10. The object detection device 10 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input/output interface 1050, and a network interface 1060.

　バス１０１０は、プロセッサ１０２０、メモリ１０３０、ストレージデバイス１０４０、入出力インタフェース１０５０、及びネットワークインタフェース１０６０が、相互にデータを送受信するためのデータ伝送路である。ただし、プロセッサ１０２０などを互いに接続する方法は、バス接続に限定されない。 The bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, input/output interface 1050, and network interface 1060 to transmit and receive data to and from each other. However, the method of connecting the processor 1020 and other components to each other is not limited to a bus connection.

　プロセッサ１０２０は、ＣＰＵ（Central Processing Unit）やＧＰＵ（Graphics Processing Unit）などで実現されるプロセッサである。 The processor 1020 is a processor realized by a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), etc.

　メモリ１０３０は、ＲＡＭ（Random Access Memory）などで実現される主記憶装置である。 Memory 1030 is a main storage device realized by RAM (Random Access Memory) or the like.

　ストレージデバイス１０４０は、ＨＤＤ（Hard Disk Drive）、ＳＳＤ（Solid State Drive）、メモリカードなどのリムーバブルメディア、又はＲＯＭ（Read Only Memory）などで実現される補助記憶装置であり、記録媒体を有している。ストレージデバイス１０４０の記録媒体は物体検出装置１０の各機能（例えば通信部１１０、３次元情報生成部１２０、２次元情報生成部１３０、及び検出部１４０）を実現するプログラムモジュールを記憶している。プロセッサ１０２０がこれら各プログラムモジュールをメモリ１０３０上に読み込んで実行することで、そのプログラムモジュールに対応する各機能が実現される。また、ストレージデバイス１０４０は記憶部１５０としても機能する。 The storage device 1040 is an auxiliary storage device realized by a removable medium such as a HDD (Hard Disk Drive), an SSD (Solid State Drive), a memory card, or a ROM (Read Only Memory), and has a recording medium. The recording medium of the storage device 1040 stores program modules that realize each function of the object detection device 10 (e.g., the communication unit 110, the three-dimensional information generation unit 120, the two-dimensional information generation unit 130, and the detection unit 140). The processor 1020 loads each of these program modules onto the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 also functions as a memory unit 150.

　入出力インタフェース１０５０は、物体検出装置１０と各種入出力機器とを接続するためのインタフェースである。 The input/output interface 1050 is an interface for connecting the object detection device 10 to various input/output devices.

　ネットワークインタフェース１０６０は、物体検出装置１０をネットワークに接続するためのインタフェースである。このネットワークは、例えばＬＡＮ（Local Area Network）やＷＡＮ（Wide Area Network）である。ネットワークインタフェース１０６０がネットワークに接続する方法は、無線接続であってもよいし、有線接続であってもよい。物体検出装置１０は、ネットワークインタフェース１０６０を介して測定装置２０と通信してもよい。 The network interface 1060 is an interface for connecting the object detection device 10 to a network. This network is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The method for connecting the network interface 1060 to the network may be a wireless connection or a wired connection. The object detection device 10 may communicate with the measurement device 20 via the network interface 1060.

　図７は、物体検出装置１０が行う処理の一例を示すフローチャートである。本図に示す例において、物体検出装置１０はバッチ式で処理を行う。 FIG. 7 is a flowchart showing an example of processing performed by the object detection device 10. In the example shown in this figure, the object detection device 10 performs processing in a batch manner.

　本図に示す処理とは別に、通信部１１０は、測定装置２０から繰り返し反射波情報を取得し、記憶部１５０に記憶させている。 In addition to the processing shown in this figure, the communication unit 110 repeatedly acquires reflected wave information from the measurement device 20 and stores it in the memory unit 150.

　まず３次元情報生成部１２０は、記憶部１５０から、今回の処理の対象となる対象領域の反射波情報を読み出し（ステップＳ１１０）、読み出した反射波情報を処理することにより３次元情報を生成する（ステップＳ１２０）。次いで２次元情報生成部１３０は、３次元情報を処理することにより２次元情報を生成する（ステップＳ１３０）。 First, the three-dimensional information generating unit 120 reads out reflected wave information of the target area to be processed this time from the storage unit 150 (step S110), and generates three-dimensional information by processing the read reflected wave information (step S120). Next, the two-dimensional information generating unit 130 processes the three-dimensional information to generate two-dimensional information (step S130).

　次いで検出部１４０は、２次元情報を処理することにより、目的領域を検出する。目的領域は、対象物体が存在している可能性が高い領域を２次元平面上で示したデータである（ステップＳ１４０）。ここで検出部１４０は、第２の点の座標に、この座標に対象物が存在している確率（信頼度）を紐づけた情報を、目的領域を示す情報としても良い。ここで用いられる確率は、第２の値であるが、第２の値を加工した値であってもよい。また検出部１４０は、投影面の座標毎に、この座標に対象物が存在している確率（信頼度）を紐づけた情報を生成してもよい。なお、検出部１４０は、表示装置に目的領域を示す画面を表示させてもよい。この表示装置は、物体検出装置１０の一部であってもよいし、物体検出装置１０の外部であってもよい。 Then, the detection unit 140 detects the target area by processing the two-dimensional information. The target area is data showing an area on a two-dimensional plane where the target object is likely to exist (step S140). Here, the detection unit 140 may use information in which the coordinates of the second point are linked to the probability (reliability) that the target object exists at these coordinates as information indicating the target area. The probability used here is a second value, but may also be a value obtained by processing the second value. The detection unit 140 may also generate information in which the probability (reliability) that the target object exists at each coordinate on the projection surface is linked to this coordinate. The detection unit 140 may display a screen showing the target area on a display device. This display device may be part of the object detection device 10 or may be external to the object detection device 10.

