CN111198371A - Forward-looking obstacle detection system - Google Patents
Forward-looking obstacle detection system Download PDFInfo
- Publication number
- CN111198371A CN111198371A CN202010139563.4A CN202010139563A CN111198371A CN 111198371 A CN111198371 A CN 111198371A CN 202010139563 A CN202010139563 A CN 202010139563A CN 111198371 A CN111198371 A CN 111198371A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- train
- distance
- rail
- information
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 69
- 238000012545 processing Methods 0.000 claims abstract description 37
- 230000004888 barrier function Effects 0.000 claims description 14
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 3
- 230000003137 locomotive effect Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 description 11
- 238000003384 imaging method Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 239000002390 adhesive tape Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000003897 fog Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000007787 solid Substances 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
- 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
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Image Analysis (AREA)
Abstract
The application discloses forward-looking obstacle detection system, including data acquisition device and control processing apparatus. The data acquisition device comprises an infrared light source module, an infrared image acquisition module, a visible light image acquisition module and a radar; the infrared image acquisition module is used for acquiring infrared images in the detection window in the advancing direction of the train, the visible light image acquisition module is used for acquiring visible light images in the detection window in the advancing direction of the train, the radar is used for measuring distance information between an obstacle and the train in a preset braking distance range in the advancing direction of the train by taking the train as a starting point, and the preset braking distance range is determined by the running speed and the braking deceleration of the train. And the control processing device is used for receiving the data information sent by the data acquisition device and outputting the detection result of the obstacles in the advancing direction of the train. The system effectively improves the identification accuracy of the obstacles in the advancing direction of the train.
Description
Technical Field
The application relates to the technical field of target detection, in particular to a forward-looking obstacle detection system.
Background
With the rapid increase of urban population, urban rail transit vehicles have the advantages of large passenger capacity, rapid operation, accurate arrival time, environmental protection, energy conservation and the like, effectively improve the urban traffic jam phenomenon, and become one of the main public transport means for urban trip.
It can be understood that the rail transit vehicle such as a subway has high running speed and long braking distance, and in the driving process, the obstacles in front of the running direction can be efficiently and accurately identified to assist the driver to drive so as to effectively reduce the occurrence probability of traffic accidents. In the related art, obstacle recognition on a driving path is performed on the basis of a visible light camera. However, the forward-looking obstacle detection system based on the visible light camera cannot provide a strong basis for the driver to judge the obstacle in front of the driving road section in severe environments such as dark environments, severe weather such as heavy fog, heavy rain, heavy snow and the like.
Disclosure of Invention
The application provides a forward-looking obstacle detection system, which improves the identification accuracy of obstacles in the advancing direction of a train.
In order to solve the above technical problems, embodiments of the present invention provide the following technical solutions:
in one aspect, the embodiment of the invention provides a forward-looking obstacle detection system, which comprises a data acquisition device and a control processing device;
the data acquisition device comprises an infrared light source module, an infrared image acquisition module, a visible light image acquisition module and a radar;
the control processing device is used for receiving the data information sent by the data acquisition device and outputting the detection result of the obstacle in the advancing direction of the train;
the infrared image acquisition module is used for acquiring infrared images positioned in the detection window in the advancing direction of the train, the visible light image acquisition module is used for acquiring visible light images positioned in the detection window in the advancing direction of the train, and the radar is used for measuring distance information between an obstacle and the train, wherein the obstacle is positioned at the starting point of the train and is within a preset braking distance range in the advancing direction of the train; the preset braking distance range is determined by the train running speed and the braking deceleration.
Optionally, the control processing device is configured to call an object recognition program instruction stored in the memory to perform the following operations:
identifying a rail area in the visible light image, and generating a limiting window of a front rail traveling area by taking the rail area as a horizontal reference plane and taking the normal direction of a rail curve as a height direction on the basis of the geometric dimension of the train;
performing two-waveband information fusion on the visible light image and the infrared image to generate a target detection image;
identifying the target object in the limit window of the target detection image to generate an initial target identification result;
removing the track area inherent equipment from the initial target identification result based on the pre-stored track area inherent equipment information to generate an obstacle identification result; the obstacle identification result comprises the number of obstacles and obstacle information contained in the target detection image, and the obstacle information comprises the length value, the height value and the distance value between the obstacle and the front end of the train;
and matching corresponding obstacles in the obstacle identification result according to the obstacle distance information sent by the radar to generate an obstacle detection result.
Optionally, the control processing device is configured to call the rail identification program instructions stored in the memory to perform the following operations:
extracting an ROI (region of interest) containing rails from the visible light image, and dividing the ROI into a plurality of sub-blocks;
calculating a spatial distance value of each pixel in the ROI from the center of a frame image;
according to Ω ═ Σ R αd+G*βd+B*γdCalculating local color system characteristic value omega of each sub-block of the ROI area, R, G, B is RGB color space value of each pixel in each sub-block αd、βd、γdThe weighted value is regulated and controlled by the spatial distance value of the pixel;
determining the probability of each sub-block containing the rail by utilizing a pre-trained shallow convolutional neural network based on the local color system characteristic value of each sub-block;
determining a target sub-block containing the rail according to a preset area judgment threshold value and the probability that each sub-block contains the rail;
and reconstructing each target sub-block based on the continuous correlation among the video frame image sequences to generate the rail area.
