CN114200498A - Satellite navigation/optical combined target detection method and system - Google Patents
Satellite navigation/optical combined target detection method and system Download PDFInfo
- Publication number
- CN114200498A CN114200498A CN202210140871.8A CN202210140871A CN114200498A CN 114200498 A CN114200498 A CN 114200498A CN 202210140871 A CN202210140871 A CN 202210140871A CN 114200498 A CN114200498 A CN 114200498A
- Authority
- CN
- China
- Prior art keywords
- optical
- target
- satellite navigation
- optical cameras
- suspected
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 135
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 5
- 238000000691 measurement method Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 19
- 238000005259 measurement Methods 0.000 abstract description 7
- 230000009467 reduction Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000000513 principal component analysis Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012880 independent component analysis Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/48—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system
- G01S19/485—Determining position by combining or switching between position solutions derived from the satellite radio beacon positioning system and position solutions derived from a further system whereby the further system is an optical system or imaging system
-
- 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
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a satellite navigation/optical combined target detection method and a system, wherein at least two optical cameras are calibrated through satellite navigation signals to obtain the relative position relation between the optical cameras; at least two optical cameras simultaneously acquire images or videos of a designated area; processing the target image or video, detecting a target and acquiring three-dimensional position information of the target; processing the image or the video, detecting a suspected target and acquiring three-dimensional position information of the suspected target; adjusting the focal length of the optical camera according to the three-dimensional information of the target to obtain a clear image or video of the suspected target; and processing the suspected target clear image or video to complete the identification of the suspected target. The method can quickly and accurately measure the position of the suspected target, has low cost and high distance measurement precision, simultaneously introduces the satellite navigation positioning technology to calibrate the position of the optical camera, unifies a coordinate system and is convenient for quick deployment of the system.
Description
Technical Field
The invention relates to the field of satellite navigation, in particular to a satellite navigation/optical combined target detection method and system.
Background
Along with the rapid development of the unmanned aerial vehicle technology, the 'low-speed small' unmanned aerial vehicle adopting satellite positioning for navigation is rapid in development and wide in application, brings convenience to industrial production and mass consumption and entertainment, and simultaneously brings new threats to the existing air defense system, national security and social stability. The low-slow small unmanned aerial vehicle has the characteristics of low flying height, low flying speed and small flying volume, and brings certain difficulty to the detection of the unmanned aerial vehicle, the photoelectric means for the target detection and identification of the low-slow small unmanned aerial vehicle mainly comprises laser ranging, visible light imaging, infrared imaging and the like, the speed and the precision of the detection and identification of the photoelectric means are mainly limited by the imaging quality, and the requirements of large-area protection and quick identification cannot be met in a large-scale application scene.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a target detection method based on satellite navigation/optical combination, which solves the problem that the imaging quality restricts the recognition speed and the accuracy, and specifically adopts the following technical scheme:
a combined satellite navigation/optical target detection method comprises the following steps,
at least two optical cameras calibrated through satellite navigation signals acquire relative position relations among the optical cameras;
at least two optical cameras simultaneously acquire images or videos of a designated area;
processing the image or the video, detecting a suspected target and acquiring three-dimensional position information of the suspected target;
adjusting the focal length of the optical camera according to the three-dimensional position information of the suspected target to obtain a clear image or video of the suspected target;
and processing the suspected target clear image or video to complete the identification of the suspected target.
Furthermore, the at least two optical cameras are arranged at different positions, and the relative positions of the optical cameras realize high-precision calibration through a satellite navigation carrier phase measurement technology, wherein the method comprises the step of outputting the three-dimensional positions of the optical cameras by using a satellite navigation receiver; confirming a relative position relationship between the optical cameras according to the three-dimensional positions of the optical cameras; and calibrating the external parameters between the optical cameras by combining the relative position relation of the optical cameras and the internal parameters of the optical cameras.
Further, the detection of the suspected target is based on a moving target identification method, and the acquisition of the three-dimensional position information of the suspected target is based on a binocular vision principle.