　以上、本実施形態によれば、物体検出装置１０の２次元情報生成部１３０は、３次元情報生成部１２０が生成した３次元情報を用いて２次元情報を生成する。この２次元情報は画像データとみなすことができる。そして検出部１４０は、この２次元情報を処理することにより、目的領域を検出する。このため、物体検出装置１０によれば、反射波情報に多くのノイズが含まれている場合でも、精度よく目的領域を検出できる。従って、調査の対象となる領域が広域となった場合でも調査時に必要な労力は少なくて済む。 As described above, according to this embodiment, the two-dimensional information generating unit 130 of the object detection device 10 generates two-dimensional information using the three-dimensional information generated by the three-dimensional information generating unit 120. This two-dimensional information can be considered as image data. The detection unit 140 then processes this two-dimensional information to detect the target area. Therefore, according to the object detection device 10, even if the reflected wave information contains a lot of noise, the target area can be detected with high accuracy. Therefore, even if the area to be investigated is large, less effort is required during the investigation.

（第２の実施形態）
　図８は、第２の実施形態に係る物体検出装置１０の機能構成の一例を示す図であり、第１の実施形態の図４に対応している。本実施形態に係る物体検出装置１０は、以下の点を除いて第１の実施形態に係る物体検出装置１０と同様の構成である。 Second Embodiment
Fig. 8 is a diagram showing an example of the functional configuration of the object detection device 10 according to the second embodiment, and corresponds to Fig. 4 of the first embodiment. The object detection device 10 according to this embodiment has the same configuration as the object detection device 10 according to the first embodiment, except for the following points.

　まず、物体検出装置１０は反射波情報処理部１６０を備えている。反射波情報処理部１６０は、反射波情報を、機械学習を用いて生成されたモデルを用いて処理する。そして検出部１４０は、２次元情報生成部１３０が生成した２次元情報と、反射波情報処理部１６０による処理結果を用いて目的領域を検出する。 First, the object detection device 10 includes a reflected wave information processing unit 160. The reflected wave information processing unit 160 processes the reflected wave information using a model generated using machine learning. The detection unit 140 then detects the target area using the two-dimensional information generated by the two-dimensional information generation unit 130 and the processing results by the reflected wave information processing unit 160.

　詳細には、反射波情報処理部１６０は、フーリエ変換部１６２、特徴抽出部１６４、及び識別部１６６を有している。 In detail, the reflected wave information processing unit 160 has a Fourier transform unit 162, a feature extraction unit 164, and an identification unit 166.

　フーリエ変換部１６２は、反射波情報をフーリエ変換することにより周波数信号を生成する。この周波数信号の一例は、スペクトログラム又はメルスペクトログラムであるが、これらに限定されない。 The Fourier transform unit 162 generates a frequency signal by performing a Fourier transform on the reflected wave information. An example of this frequency signal is a spectrogram or a mel spectrogram, but is not limited to these.

　特徴抽出部１６４は、フーリエ変換部１６２が生成した周波数信号を第１のモデルを用いて処理することにより、特徴を抽出する。詳細には、特徴抽出部１６４は、周波数信号のうち、３次元情報に含まれる第１の点に対応するデータを選択する。３次元情報に含まれる第１の点は、当該第１の点に対応する反射波情報の生成タイミングに紐づけられている。このため、特徴抽出部１６４は、この生成タイミングに対応する周波数信号を選択することができる。そして特徴抽出部１６４は、機械学習により生成された第１のモデルにこの周波数信号を入力することにより、特徴を抽出する。第１のモデルは、例えば周波数信号を説明変数として、特徴を目的変数とした機械学習により生成されている。なお、ここで用いられる機械学習の一例は畳込ニューラルネットワークであるが、これに限定されない。 The feature extraction unit 164 extracts features by processing the frequency signal generated by the Fourier transform unit 162 using a first model. In detail, the feature extraction unit 164 selects data from the frequency signal that corresponds to a first point included in the three-dimensional information. The first point included in the three-dimensional information is linked to the generation timing of the reflected wave information corresponding to the first point. Therefore, the feature extraction unit 164 can select a frequency signal that corresponds to this generation timing. The feature extraction unit 164 then inputs this frequency signal to a first model generated by machine learning, thereby extracting features. The first model is generated, for example, by machine learning using the frequency signal as an explanatory variable and the features as a target variable. Note that an example of machine learning used here is a convolutional neural network, but is not limited to this.