Optionally, the control processing device is configured to call an early warning program instruction stored in the memory to perform the following operations:
presetting a plurality of distance threshold ranges of different early warning levels, wherein each distance threshold range corresponds to unique level alarm information, the alarm information is represented on a vehicle in a sound form and comprises different sound decibels and sound types, and meanwhile, the alarm information is transmitted to a ground control center;
and comparing the current distance between the barrier and the train in the barrier detection result with the distance threshold ranges in real time, and generating a corresponding alarm instruction according to the alarm information.
Optionally, the control processing device is configured to call an intrusion early warning program instruction stored in the memory to perform the following operations:
and when detecting that the obstacle distance information sent by the radar cannot be successfully matched with the corresponding obstacle in the obstacle identification result, comparing the relation between the current distance between the obstacle and the train in the obstacle distance information and each intrusion distance threshold range in real time, and generating an alarm instruction according to corresponding alarm information.
Optionally, the device further comprises an alarm;
the alarm comprises a plurality of alarm units, and each alarm unit is used for carrying out alarm prompt according to the alarm instruction of the corresponding level sent by the control processing device.
Optionally, the device further comprises a full-automatic forced braking device;
the full-automatic forced braking device is used for being automatically triggered when the distance between the train and the barrier is smaller than a preset distance, so that the train can move forwards in a forced braking mode.
Optionally, the size of the outline of the obstacle is not less than 50cm x 50 cm.
Optionally, a storage device for storing obstacle image data and event log records is also included.
Optionally, the system further comprises a display for displaying the detected obstacle and the distance between the obstacle and the head of the train to a user in real time.
The technical scheme that this application provided's advantage lies in, adopts the data of multiple sensor collection to realize surveying the preceding barrier of train jointly. The active infrared imaging technology based on the infrared image acquisition module can clearly image under various illumination conditions, is not interfered by dim light/no light/hard light, has all-weather working capacity, is not influenced by severe weather environments such as rain, snow, fog and the like, and ensures the imaging quality under various working conditions; the visible light image acquisition module can provide images with higher resolution and richer details, can support the identification of station names, kilometers posts, signal lamps and other markers, and can be used for positioning and driving assistance; the machine vision and the radar are combined, so that the distance measurement accuracy between the barrier and the front end of the train in the advancing direction of the train can be improved, the identification accuracy of the barrier in the advancing direction of the train is effectively improved, the probability of occurrence of train traffic accidents is reduced, and the safe and stable operation of the train is guaranteed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the related art, the drawings required to be used in the description of the embodiments or the related art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a block diagram of an embodiment of a front view obstacle detection system according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of forward looking obstacle detection according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a monocular distance measurement network model according to an embodiment of the present invention;
fig. 4 is a block diagram of another embodiment of a forward looking obstacle detection system according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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 terms "first," "second," "third," "fourth," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may include other steps or elements not expressly listed.
Referring first to fig. 1, fig. 1 is a schematic diagram of a forward looking obstacle detection system in an embodiment of the present invention, and the embodiment of the present invention may include the following:
the forward-looking obstacle detection system may include a data acquisition device 1 and a control processing device 2, and the data acquisition device 1 and the control processing device 2 may perform data transmission and data communication through a switch 0. The data acquisition device 1 may include an infrared light source module 11, an infrared image acquisition module 12, a visible light image acquisition module 13, and a radar 14. The data acquisition device 1 acquires forward-looking data in the advancing direction of the train, including image data and distance data, by using each sensor, and transmits the acquired data to the control processing device 2. The infrared image acquisition module 12 and the visible light image acquisition module 13 can be installed in a cab, for example, above a ceiling and behind a transparent windshield so as to facilitate direct front imaging; the control processing device 2 may be mounted in a vehicle electrical cabinet, for example.
The infrared light source module 11 is used as a light supplement light source of the infrared image acquisition module 12, the number of light sources included in the infrared light source module 11 may be 1, and may also be the same as the number of infrared cameras in the infrared image acquisition module 12, which is not limited in this application. The light source can be a near-infrared laser light source, and can also be other types of light sources, and this does not influence the realization of this application, and near-infrared laser light source can be installed in the train roof for example. The infrared light source module 11 may be composed of a Near Infrared (NIR) laser light source and a laser driver, the irradiation distance may reach more than 250 meters, and after the light source power is increased, the irradiation distance may be further increased, thereby improving the image quality of the image acquired by the infrared image acquisition module 12.
The imaging unit of the data acquisition device 1 is integrated by the infrared image acquisition module 12 and the visible light image acquisition module 13, the infrared image acquisition module 12 is used for acquiring infrared images in the detection window in the advancing direction of the train, and the visible light image acquisition module 13 is used for acquiring visible light images in the detection window in the advancing direction of the train. The infrared image acquisition module 12 may include one or more infrared cameras, for example, each infrared camera may adopt a CMOS imaging sensor, and is integrated with a high-speed video camera and a processing board, and a laser light source is used for light supplement, so that clear imaging can be performed under various severe working conditions, and all-weather operation is guaranteed. The visible light image capturing module 13 may include, for example, 1 or more visible light cameras, and can image visible light bands, provide higher resolution images and richer details, and identify markers on the line, such as signal lights, station names, kilometers, and the like.