Further, the three-dimensional position information is relative position information of the suspected target with respect to the optical camera, and after obtaining the absolute position of the optical camera, the three-dimensional position may be the absolute position of the suspected target.
Further, the identification of the suspected objects may be by conventional computer vision methods and/or neural network methods.
Further, the method also comprises the step of carrying out target identification according to the track information and/or the shape change information of the suspected target.
The invention also provides a satellite navigation/optical combined target detection system, which comprises at least two optical cameras, wherein the optical cameras are respectively connected with the control and processing unit, the optical cameras are connected with the satellite navigation receiver, the satellite navigation receiver receives satellite navigation signals and is used for calibrating the optical cameras and acquiring the relative position relation between the optical cameras, and the control and processing unit is used for controlling the optical cameras to acquire images or videos of suspected targets and perform identification processing.
Furthermore, the satellite navigation/optical combined target detection system comprises at least two optical cameras and a variable-focus camera, wherein the optical cameras and the variable-focus camera are respectively connected with the control and processing unit, and the optical cameras and the variable-focus camera are connected with the satellite navigation receiver.
Further, the optical cameras are distributed or integrally arranged, are arranged on the holder and are connected with the storage unit.
Further, the control and processing unit includes a recognition decision module.
Compared with the prior art, the invention has the advantages and positive effects that:
1. utilize satellite navigation positioning technology to mark optical camera mounted position fast, guaranteed the unity of optical camera coordinate system, not only reduced the degree of difficulty of coordinate system conversion, the quick deployment of the system of being convenient for simultaneously, optical camera carries out quick accurate measurement to the position of target, compares laser radar range finding mode cost lower, and the precision is higher than monocular camera range finding precision simultaneously.
2. The binocular ranging mode based on the optical camera is not limited by the recognition rate and the types of different objects, the variable-focus camera is guided to stare and track the suspicious object on the basis of accurate ranging, the high quality of a video or an image is guaranteed, and the problem that the recognition speed and the accuracy are difficult to take into account is solved.
Drawings
FIG. 1 is a flow chart of a method for detecting a target by satellite navigation/optics combination;
FIG. 2 is a diagram of a first embodiment of a combined satellite navigation/optical target detection system;
FIG. 3 is a diagram of a combined satellite navigation/optical target detection system according to a second embodiment;
FIG. 4 is a diagram of a third embodiment of a combined satellite navigation/optical target detection system;
FIG. 5 is a diagram of a target detection system of a satellite navigation/optics combination according to a fourth embodiment;
fig. 6 is a diagram of a combined satellite navigation/optical target detection system according to the fifth embodiment.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments of the specification, wherein the present invention provides a method and a system for detecting a target by combining satellite navigation and optics, and fig. 1 shows a schematic flow chart of the method of the embodiment, which includes:
a combined satellite navigation/optical target detection method comprises the following steps,
at least two optical cameras calibrated through satellite navigation signals acquire relative position relations among the optical cameras;
at least two optical cameras simultaneously acquire images or videos of a designated area;
processing the image or video, and when the suspected target exists in the designated area, acquiring the position of the suspected target in the same coordinate system by using a satellite navigation coordinate system through the relative position of an optical camera calibrated based on a satellite navigation signal, detecting the suspected target and acquiring the three-dimensional position information of the suspected target;
further, according to the three-dimensional information of the target, the focal length of the optical camera is adjusted, and a suspected target clear image or video is obtained;
and processing the suspected target clear image or video to complete the identification of the suspected target.
As shown in fig. 5, when the optical cameras are distributed, a satellite navigation receiver may be installed for each optical camera, and then a carrier phase measurement technique is used to obtain a high-precision relative position between the optical cameras, so as to complete calibration of the optical cameras; the satellite navigation receiver receives satellite navigation signals and is used for calibrating the optical cameras and acquiring the relative position relation between the optical cameras, and the control and processing unit is used for controlling the optical cameras to acquire images or videos of suspected targets and perform identification processing. Specifically, the optical camera may further include a satellite navigation receiver module, so long as the position calibration of the optical camera is achieved.