　識別部１６６は、特徴抽出部１６４が抽出した特徴を第２のモデルを用いて処理することにより、目的領域となり得る領域を検出する。具体的には、第２のモデルは、例えば全結合深層学習ネットワークによる識別器である。そして識別部１６６は、この識別器により、入力された特徴が異常であると判定された場合（例えば目的領域である確からしさが基準値以上となった場合）、入力された特徴に対応する第１の点が、対象物体が存在する領域すなわち目的領域であると判定する。そしてこの第１の点を２次元情報生成部１３０と同様の方法で投影面に投影することにより、２次元情報における目的領域を特定する。この際、識別部１６６は、２次元情報のもとになった投影面上の座標ごとに、目的領域である確からしさ（信頼度）も紐づけるするのが好ましい。 The identification unit 166 detects regions that may be the target region by processing the features extracted by the feature extraction unit 164 using a second model. Specifically, the second model is, for example, a classifier using a fully connected deep learning network. If the input feature is determined to be abnormal by this classifier (for example, if the likelihood of being the target region is equal to or greater than a reference value), the identification unit 166 determines that a first point corresponding to the input feature is a region where a target object exists, i.e., the target region. The first point is then projected onto a projection surface in the same manner as the two-dimensional information generation unit 130, thereby identifying the target region in the two-dimensional information. At this time, it is preferable that the identification unit 166 also associates the likelihood (reliability) of being the target region with each coordinate on the projection surface that is the basis of the two-dimensional information.

　そして検出部１４０は、第１の実施形態で示した方法を用いて目的領域を検出するとともに、この目的領域と、識別部１６６を用いて検出された目的領域を統合することにより、最終的な目的領域を検出する。例えば検出部１４０は、第１の実施形態で示した方法によって算出された座標別の信頼度と、識別部１６６により生成された座標別の信頼度の重みづけ平均値を算出し、この平均値が閾値以上となった領域を、最終的な目的領域としても良い。また検出部１４０は、第１の実施形態で示した方法によって算出された目的領域と、識別部１６６により生成された目的領域の和集合又は積集合を、最終的な目的領域としても良い。 The detection unit 140 then detects the destination region using the method shown in the first embodiment, and detects the final destination region by integrating this destination region with the destination region detected using the identification unit 166. For example, the detection unit 140 may calculate a weighted average of the reliability for each coordinate calculated using the method shown in the first embodiment and the reliability for each coordinate generated by the identification unit 166, and determine the region where this average is equal to or greater than a threshold as the final destination region. The detection unit 140 may also determine the union or intersection of the destination region calculated using the method shown in the first embodiment and the destination region generated by the identification unit 166 as the final destination region.

　本実施形態によっても、第１の実施形態と同様に、調査の対象となる領域が広域となった場合でも調査時に必要な労力は少なくて済む。また、反射波情報処理部１６０を有しているため、目的領域の検出精度は高くなる。 As with the first embodiment, this embodiment requires less effort when investigating a wide area. In addition, the presence of the reflected wave information processing unit 160 increases the accuracy of detecting the target area.

　以上、図面を参照して本発明の実施形態について述べたが、これらは本発明の例示であり、上記以外の様々な構成を採用することもできる。 The above describes the embodiments of the present invention with reference to the drawings, but these are merely examples of the present invention, and various configurations other than those described above can also be adopted.

　また、上述の説明で用いた複数のフローチャートでは、複数の工程（処理）が順番に記載されているが、各実施形態で実行される工程の実行順序は、その記載の順番に制限されない。各実施形態では、図示される工程の順番を内容的に支障のない範囲で変更することができる。また、上述の各実施形態は、内容が相反しない範囲で組み合わせることができる。 In addition, in the multiple flow charts used in the above explanations, multiple steps (processing) are described in order, but the order in which the steps are executed in each embodiment is not limited to the order described. In each embodiment, the order of the steps shown in the figures can be changed to the extent that does not cause any problems in terms of content. In addition, the above-mentioned embodiments can be combined to the extent that the content is not contradictory.