In the embodiment of the present invention, the radar 13 is used to measure the distance information between the train and the obstacle within the preset braking distance range in the advancing direction of the train with the train as the starting point. In order to improve the radar ranging distance and the ranging precision, the radar 13 can be a millimeter wave radar, the working frequency band of the millimeter wave radar is 30-300 GHz, the wavelength range of the millimeter wave radar is 1-10 mm generally, and the millimeter wave radar has the advantages of strong rain, snow, fog, smoke and dust penetrating capability, can work all day long, has strong anti-interference capability and high reliability in data acquisition. By the millimeter wave radar, the obstacle detection with the linear distance of 250 meters can be realized. Wherein the preset braking distance range is determined by the running speed of the train and the braking deceleration, for example, when the braking deceleration is 1m/s2When the running speed of the train is 80km/h, the preset braking distance is 246.9 m; when the braking deceleration is 1m/s2When the running speed of the train is 100km/h, the preset braking distance is 385.8 m; when the braking deceleration is 1m/s2And when the running speed of the train is 60km/h, the preset braking distance is 138.9 m. In the present application, the control processing device 2 is configured to receive data information sent by the data acquisition device, and output an obstacle detection result in a train advancing direction. The control processing device 2 is responsible for collecting infrared camera images, visible light camera images and radar data. Based on the acquired sensor data, the functions of obstacle detection and identification, obstacle positioning and the like can be completed. The control processing device 2 can be designed by adopting a 19-inch standard 3U case, and can be designed by adopting high integration and modularization, and any module can be independently plugged and unplugged. Data that infrared image collection module 12, visible light image collection module 13 and radar 14 gathered can be transmitted for control processing apparatus 2 like wifi through wireless, also can transmit for control processing apparatus 2 through wired modes such as communication cable, transmission bus, this application does not do any restriction to this.
It should be noted that the control processing device 2 may store an image processing algorithm capable of realizing target detection and tracking in any related technology in advance, identify a target in a visible light image or an infrared image by using the image processing algorithm implanted in advance, and then obtain distance information of the target from the train head by using radar ranging, so as to accurately detect an obstacle existing in the train advancing direction. In addition, the infrared image and the visible light image may also be fused, the fused image is used for target detection and tracking, and any technology of fusing the infrared image and the visible light image in the related technologies may be adopted, which is not limited in this application.
In the technical scheme provided by the embodiment of the invention, the detection of the obstacle in front of the train is realized by adopting data acquired by various sensors. The active infrared imaging technology based on the infrared image acquisition module can clearly image under various illumination conditions, is not interfered by dim light/no light/hard light, has all-weather working capacity, is not influenced by severe weather environments such as rain, snow, fog and the like, and ensures the imaging quality under various working conditions; the visible light image acquisition module can provide images with higher resolution and richer details, can support the identification of station names, kilometers posts, signal lamps and other markers, and can be used for positioning and driving assistance; the machine vision and the radar are combined, so that the distance measurement accuracy between the barrier and the front end of the train in the advancing direction of the train can be improved, the identification accuracy of the barrier in the advancing direction of the train is effectively improved, the probability of occurrence of train traffic accidents is reduced, and the safe and stable operation of the train is guaranteed.
In the foregoing embodiment, how to perform the target detection and the target tracking by the control processing device 2 is not limited, and with reference to the flowchart shown in fig. 2, a target tracking detection method provided in this embodiment may include the following steps:
the control processing device 2 may call the object recognition program instructions stored in the memory to perform the following operations:
the rail area is identified in the visible light image, and a bounding window of the forward-looking rail section is generated based on the train geometry, with the rail area as a horizontal reference plane and the normal direction of the rail curve as the elevation direction.
And carrying out two-waveband information fusion on the visible light image and the infrared image to generate a target detection image.
And identifying the target object in the limiting window of the target detection image to generate an initial target identification result.
The rail travel area specific device is removed from the initial target recognition result based on the rail travel area specific device information stored in advance, and an obstacle recognition result is generated. The obstacle identification result comprises the number of obstacles and obstacle information contained in the target detection image, and the obstacle information comprises the length value, the height value and the distance value between the obstacle and the front end of the train;
and matching corresponding obstacles in the obstacle identification result according to the obstacle distance information sent by the radar to generate an obstacle detection result.
Optionally, the image acquired by the camera of the visible light image acquisition module 1 may be preprocessed, for example, denoising, normalizing, etc., and then the rail contour line may be extracted from the visible light image by using the rail feature. The detection of the rail makes use of the following features: the rail is characterized by being parallel lines in three-dimensional space no matter whether the rail is a straight rail or a curve; the rail plane is substantially in a neutral position in the image/video taken by the camera; the rail has a certain color system discrimination (rgb or hsv color space) with the surrounding background; with the above-mentioned geometric and color features of the rail, the detection of the rail can be generally achieved by a line detection algorithm and conditional filtering of the geometric position.
The front view of the train shot by the camera is a perspective view, and two-dimensional mapping straight lines of the same physical three-dimensional height in the image/video shot by the camera at different distances from the camera can be determined according to a camera calibration program. This mapping does not change as the train is driven, as long as the camera remains stable or the camera is slightly shaken but can be self-adjusted by a corresponding algorithm. Therefore, on the basis of camera calibration, the width and the height of the limiting detection frame can be determined by combining the reference object on the line.
According to the relevant industry standard, the gauge of the rail is 1435 mm. According to the basic imaging principle, a short-distance object occupies more pixels, and a long-distance object occupies fewer pixels. But can be used as a stable reference because the spacing of the rails remains constant. After the track identification is realized, the rail can be extended to two sides by taking the rail as a reference according to a fixed proportion, so that a limit detection frame is generated.
It will be appreciated that the obstacles may include stationary obstacles for which a trajectory in the image is identified, and then a boundary is constructed with reference to the trajectory, a boundary window is formed, and an obstacle of the boundary window is detected. For the moving obstacles, the system can detect the moving obstacles and judge the invading moving objects by utilizing radar ranging information because the moving obstacles between the rails can influence the running of the train and the moving objects invading the rails can influence the running of the train.