Specifically, the method includes a Real-Time Kinematic (RTK) and Precision Point Positioning (PPP) technologies, and a RTK-PPP technology combining the RTK and the PPP, and specifically includes the following steps: outputting the three-dimensional position of the optical camera with a satellite navigation receiver; confirming a relative position relationship between the optical cameras according to the three-dimensional positions of the optical cameras; and calibrating the external parameters between the optical cameras by combining the relative position relation of the optical cameras and the internal parameters of the optical cameras.
In this embodiment, the optical camera intrinsic parameters include camera focal length and pixel size; the external parameters comprise image coordinates and a three-dimensional coordinate transformation matrix; in this embodiment, the three-dimensional coordinate transformation matrix adopts a satellite navigation coordinate system based on the relative position of the optical camera calibrated by the satellite navigation signal. Therefore, the acquired images or videos of the suspected target are satellite navigation coordinate systems.
In another embodiment, as shown in fig. 6, at least one optical camera is positioned by a satellite navigation receiver to obtain absolute position information thereof.
In this embodiment, the at least two optical cameras are arranged at different positions, and the relative positions between the optical cameras are calibrated with high precision by a satellite navigation carrier phase measurement technology.
The invention utilizes the satellite navigation positioning technology to quickly calibrate the installation position of the optical camera, ensures the unification of the coordinate system of the optical camera, reduces the difficulty of the transformation of the coordinate system, is convenient for quick deployment of the system, quickly and accurately measures the position of a target by the optical camera, has lower cost compared with a laser and radar ranging mode by a satellite navigation receiver, and does not need complex three-dimensional coordinate processing calculation.
In this embodiment, the detection of the suspected target is based on a moving target identification method, the acquisition of the three-dimensional position information of the suspected target is based on a binocular vision principle, and the precision is higher than that of the distance measurement by a monocular camera. The moving object identification method refers to detection of a dynamic object image and comprises a background difference method, an inter-frame difference method, an optical flow method, a Gaussian mixture model, a codebook and the like.
Specifically, the three-dimensional position information of the suspected target is relative position information of the suspected target relative to the optical camera, and the position information or distance information of the target relative to the optical camera is calculated through the relative position between the three-dimensional position information of the suspected target relative to the optical camera and the calibrated optical camera;
in another embodiment, the three-dimensional position information is obtained from an absolute position of an optical camera. And calibrating the absolute position of the optical camera by a satellite navigation positioning technology, and further calculating the absolute position information of the target according to the three-dimensional position information of the target relative to the optical camera.
In the present embodiment, the position information includes distance information or/and horizontal coordinates; according to the position information, the pitch angle, the azimuth angle and the focal length of the target relative to the optical camera can be calculated; in particular, the optical camera is a variable focus camera. According to the target position information, the variable focus camera performs gaze tracking on the target to acquire a clear image or video of the target; when the imaging size of the target can meet the identification and classification requirements of the target, the focal length of the optical camera does not need to be adjusted.
In this embodiment, the suspected target may be identified by a conventional computer vision method and/or a neural network method. The suspected target can be identified by a neural network method such as a traditional computer vision method and deep learning, if the suspected target is a target needing early warning, the next step of control strategy is started, and the methods can be used in a superposition mode and used for mutually verifying the suspected target; or can be used independently and configured according to the actual requirements of users. Conventional computer vision methods include: subspace (linear dimensionality reduction) PCA (principal component analysis): main information of original data is reserved as much as possible, and redundant information is reduced; LDA (linear discriminant analysis): increasing the inter-class gap and decreasing the intra-class gap. Nonlinear dimension reduction: manifold learning, adding kernel functions. ICA (independent component analysis): compared with PCA, the method has the advantages of good effect, dependence on training test scenes, sensitivity to illumination, facial expression and posture, and insufficient generalization capability. HMM (hidden markov): it is more robust to changes in lighting, expression and pose than the previous algorithms.