　上記の実施形態の一部または全部は、以下の付記のようにも記載されうるが、以下に限られない。
　１．対象領域へ照射された電磁波の反射波を示す反射波情報を処理することにより、前記対象領域に対応する３次元空間に含まれる複数の第１の点について、対象物体が存在する可能性を示す３次元情報を生成する３次元情報生成手段と、
　前記３次元情報を所定の平面に投影することにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成する２次元情報生成手段と、
　前記２次元情報を処理することにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出する検出手段と、
を備える物体検出装置。
２．上記１に記載の物体検出装置において、
　前記電磁波の周波数は０．３ＧＨｚ以上３００ＧＨｚ以下である、物体検出装置。
３．上記１又は２に記載の物体検出装置において、
　前記反射波情報は、前記電磁波を照射する照射手段及び前記反射波を受信する受信手段を有する、飛行体又は自走式の装置により生成される、物体検出装置。
４．上記１～３のいずれか一項に記載の物体検出装置において、
　前記３次元情報は、前記複数の第１の点毎に前記対象物体が存在する可能性を示す第１の値を含んでおり、
　前記２次元情報生成手段は、前記第２の点毎に、
　　当該第２の点に対応する複数の前記第１の点を特定し、
　　特定された前記複数の第１の点それぞれに対応する前記第１の値を特定し、当該第１の値を用いて、当該第２の点に前記対象物体が存在する可能性を示す第２の値を生成する、物体検出装置。
５．上記１～４のいずれか一項に記載の物体検出装置において、
　前記反射波情報を、機械学習を用いて生成されたモデルを用いて処理する反射波情報処理手段を備え、
　前記検出手段は、さらに前記モデルによる処理結果を用いて前記目的領域を検出する物体検出装置。
６．上記５に記載の物体検出装置において、
　前記反射波情報処理手段は、
　　前記反射波情報をフーリエ変換することにより周波数信号を生成し、
　　前記周波数信号を第１の前記モデルを用いて処理することにより、特徴を抽出し、
　　前記抽出された特徴を第２の前記モデルを用いて処理することにより、前記目的領域となり得る領域を検出する、物体検出装置。
７．上記１～６のいずれか一項に記載の物体検出装置において、
　前記対象領域は地面及びその下の地中であり、
　前記対象物体は、前記地面又は前記地中に存在する、物体検出装置。
８．上記７に記載の物体検出装置において、
　前記所定の平面が前記地面に対してなす角度は１０°以下である、物体検出装置。 A part or all of the above-described embodiments may be described as, but is not limited to, the following supplementary notes.
1. A three-dimensional information generating means for generating three-dimensional information indicating the possibility of the presence of a target object for a plurality of first points included in a three-dimensional space corresponding to a target area by processing reflected wave information indicating reflected waves of electromagnetic waves irradiated to the target area;
a two-dimensional information generating means for generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in a predetermined plane by projecting the three-dimensional information onto the predetermined plane;
a detection means for detecting a target region, which is a region in which the target object exists, of the target region by processing the two-dimensional information;
An object detection device comprising:
2. In the object detection device described in 1 above,
The object detection device, wherein the frequency of the electromagnetic wave is 0.3 GHz or more and 300 GHz or less.
3. In the object detection device according to 1 or 2 above,
An object detection device, wherein the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic wave and a receiving means for receiving the reflected wave.
4. In the object detection device according to any one of claims 1 to 3,
the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
The two-dimensional information generating means generates, for each of the second points,
identifying a plurality of the first points corresponding to the second point;
An object detection device that identifies the first value corresponding to each of the identified first points, and uses the first value to generate a second value indicating a possibility that the target object is present at the second point.
5. In the object detection device according to any one of claims 1 to 4,
A reflected wave information processing means processes the reflected wave information using a model generated by machine learning,
The detection means further detects the target region using the processing results of the model.
6. In the object detection device according to the above item 5,
The reflected wave information processing means
generating a frequency signal by performing a Fourier transform on the reflected wave information;
Processing the frequency signal with a first said model to extract features;
The object detection apparatus detects regions that may be the target regions by processing the extracted features using a second model.
7. In the object detection device according to any one of claims 1 to 6,
the target area is the ground and the subsurface therebelow;
An object detection device, wherein the target object is present on the ground or underground.
8. In the object detection device according to the above item 7,
An object detection device, wherein the angle between the specified plane and the ground is 10° or less.

９．コンピュータが、
　　対象領域へ照射された電磁波の反射波を示す反射波情報を処理することにより、前記対象領域を示す３次元空間に含まれる複数の第１の点毎に対象物体が存在する可能性を示す３次元情報を生成し、
　　前記３次元情報を所定の平面に投影することにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成し、
　　前記２次元情報を処理することにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出する、物体検出方法。
１０．上記９に記載の物体検出方法において、
　前記電磁波の周波数は０．３ＧＨｚ以上３００ＧＨｚ以下である、物体検出方法。
１１．上記９又は１０に記載の物体検出方法において、
　前記反射波情報は、前記電磁波を照射する照射手段及び前記反射波を受信する受信手段を有する、飛行体又は自走式の装置により生成される、物体検出方法。
１２．上記９～１１のいずれか一項に記載の物体検出方法において、
　前記３次元情報は、前記複数の第１の点毎に前記対象物体が存在する可能性を示す第１の値を含んでおり、
　前記コンピュータは、前記第２の点毎に、
　　当該第２の点に対応する複数の前記第１の点を特定し、
　　特定された前記複数の第１の点それぞれに対応する前記第１の値を特定し、当該第１の値を用いて、当該第２の点に前記対象物体が存在する可能性を示す第２の値を生成する、物体検出方法。
１３．上記９～１２のいずれか一項に記載の物体検出方法において、
　前記コンピュータは、
　　前記反射波情報を、機械学習を用いて生成されたモデルを用いて処理し、
　　さらに前記モデルによる処理結果を用いて前記目的領域を検出する物体検出方法。
１４．上記１３に記載の物体検出方法において、
　前記コンピュータは、
　　前記反射波情報をフーリエ変換することにより周波数信号を生成し、
　　前記周波数信号を第１の前記モデルを用いて処理することにより、特徴を抽出し、
　　前記抽出された特徴を第２の前記モデルを用いて処理することにより、前記目的領域となり得る領域を検出する、物体検出方法。
１５．上記９～１４のいずれか一項に記載の物体検出方法において、
　前記対象領域は地面及びその下の地中であり、
　前記対象物体は、前記地面又は前記地中に存在する、物体検出方法。
１６．上記１５に記載の物体検出方法において、
　前記所定の平面が前記地面に対してなす角度は１０°以下である、物体検出方法。 9. The computer:
generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area;
generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane;
an object detection method for detecting a target region, which is a region of the target region in which the target object exists, by processing the two-dimensional information;
10. In the object detection method according to claim 9,
The object detection method, wherein the frequency of the electromagnetic wave is 0.3 GHz or more and 300 GHz or less.
11. In the object detection method according to claim 9 or 10,
An object detection method, wherein the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic wave and a receiving means for receiving the reflected wave.
12. In the object detection method according to any one of claims 9 to 11,
the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
The computer, for each of the second points,
identifying a plurality of the first points corresponding to the second point;
A method for object detection comprising: identifying a first value corresponding to each of the identified first points; and using the first value to generate a second value indicating a possibility that the target object is present at the second point.
13. In the object detection method according to any one of claims 9 to 12,
The computer includes:
Processing the reflected wave information using a model generated using machine learning;
Further, the object detection method includes detecting the target region using the processing results of the model.
14. In the object detection method according to claim 13,
The computer includes:
generating a frequency signal by performing a Fourier transform on the reflected wave information;
Processing the frequency signal with a first said model to extract features;
and processing the extracted features with a second said model to detect regions that may be said regions of interest.
15. In the object detection method according to any one of claims 9 to 14,
the target area is the ground and the subsurface therebelow;
An object detection method, wherein the target object is present on the ground or underground.
16. In the object detection method according to claim 15,
An object detection method, wherein the angle between the predetermined plane and the ground is 10° or less.