Generally, there are pre-installed devices in the track area, that is, inherent devices in the track area, and in order to prevent the existing devices from being mistakenly reported as obstacles, the system may pre-establish a white list. At the beginning of system operation, images of installed equipment need to be collected in a line, feature extraction is carried out, and the images are used as matching bases. During the running process of the train, the area in the limiting window can be detected, and when the existence of an object is detected, the system calls the white list to perform feature matching. If the characteristics are matched with the objects in the white list, the equipment is judged to be installed; and if the characteristics are not matched with the white list, judging the obstacle.
The relative position of the moving object in the image can be changed, and the moving obstacle detection can be realized by tracking the relative position change of the feature points in the series of images. The moving obstacle includes a moving obstacle within the camera view field and a moving obstacle outside the camera view field, and the obstacle refers to a camera acquirable area such as a rail driving area. The moving obstacles in the camera vision field can be collected by the camera to form a visible light image or an infrared image, and then the real-time object distance judgment can be realized through a calibration and calculation algorithm of a monocular camera system. After calibration by the camera, the three-dimensional coordinates of the physical space can be mapped to the two-dimensional space of the camera. After the obstacle is detected, the two-dimensional coordinates of the obstacle in the image can be locked, and then the two-dimensional coordinates on the image are mapped to a real physical space through a mapping relation, so that the distance information of the obstacle can be obtained. For a moving object which has an intrusion tendency towards the rail, namely an object which cannot be collected by a camera, radar ranging information can be used for detecting distance information between the intruding moving object and the train, so that whether a foreign object enters the rail or has the tendency of entering the rail is accurately judged.
Optionally, the control processing device 2 may perform real-time calculation of the contour information and the horizontal distance information on the object within, for example, 250m, which is smaller than the preset braking distance range, for example, two times of calculation time is not longer than 40ms, in the process of calling the target recognition program instruction to recognize and track the target. The contour information refers to the horizontal length and the vertical height of a target object, which are two important factors influencing the running safety of the subway train. The size of the outline of an obstacle identifiable by the present application is not less than 50cm by 50 cm. Because the area of the far-end object passing through the optical sensing imaging area has fewer pixels and is more similar to the light spot, the similar imaging area of the far-end object can be estimated by designing the matching of the approximate area of the circle/ellipse, calculating the approximate length and height, and then converting the length in pixel coordinates into physical units in real space through the calibration coefficient of the visible light camera:
(x，y)＝Λ(ρ，v)
wherein, x and y are the physical length and height of the target object, Λ is the conversion relation between the camera space and the actual space, ρ and v are pixels of approximate length and height obtained by matching, and Λ can be determined by the calibration process of the camera.
The horizontal distance of the target object is the distance between a far-end object and the front locomotive of the train, and is one of important information for prompting drivers and passengers. The calculation and mutual verification of the horizontal distance information can be simultaneously carried out through the horizontal distance measurement of the monocular camera and the special gating function of the adopted infrared camera. The monocular distance measurement function can be implemented by using the multilayer connection neural network shown in fig. 3, without prior information of a scene or explicit camera parameter information. Coordinate information of a plurality of pixel points of an imaging area which is approximately matched is input, and horizontal distance information between the matching area and a camera can be well predicted through training of a certain number of samples.
The above implementation does not limit the track identification, and an embodiment of the present invention further provides a track identification method, which may include the following steps:
the control processing device 2 is used for calling the rail identification program instructions stored in the memory to execute the following operations:
an ROI area containing rails is extracted from the visible light image, and the ROI area is divided into a plurality of sub-blocks.
Calculating a spatial distance value of each pixel in the ROI from the center of the frame image; for example, the euclidean spatial distance calculation relation may be used to calculate the spatial distance value between each pixel point and the center of the frame image, and of course, other calculation methods may also be used, which do not affect the implementation of the present application.
According to Ω ═ Σ R αd+G*βd+B*γdCalculating the local color system characteristic value omega of each sub-block of the ROI area, R, G, B is the RGB color space value of each pixel in each sub-block αd、βd、γdThe weight value is regulated and controlled by the spatial distance value of the pixel. The relationship between the weight value and the pixel point space distance value can be calculated through a pre-trained shallow fully-connected neural network, and the color system characteristic of each block is obtained through the characteristic sum of the pixels.
And determining the probability that each subblock contains the rail by utilizing a pre-trained shallow convolutional neural network based on the local color system characteristic value of each subblock. The shallow convolutional neural network can be trained by utilizing the sample image, the local color system characteristic value of each sub-block in the sample image is known, and the probability of the sub-block containing the rail is known.
And determining a target sub-block containing the rail according to a preset area judgment threshold value and the probability that each sub-block contains the rail. For example, the judgment threshold values and the prior Gamma probabilities of the far, middle and near three regions of the image frame can be preset, and the posterior distribution of the threshold values can be determined through the learning of the samples. And finally, distinguishing the calculated probability by the three area judgment threshold values, and finally determining the area where the rail is located.
And reconstructing each target sub-block based on the continuous correlation among the video frame image sequences to generate the rail area. It will be appreciated that there is some continuous correlation between the sequence of video frame images, which is characterized by the rail identification region Θ of the previous framenFor the rail existence region Θ of the subsequent framen+1The following limitations are carried out: thetan+1＝Θn+ Gaussian (μ, σ), i.e., there is random Gaussian migration of the rail identification area of the previous and following frames; μ and σ are the mean and variance of this Gaussian determined by sample learning, and several subsequent image frames are determined by a Gaussian time series determined by continuous correlation.