The neural network method is a relatively novel image recognition technology, and is an image recognition method fusing a neural network algorithm on the basis of the traditional image recognition method. The neural network refers to an artificial neural network, that is, the neural network is not a real neural network owned by an animal, but is artificially generated by a human after simulating the animal neural network. In the neural network image recognition technology, a neural network image recognition model with genetic algorithm and BP network fused is very classical and has application in many fields. In an image recognition system, a neural network system is used, and generally, features of an image are extracted first, and then the features of the image are mapped to a neural network for image recognition and classification. Taking the automatic recognition technology of automobile photographing as an example, when the automobile passes through, the detection equipment of the automobile can sense the automobile. At the moment, the detection equipment can start the image acquisition device to acquire images of the front side and the back side of the automobile. After the image is acquired, the image must be uploaded to a computer for storage for identification. And finally, the license plate positioning module can extract license plate information, recognize characters on the license plate and display a final result. The template matching algorithm and the artificial neural network algorithm are used in the process of recognizing the characters on the license plate.
The method also comprises a nonlinear dimension reduction image identification technology, and the image identification technology of the computer is an abnormal high-dimensional identification technology. Regardless of the resolution of the image itself, the data it produces is often multidimensional, which presents significant difficulties for computer recognition. To allow computers to have efficient recognition capabilities, the most straightforward and effective method is dimension reduction. The dimensionality reduction is divided into linear dimensionality reduction and nonlinear dimensionality reduction. For example, Principal Component Analysis (PCA) and linear singular analysis (LDA) are common linear dimensionality reduction methods, and their features are simple and easy to understand. But the linear dimensionality reduction process is used for processing the whole data set, and the optimal low-dimensional projection of the whole data set is obtained. Through verification, the linear dimension reduction strategy is high in calculation complexity and occupies relatively more time and space, so that an image identification technology based on nonlinear dimension reduction is generated, and the method is an extremely effective nonlinear feature extraction method. The technology can find the nonlinear structure of the image and can reduce the dimension of the image on the basis of not destroying the intrinsic structure of the image, so that the image identification of a computer is carried out on the dimension as low as possible, and the identification rate is improved. For example, the dimensions required for facial image recognition systems are often high, and their complexity is undoubtedly a huge "disaster" for computers. Due to the uneven distribution of the face images in the high-dimensional space, human beings can obtain the face images with compact distribution through a nonlinear dimension reduction technology, and the efficiency of the face recognition technology is improved. In this embodiment, the method further includes identifying the trajectory information and/or the shape change information of the suspected object. Specifically, according to the clear image or video of the target, trajectory information, contour information, and shape change feature information of the suspected target may be extracted, and whether the suspected target is a target that needs to be determined is further identified.
The invention also provides a satellite navigation/optical combined target detection and recognition system, as shown in fig. 2, in the first embodiment, the detection and recognition system is composed of at least two optical cameras, the optical cameras are connected with a control and processing unit, the optical cameras are connected with a satellite navigation receiver, the satellite navigation receiver receives satellite navigation signals and is used for calibrating the optical cameras and obtaining the relative position relationship between the optical cameras, and the control and processing unit is used for controlling the optical cameras to obtain images or videos of suspected targets and perform recognition processing. Firstly, the optical camera carries out position calibration through a satellite navigation receiver, the control and processing unit controls the optical camera to simultaneously carry out image/video acquisition on a designated area, the control and processing unit carries out detection and identification processing on the image or the video, if other suspected targets are detected in the designated area, the three-dimensional position information of the suspected targets is further obtained based on the binocular vision principle, the three-dimensional position information is directly obtained through calculation in a satellite navigation coordinate system, the conversion between the optical/visual coordinate system and the satellite navigation coordinate system is not additionally carried out, the processing efficiency is improved, then the variable focus camera is guided to stare and track the suspected objects on the basis of accurate distance measurement according to the three-dimensional position information of the suspected targets, the focal length of the optical camera is adjusted, clear images or videos of the suspected targets are obtained, and the high quality of the images/videos is ensured, the problem that the identification speed and the identification accuracy are difficult to take into account is solved, the suspected target clear image or video is processed, the suspected target is identified, whether an illegal/malicious target (including an unmanned aerial vehicle) invades the designated area or not is found in time, and a strategy and a means for resisting the target are made in time.