１７．　コンピュータに、
　　対象領域へ照射された電磁波の反射波を示す反射波情報を処理させることにより、前記対象領域を示す３次元空間に含まれる複数の第１の点毎に対象物体が存在する可能性を示す３次元情報を生成させ、
　　前記３次元情報を所定の平面に投影させることにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成させ、
　　前記２次元情報を処理させることにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出させる、プログラム。
１８．上記１７に記載のプログラムにおいて、
　前記電磁波の周波数は０．３ＧＨｚ以上３００ＧＨｚ以下である、プログラム。
１９．上記１７又は１８に記載のプログラムにおいて、
　前記反射波情報は、前記電磁波を照射する照射手段及び前記反射波を受信する受信手段を有する、飛行体又は自走式の装置により生成される、プログラム。
２０．上記１７～１９のいずれか一項に記載のプログラムにおいて、
　前記３次元情報は、前記複数の第１の点毎に前記対象物体が存在する可能性を示す第１の値を含んでおり、
　前記コンピュータに、前記第２の点毎に、
　　当該第２の点に対応する複数の前記第１の点を特定させ、
　　特定された前記複数の第１の点それぞれに対応する前記第１の値を特定させ、当該第１の値を用いて、当該第２の点に前記対象物体が存在する可能性を示す第２の値を生成させる、プログラム。
２１．上記１７～２０のいずれか一項に記載のプログラムにおいて、
　前記コンピュータに、
　　前記反射波情報を、機械学習を用いて生成されたモデルを用いて処理させ、
　　さらに前記モデルによる処理結果を用いて前記目的領域を検出させるプログラム。
２２．上記２１に記載のプログラムにおいて、
　前記コンピュータに、
　　前記反射波情報をフーリエ変換させることにより周波数信号を生成させ、
　　前記周波数信号を第１の前記モデルを用いて処理させることにより、特徴を抽出させ、
　　前記抽出された特徴を第２の前記モデルを用いて処理させることにより、前記目的領域となり得る領域を検出させる、プログラム。
２３．上記１７～２２のいずれか一項に記載のプログラムにおいて、
　前記対象領域は地面及びその下の地中であり、
　前記対象物体は、前記地面又は前記地中に存在する、プログラム。
２４．上記２３記載のプログラムにおいて、
　前記所定の平面が前記地面に対してなす角度は１０°以下である、プログラム。
２５．上記１７～２４のいずれか一項に記載のプログラムを記録した記録媒体。 17. On the computer:
generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area;
generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane;
A program for detecting a target region, which is a region in which the target object exists, within the target region by processing the two-dimensional information.
18. In the program according to 17 above,
The program, wherein the frequency of the electromagnetic waves is 0.3 GHz or more and 300 GHz or less.
19. In the program according to 17 or 18 above,
A program in which the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic waves and a receiving means for receiving the reflected waves.
20. In the program according to any one of claims 17 to 19,
the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
the computer, for each of the second points,
identifying a plurality of the first points corresponding to the second points;
A program that identifies the first value corresponding to each of the identified first points, and generates a second value indicating a possibility that the target object is present at the second point using the first value.
21. In the program according to any one of claims 17 to 20,
The computer includes:
Processing the reflected wave information using a model generated using machine learning;
and a program for detecting the target region using the processing results of the model.
22. In the program according to 21 above,
The computer includes:
generating a frequency signal by performing a Fourier transform on the reflected wave information;
Processing the frequency signal with a first said model to extract features;
and processing the extracted features using a second said model to detect regions that may be the regions of interest.
23. In the program according to any one of claims 17 to 22,
the target area is the ground and the subsurface therebelow;
The target object is present on the ground or underground.
24. In the program according to 23 above,
The angle between the predetermined plane and the ground is 10° or less.
25. A recording medium having the program according to any one of claims 17 to 24 recorded thereon.

　この出願は、２０２３年３月３０日に出願された日本出願特願２０２３－０５５１０７号を基礎とする優先権を主張し、その開示の全てをここに取り込む。 This application claims priority based on Japanese Patent Application No. 2023-055107, filed on March 30, 2023, the entire disclosure of which is incorporated herein by reference.