As another alternative implementation, the application may also perform the classified warning based on the difference of the distance between the obstacle and the train, and may include the following:
the control processing device 2 is used for calling the early warning program instructions stored in the memory to execute the following operations:
the method comprises the steps that a plurality of distance threshold ranges of different early warning levels are preset, each distance threshold range corresponds to alarm information of a unique level, the alarm information is represented on a vehicle in a sound mode and comprises different sound decibels and sound types, and meanwhile the alarm information is transmitted to a ground control center.
And comparing the current distance between the barrier and the train in the barrier detection result with the distance threshold ranges in real time, and generating an alarm instruction according to corresponding alarm information.
In order to further improve the safety of the train, the application can also preset two brake deceleration rates, wherein one brake deceleration rate is a conventional brake deceleration rate, the other brake deceleration rate is an emergency brake deceleration rate, the emergency brake deceleration rate is greater than the conventional brake deceleration rate, and correspondingly, the emergency brake distance is smaller than the conventional automatic distance. For example, when braking conventionallyDeceleration is 1m/s2When the running speed of the train is 80km/h, the conventional braking distance is 246.9 m; when the emergency braking deceleration is 1.2m/s2And if the running speed of the train is 80km/h, the emergency braking distance is 205.8 m. Furthermore, the system can mark the safe distance in the image displayed for a driver or other workers according to the braking distance of the train, carry out graded early warning according to the distance between the barrier and the train, trigger braking if necessary, and guarantee the driving safety in all directions. In another embodiment, the control processing device 2 is further configured to call an intrusion warning program instruction stored in the memory to perform the following operations:
and when detecting that the obstacle distance information sent by the radar cannot be successfully matched with the corresponding obstacle in the obstacle identification result, comparing the relation between the current distance between the obstacle and the train in the obstacle distance information and each intrusion distance threshold range in real time, and generating an alarm instruction according to corresponding alarm information. The system can also utilize a high-resolution visible light camera to continuously monitor abnormal conditions on a short-distance line, such as short-distance fine foreign matters, trackside equipment states, platform area door abnormity/billboard abnormity/adhesive tape falling and the like; when the abnormity is found, a log record is generated, the position of the abnormal point is positioned, and the abnormal information is led into an operation maintenance department for line management and maintenance.
Accordingly, referring to fig. 4, the forward looking obstacle detection system may further include an alarm 3. The alarm 3 may include a plurality of alarm units, each of which is configured to perform an alarm prompt according to the alarm command of the corresponding level sent by the reception control processing device. Wherein, the alarm 3 can be installed on the left side or the right side of the cab main console.
As another alternative, in order to further improve the safety of train operation and reduce the accident probability, the forward-looking obstacle detection system may further include a full-automatic forced braking device 4. The full-automatic forced braking device 4 is used for being automatically triggered when the distance between the train and the obstacle is smaller than a preset safety distance, so that the train can advance forwards in a forced braking mode, for example, when the distance is smaller than 50m, the train is forcibly braked, the preset safety distance can be determined based on train operation parameters such as running speed and braking deceleration, the minimum value of the safety distance is that the train can stop sliding when the safety distance is finished, and the maximum speed of the train operation can be used as a standard when the safety distance is determined.
As another alternative, the forward looking obstacle detection system may further include a storage device 5, and the storage device 5 may be a solid state disk, for example. The storage device 5 may be used to store obstacle image data and event log records. That is, if the obstacle detection result output from the control processing device 2 indicates that an obstacle is present, the acquired image data or video data is automatically stored in the storage device 5. The event log records log information used for recording preset events, the events can be parking events, fault events and the like, accurate basis can be provided for train event positioning according to trackside markers, the trackside markers can be signboards recorded by numbers, Chinese characters or characters and the like, such as hectometer marks, arrival distance prompts, train station names and the like, and the train event positioning function can be realized by identifying information in the signboards by any character identification technology.
In addition, the forward-looking obstacle detection system can also comprise a display 6 for displaying the detected obstacles and the distance between the obstacles and the train head to a user in real time, information can be displayed to a driver in a visual form through the display, rich information is provided for safe driving of the driver, and safe driving of the driver is guaranteed.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
A forward looking obstacle detection system provided by the present application is described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present application.
Claims (10)
1. A forward-looking obstacle detection system is characterized by comprising a data acquisition device and a control processing device;
the data acquisition device comprises an infrared light source module, an infrared image acquisition module, a visible light image acquisition module and a radar;
the control processing device is used for receiving the data information sent by the data acquisition device and outputting the detection result of the obstacle in the advancing direction of the train;
the infrared image acquisition module is used for acquiring infrared images positioned in the detection window in the advancing direction of the train, the visible light image acquisition module is used for acquiring visible light images positioned in the detection window in the advancing direction of the train, and the radar is used for measuring distance information between an obstacle and the train, wherein the obstacle is positioned at the starting point of the train and is within a preset braking distance range in the advancing direction of the train; the preset braking distance range is determined by the train running speed and the braking deceleration.
2. The forward looking obstacle detection system of claim 1, wherein the control processing means is configured to invoke object recognition program instructions stored in memory to perform the following operations:
identifying a rail area in the visible light image, and generating a limiting window of a front rail traveling area by taking the rail area as a horizontal reference plane and taking the normal direction of a rail curve as a height direction on the basis of the geometric dimension of the train;
performing two-waveband information fusion on the visible light image and the infrared image to generate a target detection image;
identifying the target object in the limit window of the target detection image to generate an initial target identification result;
removing the track area inherent equipment from the initial target identification result based on the pre-stored track area inherent equipment information to generate an obstacle identification result; the obstacle identification result comprises the number of obstacles and obstacle information contained in the target detection image, and the obstacle information comprises the length value, the height value and the distance value between the obstacle and the front end of the train;
and matching corresponding obstacles in the obstacle identification result according to the obstacle distance information sent by the radar to generate an obstacle detection result.