In the second embodiment, as shown in fig. 3, the detection and recognition system is composed of at least two optical cameras and a zoom camera, and the optical cameras and the zoom camera are respectively connected with the control and processing unit. In this embodiment, at least two optical cameras are used only for binocular vision distance measurement, one zoom camera is specially arranged for adjusting the focal length of the camera, and when a suspected target is detected, the control and processing unit controls the zoom camera to adjust the focal length so as to acquire a clearer image/video of the suspected target.
In the third embodiment, as shown in fig. 4, the optical cameras are connected to the storage units respectively, and then connected to the control and processing unit; in this embodiment, the storage unit stores images/videos of the optical camera or the zoom camera, the control and processing unit may perform detection, identification and analysis through the storage unit, the storage unit may also be disposed in the control and processing unit, the control and processing unit may store the images/videos after detecting the images/identifications in the storage unit, or suspected objects identified by the control and processing unit, and the identified results are stored in the storage unit, so as to facilitate deep learning and continuously enrich a suspected object library in the control and processing unit.
In the fourth embodiment, as shown in fig. 5, when the optical cameras are distributed, a satellite navigation receiver may be installed for each optical camera, and then a carrier phase measurement technique is used to obtain a high-precision relative position between the optical cameras, so as to complete calibration; similar to the principle of the foregoing embodiment, the three-dimensional position information of the suspected target may be calculated based on the binocular vision principle by using 2 or more optical cameras that are completely independently distributed.
In the fifth embodiment, as shown in fig. 6, at least one optical camera is positioned by the satellite navigation receiver to obtain absolute position information thereof. It should be noted that, in this embodiment, the optical camera may be integrally provided, and is divided into 2 cameras, and the three-dimensional position information where the suspected target is located may still be calculated based on the principle of binocular vision.
The invention realizes the detection of the target by a satellite navigation/optical combination mode, and realizes the rapid calibration of the optical camera by a satellite navigation receiver, on one hand, the mode can ensure the rapid deployment and calibration of the detection equipment, and simultaneously, the cost is lower than that of a laser and radar ranging mode, and the precision is higher than that of a monocular camera ranging; the binocular ranging-based mode is not limited by the recognition rate and the types of different objects, and the focus-variable camera is guided to stare and track the suspicious object on the basis of accurate ranging, so that the high quality of images/videos is guaranteed, and the problem that the recognition speed and the accuracy are difficult to take into account is solved.
In conclusion, by the satellite navigation/optical combined target detection method and system, when the suspected target is the black-flying unmanned aerial vehicle, the unmanned aerial vehicle counter control strategy can be performed efficiently and accurately, so that the black-flying unmanned aerial vehicle can be efficiently attacked, and efficient guarantee is provided for a protection area/activity.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present invention, or modify equivalent embodiments to equivalent variations, without departing from the scope of the invention, using the teachings disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical spirit of the present invention should fall within the protection scope of the technical scheme of the present invention, unless the technical spirit of the present invention departs from the content of the technical scheme of the present invention.
Claims (10)
1. A combined satellite navigation/optical target detection method is characterized by comprising the following steps,
at least two optical cameras calibrated through satellite navigation signals acquire relative position relations among the optical cameras;
at least two optical cameras simultaneously acquire images or videos of a designated area;
processing the image or the video, detecting a suspected target and acquiring three-dimensional position information of the suspected target;
adjusting the focal length of the optical camera according to the three-dimensional position information of the suspected target to obtain a clear image or video of the suspected target;
and processing the suspected target clear image or video to complete the identification of the suspected target.