１０　　　　物体検出装置
２０　　　　測定装置
１１０　　　　通信部
１２０　　　　３次元情報生成部
１３０　　　　２次元情報生成部
１４０　　　　検出部
１５０　　　　記憶部
１６０　　　　反射波情報処理部
１６２　　　　フーリエ変換部
１６４　　　　特徴抽出部
１６６　　　　識別部
２１０　　　　電磁波発信部
２２０　　　　電磁波受信部
２３０　　　　反射波情報生成部
２４０　　　　通信部 10 Object detection device 20 Measuring device 110 Communication unit 120 Three-dimensional information generation unit 130 Two-dimensional information generation unit 140 Detection unit 150 Storage unit 160 Reflected wave information processing unit 162 Fourier transform unit 164 Feature extraction unit 166 Identification unit 210 Electromagnetic wave transmission unit 220 Electromagnetic wave reception unit 230 Reflected wave information generation unit 240 Communication unit

Claims (20)

　対象領域へ照射された電磁波の反射波を示す反射波情報を処理することにより、前記対象領域に対応する３次元空間に含まれる複数の第１の点について、対象物体が存在する可能性を示す３次元情報を生成する３次元情報生成手段と、
　前記３次元情報を所定の平面に投影することにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成する２次元情報生成手段と、
　前記２次元情報を処理することにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出する検出手段と、
を備える物体検出装置。 a three-dimensional information generating means for generating three-dimensional information indicating a possibility that a target object exists for a plurality of first points included in a three-dimensional space corresponding to the target area by processing reflected wave information indicating reflected waves of electromagnetic waves irradiated to the target area;
a two-dimensional information generating means for generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in a predetermined plane by projecting the three-dimensional information onto the predetermined plane;
a detection means for detecting a target region, which is a region in which the target object exists, of the target region by processing the two-dimensional information;
An object detection device comprising: 　請求項１に記載の物体検出装置において、
　前記電磁波の周波数は０．３ＧＨｚ以上３００ＧＨｚ以下である、物体検出装置。 The object detection device according to claim 1 ,
The object detection device, wherein the frequency of the electromagnetic wave is 0.3 GHz or more and 300 GHz or less. 　請求項１又は２に記載の物体検出装置において、
　前記反射波情報は、前記電磁波を照射する照射手段及び前記反射波を受信する受信手段を有する、飛行体又は自走式の装置により生成される、物体検出装置。 3. The object detection device according to claim 1,
An object detection device, wherein the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic wave and a receiving means for receiving the reflected wave. 　請求項１から３のいずれか一項に記載の物体検出装置において、
　前記３次元情報は、前記複数の第１の点毎に前記対象物体が存在する可能性を示す第１の値を含んでおり、
　前記２次元情報生成手段は、前記第２の点毎に、
　　当該第２の点に対応する複数の前記第１の点を特定し、
　　特定された前記複数の第１の点それぞれに対応する前記第１の値を特定し、当該第１の値を用いて、当該第２の点に前記対象物体が存在する可能性を示す第２の値を生成する、物体検出装置。 The object detection device according to any one of claims 1 to 3,
the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
The two-dimensional information generating means generates, for each of the second points,
identifying a plurality of the first points corresponding to the second point;
An object detection device that identifies the first value corresponding to each of the identified first points, and uses the first value to generate a second value indicating a possibility that the target object is present at the second point. 　請求項１から４いずれか一項に記載の物体検出装置において、
　前記反射波情報を、機械学習を用いて生成されたモデルを用いて処理する反射波情報処理手段を備え、
　前記検出手段は、さらに前記モデルによる処理結果を用いて前記目的領域を検出する、物体検出装置。 The object detection device according to claim 1 ,
A reflected wave information processing means processes the reflected wave information using a model generated by machine learning,
The object detection device, wherein the detection means further detects the target region using a processing result by the model. 　請求項１から５いずれか一項に記載の物体検出装置において、
　前記対象領域は地面及びその下の地中であり、
　前記対象物体は、前記地面又は前記地中に存在する、物体検出装置。 The object detection device according to claim 1 ,
the target area is the ground and the subsurface therebelow;
An object detection device, wherein the target object is present on the ground or underground. 　請求項５に記載の物体検出装置において、
　前記反射波情報処理手段は、
　　前記反射波情報をフーリエ変換することにより周波数信号を生成し、
　　前記周波数信号を第１の前記モデルを用いて処理することにより、特徴を抽出し、
　　前記抽出された特徴を第２の前記モデルを用いて処理することにより、前記目的領域となり得る領域を検出する、物体検出装置。 The object detection device according to claim 5 ,
The reflected wave information processing means
generating a frequency signal by performing a Fourier transform on the reflected wave information;
Processing the frequency signal with a first said model to extract features;
The object detection apparatus detects regions that may be the target regions by processing the extracted features using a second model. 　請求項６に記載の物体検出装置において、
　前記所定の平面が前記地面に対してなす角度は１０°以下である、物体検出装置。 7. The object detection device according to claim 6,
An object detection device, wherein the angle between the specified plane and the ground is 10° or less. 　１以上のコンピュータが、
　　対象領域へ照射された電磁波の反射波を示す反射波情報を処理することにより、前記対象領域を示す３次元空間に含まれる複数の第１の点毎に対象物体が存在する可能性を示す３次元情報を生成し、
　　前記３次元情報を所定の平面に投影することにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成し、
　　前記２次元情報を処理することにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出する、物体検出方法。 One or more computers
generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area;
generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane;
an object detection method for detecting a target region, which is a region of the target region in which the target object exists, by processing the two-dimensional information; 　請求項９に記載の物体検出方法において、
　前記電磁波の周波数は０．３ＧＨｚ以上３００ＧＨｚ以下である、物体検出方法。 The object detection method according to claim 9,