3. The forward looking obstacle detection system of claim 2, wherein the control processing means is configured to invoke rail identification program instructions stored in the memory to perform the following operations:
extracting an ROI (region of interest) containing rails from the visible light image, and dividing the ROI into a plurality of sub-blocks;
calculating a spatial distance value of each pixel in the ROI from the center of a frame image;
according to Ω ═ Σ R αd+G*βd+B*γdCalculating local color system characteristic value omega of each sub-block of the ROI area, R, G, B is RGB color space value of each pixel in each sub-block αd、βd、γdThe weighted value is regulated and controlled by the spatial distance value of the pixel;
determining the probability of each sub-block containing the rail by utilizing a pre-trained shallow convolutional neural network based on the local color system characteristic value of each sub-block;
determining a target sub-block containing the rail according to a preset area judgment threshold value and the probability that each sub-block contains the rail;
and reconstructing each target sub-block based on the continuous correlation among the video frame image sequences to generate the rail area.
4. The forward looking obstacle detection system of claim 2, wherein the control processing means is configured to invoke pre-warning program instructions stored in memory to perform the following operations:
presetting a plurality of distance threshold ranges of different early warning levels, wherein each distance threshold range corresponds to unique level alarm information, the alarm information is represented on a vehicle in a sound form and comprises different sound decibels and sound types, and meanwhile, the alarm information is transmitted to a ground control center;
and comparing the current distance between the barrier and the train in the barrier detection result with the distance threshold ranges in real time, and generating a corresponding alarm instruction according to the alarm information.
5. The forward looking obstacle detection system of claim 2, wherein the control processing means is configured to invoke intrusion alert program instructions stored in the memory to perform the following operations:
and when detecting that the obstacle distance information sent by the radar cannot be successfully matched with the corresponding obstacle in the obstacle identification result, comparing the relation between the current distance between the obstacle and the train in the obstacle distance information and each intrusion distance threshold range in real time, and generating an alarm instruction according to corresponding alarm information.
6. The forward looking obstacle detection system of claim 4 or 5, further comprising an alarm;
the alarm comprises a plurality of alarm units, and each alarm unit is used for carrying out alarm prompt according to the alarm instruction of the corresponding level sent by the control processing device.
7. The forward looking obstacle detection system of any one of claims 1 to 4, further including a fully automatic positive braking device;
the full-automatic forced braking device is used for being automatically triggered when the distance between the train and the barrier is smaller than a preset distance, so that the train can move forwards in a forced braking mode.
8. The forward looking obstruction detection system of claim 7, wherein the obstruction has a profile dimension of no less than 50cm x 50 cm.
9. The forward looking obstacle detection system of claim 8, further comprising a storage device for storing obstacle image data and event log records.
10. The forward-looking obstacle detection system of claim 9, further comprising a display for presenting the detected obstacle and the distance of the obstacle from the locomotive of the train to a user in real-time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139563.4A CN111198371A (en) | 2020-03-03 | 2020-03-03 | Forward-looking obstacle detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139563.4A CN111198371A (en) | 2020-03-03 | 2020-03-03 | Forward-looking obstacle detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111198371A true CN111198371A (en) | 2020-05-26 |
Family
ID=70745205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010139563.4A Pending CN111198371A (en) | 2020-03-03 | 2020-03-03 | Forward-looking obstacle detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111198371A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753741A (en) * | 2020-06-28 | 2020-10-09 | 北京小眼探索科技有限公司 | Special vehicle auxiliary driving method and device based on deep learning and storage medium |
| CN111796285A (en) * | 2020-06-15 | 2020-10-20 | 北京汽车研究总院有限公司 | Obstacle detection method and apparatus for vehicle |
| CN111829484A (en) * | 2020-06-03 | 2020-10-27 | 江西江铃集团新能源汽车有限公司 | Target distance measuring and calculating method based on vision |
| CN112651343A (en) * | 2020-12-28 | 2021-04-13 | 哈尔滨市科佳通用机电股份有限公司 | Railway wagon brake beam breaking fault identification method based on image processing |
| CN112856170A (en) * | 2020-12-25 | 2021-05-28 | 河南科技大学 | Automatic device of grading of milk cow body condition |
| CN113158898A (en) * | 2021-04-22 | 2021-07-23 | 宝武集团鄂城钢铁有限公司 | Automatic height measurement method for molten iron tank car based on infrared imaging |