2. The object detection method of claim 1, wherein the at least two optical cameras are arranged at different positions, and the relative positions between the optical cameras are calibrated with high precision by a satellite navigation carrier phase measurement technique, which comprises outputting three-dimensional positions of the optical cameras by a satellite navigation receiver; confirming a relative position relationship between the optical cameras according to the three-dimensional positions of the optical cameras; and calibrating the external parameters between the optical cameras by combining the relative position relation of the optical cameras and the internal parameters of the optical cameras.
3. The method for detecting the target of claim 1, wherein the detection of the suspected target is based on a moving target identification method, and the obtaining of the three-dimensional position information of the suspected target is based on a binocular vision principle.
4. The object detection method according to claim 1, wherein the three-dimensional position information is relative position information of the suspected object with respect to an optical camera.
5. The object detection method of claim 1, wherein the three-dimensional position information is an absolute position of the suspected object obtained from an absolute position of an optical camera.
6. The method of claim 1, wherein the suspected objects are identified by conventional computer vision and/or neural network methods.
7. The method according to claim 5, further comprising performing object recognition based on trajectory information and/or shape change information of the suspected object.
8. The satellite navigation/optical combined target detection system is characterized by comprising at least two optical cameras, wherein the optical cameras are respectively connected with a control and processing unit, the optical cameras are connected with a satellite navigation receiver, the satellite navigation receiver receives satellite navigation signals and is used for calibrating the optical cameras and acquiring the relative position relation between the optical cameras, and the control and processing unit is used for controlling the optical cameras to acquire images or videos of suspected targets and perform recognition processing.
9. The object detection system of claim 8, comprising at least two optical cameras
And the optical camera and the zoom camera are respectively connected with the control and processing unit and are connected with the satellite navigation receiver.
10. The object detection system of claim 8, wherein the optical cameras are distributed or integrated, and are disposed in a pan-tilt and connected to the storage unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210140871.8A CN114200498A (en) | 2022-02-16 | 2022-02-16 | Satellite navigation/optical combined target detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210140871.8A CN114200498A (en) | 2022-02-16 | 2022-02-16 | Satellite navigation/optical combined target detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114200498A true CN114200498A (en) | 2022-03-18 |
Family
ID=80659025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210140871.8A Pending CN114200498A (en) | 2022-02-16 | 2022-02-16 | Satellite navigation/optical combined target detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114200498A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115278073A (en) * | 2022-07-25 | 2022-11-01 | 西安工业大学 | Unmanned aerial vehicle photoelectric detection system based on visual control technology |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104729482A (en) * | 2015-03-30 | 2015-06-24 | 中国人民解放军63655部队 | Ground tiny target detection system and ground tiny target detection method based on airship |
| CN108801274A (en) * | 2018-04-16 | 2018-11-13 | 电子科技大学 | A kind of terrestrial reference ground drawing generating method of fusion binocular vision and differential satellite positioning |
| CN109917413A (en) * | 2019-01-21 | 2019-06-21 | 苏州雷泰医疗科技有限公司 | An accurate navigation and positioning method of an intelligent transfer bed |
| US20190204427A1 (en) * | 2017-12-28 | 2019-07-04 | Lyft, Inc. | Sensor calibration facility |
| CN110443247A (en) * | 2019-08-22 | 2019-11-12 | 中国科学院国家空间科学中心 | A kind of unmanned aerial vehicle moving small target real-time detecting system and method |