The object detection method, wherein the frequency of the electromagnetic wave is 0.3 GHz or more and 300 GHz or less. 　請求項９又は１０に記載の物体検出方法において、
　前記反射波情報は、前記電磁波を照射する照射手段及び前記反射波を受信する受信手段を有する、飛行体又は自走式の装置により生成される、物体検出方法。 The object detection method according to claim 9 or 10,
An object detection method, wherein the reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic wave and a receiving means for receiving the reflected wave. 　請求項９から１１のいずれか一項に記載の物体検出方法において、
　前記３次元情報は、前記複数の第１の点毎に前記対象物体が存在する可能性を示す第１の値を含んでおり、
　前記１以上のコンピュータは、前記第２の点毎に、
　　当該第２の点に対応する複数の前記第１の点を特定し、
　　特定された前記複数の第１の点それぞれに対応する前記第１の値を特定し、当該第１の値を用いて、当該第２の点に前記対象物体が存在する可能性を示す第２の値を生成する、物体検出方法。 The object detection method according to any one of claims 9 to 11,
the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
The one or more computers, for each of the second points:
identifying a plurality of the first points corresponding to the second point;
A method for object detection comprising: identifying a first value corresponding to each of the identified first points; and using the first value to generate a second value indicating a possibility that the target object is present at the second point. 　請求項９から１２いずれか一項に記載の物体検出方法において、
　前記対象領域は地面及びその下の地中であり、
　前記対象物体は、前記地面又は前記地中に存在する、物体検出方法。 The object detection method according to any one of claims 9 to 12,
the target area is the ground and the subsurface therebelow;
An object detection method, wherein the target object is present on the ground or underground. 　請求項１３に記載の物体検出方法において、
　前記所定の平面が前記地面に対してなす角度は１０°以下である、物体検出方法。 The object detection method according to claim 13,
An object detection method, wherein the angle between the predetermined plane and the ground is 10° or less. 　コンピュータに、
　　対象領域へ照射された電磁波の反射波を示す反射波情報を処理させることにより、前記対象領域を示す３次元空間に含まれる複数の第１の点毎に対象物体が存在する可能性を示す３次元情報を生成させ、
　　前記３次元情報を所定の平面に投影させることにより、前記平面内に含まれる複数の第２の点毎に前記対象物体が存在する可能性を示す２次元情報を生成させ、
　　前記２次元情報を処理させることにより前記対象領域のうち前記対象物体が存在している領域である目的領域を検出させる、プログラムを記憶したコンピュータで読取可能な記録媒体。 On the computer,
generating three-dimensional information indicating a possibility that a target object exists for each of a plurality of first points included in a three-dimensional space indicating the target area by processing reflected wave information indicating a reflected wave of the electromagnetic wave irradiated to the target area;
generating two-dimensional information indicating a possibility that the target object exists for each of a plurality of second points included in the plane by projecting the three-dimensional information onto a predetermined plane;
A computer-readable recording medium storing a program for detecting a target area, which is an area in which the target object exists, within the target area by processing the two-dimensional information. 　請求項１５に記載の記録媒体において、
　前記電磁波の周波数は０．３ＧＨｚ以上３００ＧＨｚ以下である、プログラムを記憶したコンピュータで読取可能な記録媒体。 16. The recording medium according to claim 15,
A computer-readable recording medium storing a program, wherein the frequency of the electromagnetic waves is 0.3 GHz or more and 300 GHz or less. 　請求項１５又は１６に記載の記録媒体において、
　前記反射波情報は、前記電磁波を照射する照射手段及び前記反射波を受信する受信手段を有する、飛行体又は自走式の装置により生成される、プログラムを記憶したコンピュータで読取可能な記録媒体。 17. The recording medium according to claim 15 or 16,
The reflected wave information is generated by an aircraft or a self-propelled device having an irradiation means for irradiating the electromagnetic waves and a receiving means for receiving the reflected waves, and the reflected wave information is generated by a computer-readable recording medium having a program stored thereon. 　請求項１５から１７いずれか一項に記載の記録媒体において、
　前記３次元情報は、前記複数の第１の点毎に前記対象物体が存在する可能性を示す第１の値を含んでおり、
　前記コンピュータに、前記第２の点毎に、
　　当該第２の点に対応する複数の前記第１の点を特定させ、
　　特定された前記複数の第１の点それぞれに対応する前記第１の値を特定させ、当該第１の値を用いて、当該第２の点に前記対象物体が存在する可能性を示す第２の値を生成させる、プログラムを記憶したコンピュータで読取可能な記録媒体。 18. The recording medium according to claim 15,
the three-dimensional information includes a first value indicating a possibility that the target object exists for each of the plurality of first points;
the computer, for each of the second points,
identifying a plurality of the first points corresponding to the second points;
A computer-readable recording medium storing a program for identifying the first value corresponding to each of the identified multiple first points, and using the first value to generate a second value indicating the possibility that the target object is present at the second point. 　請求項１５から１８のいずれか一項に記載の記録媒体において、
　前記対象領域は地面及びその下の地中であり、
　前記対象物体は、前記地面又は前記地中に存在する、プログラムを記憶したコンピュータで読取可能な記録媒体。 19. The recording medium according to claim 15,
the target area is the ground and the subsurface therebelow;
The target object is a computer-readable recording medium having a program stored thereon, the computer-readable recording medium being present on the ground or underground. 　請求項１９に記載の記録媒体において、
　前記所定の平面が前記地面に対してなす角度は１０°以下である、プログラムを記憶したコンピュータで読取可能な記録媒体。 20. The recording medium according to claim 19,
A computer-readable recording medium storing a program, wherein the angle between the specified plane and the ground is 10° or less.
PCT/JP2024/002171 2023-03-30 2024-01-25 Object detection device, object detection method, and recording medium WO2024202467A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2023-055107 2023-03-30
JP2023055107 2023-03-30