| CN113486783A (en) * | 2021-07-02 | 2021-10-08 | 浙江省交通投资集团有限公司智慧交通研究分公司 | Obstacle detection method and system for rail transit vehicle |
| CN113687438A (en) * | 2021-09-22 | 2021-11-23 | 汤恩智能科技(常熟)有限公司 | Anti-press foot detection method and terminal |
| CN113734120A (en) * | 2020-05-28 | 2021-12-03 | 比亚迪股份有限公司 | Vehicle control method and device and vehicle |
| CN113879234A (en) * | 2021-10-27 | 2022-01-04 | 北京星箭长空测控技术股份有限公司 | Special car assistant driving positioning system |
| CN113963327A (en) * | 2021-09-06 | 2022-01-21 | 阿波罗智能技术(北京)有限公司 | Obstacle detection method, device, autonomous vehicle, device and storage medium |
| CN114212122A (en) * | 2021-11-18 | 2022-03-22 | 哈尔滨恒通机械设备有限公司 | Station section special line shunting operation auxiliary system and method based on machine vision |
| CN114955880A (en) * | 2022-04-29 | 2022-08-30 | 弥费实业(上海)有限公司 | Overhead traveling crane walking safety monitoring system and overhead traveling crane |
| CN115123342A (en) * | 2022-06-20 | 2022-09-30 | 西南交通大学 | Railway special line pushing shunting safety early warning method, device and system |
| CN116109541A (en) * | 2021-11-09 | 2023-05-12 | 株洲中车时代电气股份有限公司 | Vehicle bottom oil-water identification system and method |
| CN116433883A (en) * | 2021-12-28 | 2023-07-14 | 上海泽高电子工程技术股份有限公司 | Rail vehicle positioning method and device |
| CN116750046A (en) * | 2023-08-03 | 2023-09-15 | 北京全路通信信号研究设计院集团有限公司 | Train obstacle warning methods, systems, devices, electronic equipment and storage media |
| CN117238143A (en) * | 2023-09-15 | 2023-12-15 | 北京卓视智通科技有限责任公司 | Traffic data fusion method, system and device based on radar double-spectrum camera |
| CN117975383A (en) * | 2024-04-01 | 2024-05-03 | 湖北经济学院 | Vehicle positioning and identifying method based on multi-mode image fusion technology |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204541A (en) * | 2016-06-29 | 2016-12-07 | 南京雅信科技集团有限公司 | The track foreign body intrusion detection method being combined with infrared light based on visible ray |
| CN108229270A (en) * | 2017-01-12 | 2018-06-29 | 北京市商汤科技开发有限公司 | For identifying the method, apparatus and electronic equipment of road from remote sensing images |
| CN109188460A (en) * | 2018-09-25 | 2019-01-11 | 北京华开领航科技有限责任公司 | Unmanned foreign matter detection system and method |
| CN109552366A (en) * | 2018-12-24 | 2019-04-02 | 西安思科赛德电子科技有限公司 | Locomotive vehicle-mounted railway barrier intelligent detecting alarm system and its method for early warning |
| CN109598187A (en) * | 2018-10-15 | 2019-04-09 | 西北铁道电子股份有限公司 | Obstacle recognition method, differentiating obstacle and railcar servomechanism |
| CN109664916A (en) * | 2017-10-17 | 2019-04-23 | 交控科技股份有限公司 | Using Vehicle Controller as the train operation control system of core |
| CN110719442A (en) * | 2019-10-12 | 2020-01-21 | 深圳市镭神智能系统有限公司 | Security monitoring system |
| CN211718518U (en) * | 2020-03-03 | 2020-10-20 | 杭州中车数字科技有限公司 | Forward-looking obstacle detection system |
-
2020
- 2020-03-03 CN CN202010139563.4A patent/CN111198371A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204541A (en) * | 2016-06-29 | 2016-12-07 | 南京雅信科技集团有限公司 | The track foreign body intrusion detection method being combined with infrared light based on visible ray |
| CN108229270A (en) * | 2017-01-12 | 2018-06-29 | 北京市商汤科技开发有限公司 | For identifying the method, apparatus and electronic equipment of road from remote sensing images |
| CN109664916A (en) * | 2017-10-17 | 2019-04-23 | 交控科技股份有限公司 | Using Vehicle Controller as the train operation control system of core |
| CN109188460A (en) * | 2018-09-25 | 2019-01-11 | 北京华开领航科技有限责任公司 | Unmanned foreign matter detection system and method |
| CN109598187A (en) * | 2018-10-15 | 2019-04-09 | 西北铁道电子股份有限公司 | Obstacle recognition method, differentiating obstacle and railcar servomechanism |
| CN109552366A (en) * | 2018-12-24 | 2019-04-02 | 西安思科赛德电子科技有限公司 | Locomotive vehicle-mounted railway barrier intelligent detecting alarm system and its method for early warning |
| CN110719442A (en) * | 2019-10-12 | 2020-01-21 | 深圳市镭神智能系统有限公司 | Security monitoring system |
| CN211718518U (en) * | 2020-03-03 | 2020-10-20 | 杭州中车数字科技有限公司 | Forward-looking obstacle detection system |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113734120A (en) * | 2020-05-28 | 2021-12-03 | 比亚迪股份有限公司 | Vehicle control method and device and vehicle |
| CN111829484B (en) * | 2020-06-03 | 2022-05-03 | 江西江铃集团新能源汽车有限公司 | Target distance measuring and calculating method based on vision |
| CN111829484A (en) * | 2020-06-03 | 2020-10-27 | 江西江铃集团新能源汽车有限公司 | Target distance measuring and calculating method based on vision |
| CN111796285A (en) * | 2020-06-15 | 2020-10-20 | 北京汽车研究总院有限公司 | Obstacle detection method and apparatus for vehicle |
| CN111753741A (en) * | 2020-06-28 | 2020-10-09 | 北京小眼探索科技有限公司 | Special vehicle auxiliary driving method and device based on deep learning and storage medium |
| CN111753741B (en) * | 2020-06-28 | 2024-03-15 | 北京小眼探索科技有限公司 | Special vehicle driving assisting method and device based on deep learning and storage medium |
| CN112856170A (en) * | 2020-12-25 | 2021-05-28 | 河南科技大学 | Automatic device of grading of milk cow body condition |