| WO2020024079A1 (en) * | 2018-07-28 | 2020-02-06 | 合刃科技（深圳）有限公司 | Image recognition system |
| US20210263166A1 (en) * | 2020-02-21 | 2021-08-26 | Qualcomm Incorporated | Method and apparatus to determine relative location using gnss carrier phase |
-
2022
- 2022-02-16 CN CN202210140871.8A patent/CN114200498A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104729482A (en) * | 2015-03-30 | 2015-06-24 | 中国人民解放军63655部队 | Ground tiny target detection system and ground tiny target detection method based on airship |
| US20190204427A1 (en) * | 2017-12-28 | 2019-07-04 | Lyft, Inc. | Sensor calibration facility |
| CN108801274A (en) * | 2018-04-16 | 2018-11-13 | 电子科技大学 | A kind of terrestrial reference ground drawing generating method of fusion binocular vision and differential satellite positioning |
| WO2020024079A1 (en) * | 2018-07-28 | 2020-02-06 | 合刃科技（深圳）有限公司 | Image recognition system |
| CN109917413A (en) * | 2019-01-21 | 2019-06-21 | 苏州雷泰医疗科技有限公司 | An accurate navigation and positioning method of an intelligent transfer bed |
| CN110443247A (en) * | 2019-08-22 | 2019-11-12 | 中国科学院国家空间科学中心 | A kind of unmanned aerial vehicle moving small target real-time detecting system and method |
| US20210263166A1 (en) * | 2020-02-21 | 2021-08-26 | Qualcomm Incorporated | Method and apparatus to determine relative location using gnss carrier phase |
Non-Patent Citations (2)
| Title |
|---|
| 岳子涵: "无人机管制系统中的视觉识别技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 郑子儒: "《工程测量》", 30 August 2018, 中国建材工业出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115278073A (en) * | 2022-07-25 | 2022-11-01 | 西安工业大学 | Unmanned aerial vehicle photoelectric detection system based on visual control technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11922643B2 (en) | Vehicle speed intelligent measurement method based on binocular stereo vision system | |
| US11900619B2 (en) | Intelligent vehicle trajectory measurement method based on binocular stereo vision system | |
| Zhao et al. | Detection, tracking, and geolocation of moving vehicle from uav using monocular camera | |
| CN111476827B (en) | Target tracking method, system, electronic device and storage medium | |
| García et al. | Driver monitoring based on low-cost 3-D sensors | |
| CN108731587A (en) | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model | |
| CN104378582A (en) | Intelligent video analysis system and method based on PTZ video camera cruising | |
| Yang et al. | Panoramic UAV surveillance and recycling system based on structure-free camera array | |
| CN111144207B (en) | Human body detection and tracking method based on multi-mode information perception | |
| WO2014176485A1 (en) | Facial recognition method and apparatus | |
| CN114905512B (en) | Panoramic tracking and obstacle avoidance method and system for intelligent inspection robot | |
| Sun et al. | Obstacle Detection of Intelligent Vehicle Based on Fusion of Lidar and Machine Vision. | |
| Schumann et al. | An image processing pipeline for long range UAV detection | |
| CN105516661B (en) | Principal and subordinate's target monitoring method that fisheye camera is combined with ptz camera | |
| Hammer et al. | Automated object detection and tracking with a flash LiDAR system | |
| CN112800918A (en) | Identity recognition method and device for illegal moving target | |
| CN114200498A (en) | Satellite navigation/optical combined target detection method and system | |
| CN111402324B (en) | Target measurement method, electronic equipment and computer storage medium | |
| Guo et al. | Visibility detection based on the recognition of the preceding vehicle’s taillight signals | |
| Long et al. | A novel wide-area multiobject detection system with high-probability region searching | |
| Wu et al. | Multimodal collaboration networks for geospatial vehicle detection in dense, occluded, and large-scale events | |
| Bashir et al. | Video surveillance for biometrics: long-range multi-biometric system | |
| CN109492513B (en) | Face space duplication eliminating method for light field monitoring | |
| CN117830934A (en) | Road target tracking and identifying method and system based on millimeter wave radar and variable-focus camera | |
| Yang et al. | Multiview infrared target detection and localization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220318 |
|
| RJ01 | Rejection of invention patent application after publication |