Publications (1)

Publication Number Publication Date
WO2024202467A1 true WO2024202467A1 (en) 2024-10-03

Family

ID=92904995

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2024/002171 WO2024202467A1 (en) 2023-03-30 2024-01-25 Object detection device, object detection method, and recording medium

Country Status (1)

Country Link
WO (1) WO2024202467A1 (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000023762A1 (en) * 1998-10-21 2000-04-27 Omron Corporation Mine detector and inspection apparatus
JP2003098263A (en) * 2001-09-21 2003-04-03 Osaka Gas Co Ltd Method of surveying shielding body
JP2014032016A (en) * 2012-08-01 2014-02-20 Furuno Electric Co Ltd Representative position detecting device, display device, radar device, representative position detecting method, and representative position detecting program
JP2018132873A (en) * 2017-02-14 2018-08-23 株式会社デンソー Information processing device
JP2020085871A (en) * 2018-11-30 2020-06-04 すみえ 池田 Underground radar survey device
JP2021124290A (en) * 2020-01-31 2021-08-30 日本信号株式会社 Data processing method for underground radar, data processing program, and underground radar device
JP2022090607A (en) * 2020-12-07 2022-06-17 株式会社Ｃｑ－Ｓネット Virus sterilizer
WO2022230897A1 (en) * 2021-04-26 2022-11-03 株式会社計測技術サービス Information processing device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2000023762A1 (en) * 1998-10-21 2000-04-27 Omron Corporation Mine detector and inspection apparatus
JP2003098263A (en) * 2001-09-21 2003-04-03 Osaka Gas Co Ltd Method of surveying shielding body
JP2014032016A (en) * 2012-08-01 2014-02-20 Furuno Electric Co Ltd Representative position detecting device, display device, radar device, representative position detecting method, and representative position detecting program
JP2018132873A (en) * 2017-02-14 2018-08-23 株式会社デンソー Information processing device
JP2020085871A (en) * 2018-11-30 2020-06-04 すみえ 池田 Underground radar survey device
JP2021124290A (en) * 2020-01-31 2021-08-30 日本信号株式会社 Data processing method for underground radar, data processing program, and underground radar device
JP2022090607A (en) * 2020-12-07 2022-06-17 株式会社Ｃｑ－Ｓネット Virus sterilizer
WO2022230897A1 (en) * 2021-04-26 2022-11-03 株式会社計測技術サービス Information processing device

Similar Documents

Publication Publication Date Title
EP3663790B1 (en) Method and apparatus for processing radar data
CN111899568B (en) Bridge anti-collision early warning system, method and device and storage medium
US8982669B2 (en) Method for detecting objects
US12080060B2 (en) Method and system for indoor multipath ghosts recognition
CN109212531A (en) The method for determining target vehicle orientation
US20210018611A1 (en) Object detection system and method
JPH1164497A (en) Laser device
JP2017156219A (en) Tracking device, tracking method, and program
EP3167309B1 (en) Encoder-less lidar positioning technique for detection and alarm
US20190187253A1 (en) Systems and methods for improving lidar output
KR101968327B1 (en) Apparatus and method for compensating distance of track
JP5463875B2 (en) Aircraft position measurement system, response signal discrimination method and response signal discrimination program used in the system
KR102060286B1 (en) Radar object detection threshold value determination method using image information and radar object information generation device using the same
US20190187251A1 (en) Systems and methods for improving radar output
KR101868594B1 (en) Apparatus for Analyzing Topographic Line of Sight Using Radar Beam and Long Range Radar System
RU2659090C1 (en) Method of identificating of ground targets
WO2019186641A1 (en) Object detection device, vehicle, object detection method, and object detection program
WO2024202467A1 (en) Object detection device, object detection method, and recording medium
US20230003884A1 (en) Target object detection apparatus, target object detection method, and non-transitory computer-readable storage medium
WO2024202610A1 (en) Information processing device, information processing method, and recording medium
CN111693986A (en) Target object intrusion detection system
US20090297049A1 (en) Detection of partially occluded targets in ladar images
US20230110788A1 (en) Learning device, learning method, recording medium, and radar device
WO2024202611A1 (en) Object detection system, processing system, method for generating teacher data, object detection method, and recording medium
KR20210054769A (en) Radar signal prcessing apparatus and radar signal processing method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24778613

Country of ref document: EP

Kind code of ref document: A1