| CN112651343A (en) * | 2020-12-28 | 2021-04-13 | 哈尔滨市科佳通用机电股份有限公司 | Railway wagon brake beam breaking fault identification method based on image processing |
| CN113158898A (en) * | 2021-04-22 | 2021-07-23 | 宝武集团鄂城钢铁有限公司 | Automatic height measurement method for molten iron tank car based on infrared imaging |
| CN113486783A (en) * | 2021-07-02 | 2021-10-08 | 浙江省交通投资集团有限公司智慧交通研究分公司 | Obstacle detection method and system for rail transit vehicle |
| US12293574B2 (en) | 2021-09-06 | 2025-05-06 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Obstacle detection method, electronic device and storage medium |
| CN113963327B (en) * | 2021-09-06 | 2023-09-08 | 阿波罗智能技术(北京)有限公司 | Obstacle detection method, obstacle detection device, autonomous vehicle, apparatus, and storage medium |
| CN113963327A (en) * | 2021-09-06 | 2022-01-21 | 阿波罗智能技术(北京)有限公司 | Obstacle detection method, device, autonomous vehicle, device and storage medium |
| CN113687438A (en) * | 2021-09-22 | 2021-11-23 | 汤恩智能科技(常熟)有限公司 | Anti-press foot detection method and terminal |
| CN113879234A (en) * | 2021-10-27 | 2022-01-04 | 北京星箭长空测控技术股份有限公司 | Special car assistant driving positioning system |
| CN116109541A (en) * | 2021-11-09 | 2023-05-12 | 株洲中车时代电气股份有限公司 | Vehicle bottom oil-water identification system and method |
| CN116109541B (en) * | 2021-11-09 | 2025-07-25 | 株洲中车时代电气股份有限公司 | Vehicle bottom oil-water identification system and method |
| CN114212122A (en) * | 2021-11-18 | 2022-03-22 | 哈尔滨恒通机械设备有限公司 | Station section special line shunting operation auxiliary system and method based on machine vision |
| CN116433883A (en) * | 2021-12-28 | 2023-07-14 | 上海泽高电子工程技术股份有限公司 | Rail vehicle positioning method and device |
| CN114955880A (en) * | 2022-04-29 | 2022-08-30 | 弥费实业(上海)有限公司 | Overhead traveling crane walking safety monitoring system and overhead traveling crane |
| CN115123342A (en) * | 2022-06-20 | 2022-09-30 | 西南交通大学 | Railway special line pushing shunting safety early warning method, device and system |
| CN115123342B (en) * | 2022-06-20 | 2024-02-13 | 西南交通大学 | A safety early warning method, device and system for pushing and shunting trains on special railway lines |
| CN116750046A (en) * | 2023-08-03 | 2023-09-15 | 北京全路通信信号研究设计院集团有限公司 | Train obstacle warning methods, systems, devices, electronic equipment and storage media |
| CN117238143B (en) * | 2023-09-15 | 2024-03-22 | 北京卓视智通科技有限责任公司 | Traffic data fusion method, system and device based on radar double-spectrum camera |
| CN117238143A (en) * | 2023-09-15 | 2023-12-15 | 北京卓视智通科技有限责任公司 | Traffic data fusion method, system and device based on radar double-spectrum camera |
| CN117975383A (en) * | 2024-04-01 | 2024-05-03 | 湖北经济学院 | Vehicle positioning and identifying method based on multi-mode image fusion technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111198371A (en) | Forward-looking obstacle detection system | |
| CN108883725B (en) | Driving vehicle alarm system and method | |
| US7046822B1 (en) | Method of detecting objects within a wide range of a road vehicle | |
| CN111461088B (en) | Rail transit obstacle avoidance system based on image processing and target recognition | |
| US10699567B2 (en) | Method of controlling a traffic surveillance system | |
| CN106647776B (en) | Method and device for judging lane changing trend of vehicle and computer storage medium | |
| CN204632107U (en) | A Combined Vehicle Vehicle Identification System Based on Scanning Laser Range Finder | |
| WO2017145600A1 (en) | Image processing device, imaging device, mobile entity apparatus control system, image processing method, and program | |
| CN104331910A (en) | Track obstacle detection system based on machine vision | |
| KR20140104954A (en) | Method and device for identifying a braking situation | |
| CN111717243B (en) | Rail transit monitoring system and method | |
| CN108639108B (en) | Locomotive operation safety protection system | |
| CN107274678B (en) | A Kinect-based night traffic flow statistics and vehicle identification method | |
| CN104260723A (en) | Device and method for predicting motion state of vehicle behind by tracing | |
| WO2022267266A1 (en) | Vehicle control method based on visual recognition, and device | |
| CN110007669A (en) | A kind of intelligent driving barrier-avoiding method for automobile | |
| WO2017145605A1 (en) | Image processing device, image pickup device, moving body apparatus control system, image processing method, and program | |
| CN112896159A (en) | Driving safety early warning method and system | |
| CN116461571B (en) | Obstacle sensing system based on vision, radio frequency positioning and multi-line laser fusion | |
| CN113353071B (en) | Narrow area intersection vehicle safety auxiliary method and system based on deep learning | |
| CN114241447A (en) | Real-time obstacle detection method based on vehicle-mounted equipment | |
| CN109389060A (en) | A kind of vehicle week anti-collision warning method of view-based access control model | |
| KR20150096924A (en) | System and method for selecting far forward collision vehicle using lane expansion | |
| CN111985388B (en) | Pedestrian attention detection driving assistance system, device and method | |
| JP2022056153A (en) | Temporary stop detection device, temporary stop detection system, and temporary stop detection program |
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 |