CN115598656B - Obstacle detection method, device and system based on suspension track - Google Patents
Obstacle detection method, device and system based on suspension track Download PDFInfo
- Publication number
- CN115598656B CN115598656B CN202211598638.0A CN202211598638A CN115598656B CN 115598656 B CN115598656 B CN 115598656B CN 202211598638 A CN202211598638 A CN 202211598638A CN 115598656 B CN115598656 B CN 115598656B
- Authority
- CN
- China
- Prior art keywords
- track
- sensing device
- dadian
- lei
- data
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
-
- 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
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/60—Electric or hybrid propulsion means for production processes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a method, a device and a system for detecting obstacles based on a suspension track, and belongs to the technical field of track traffic overhaul. The obstacle detection method comprises the following steps: the method comprises the steps of configuring a sensing device, wherein the sensing device is arranged on an AGV trolley, and the AGV trolley is inversely hung on a hanging rail above a train to be detected; acquiring 3D Lei Dadian cloud data and camera data of a train roof to be detected based on the sensing device; fitting an off-track region based on the camera data; filtering out track areas in the 3D Lei Dadian cloud data; clustering the 3D Lei Dadian cloud data after the track area is filtered, and detecting an obstacle if the target object is aggregated. The method can accurately detect the obstacle on the train roof.
Description
Technical Field
The invention belongs to the technical field of rail transit maintenance, and particularly relates to a method, a device and a system for detecting obstacles based on a suspension rail.
Background
In recent years, with the rapid development of the rail transit industry in China, the running safety of trains is increasingly emphasized, and the cleaning and maintenance of train roofs are key points for ensuring the safe running of trains. The operation of the train roof comprises roof foreign matter detection, pantograph damage detection, insulator cleaning and the like, but due to the fact that the overhaul position is too high, roof parts are too many, high-voltage electricity is accompanied, the train is not easy to walk, if manual overhaul is used, accidents are easy to occur, and the risk is high. If intelligent maintenance and intelligent cleaning equipment auxiliary operation are adopted, the problem of operation safety of the AGV trolley can be caused due to factors such as unpredictable obstacle invasion.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method, a device and a system for detecting obstacles based on a suspension track.
The aim of the invention is realized by the following technical scheme:
according to a first aspect of the present invention, a suspension rail based obstacle detection method comprises:
the method comprises the steps of configuring a sensing device, wherein the sensing device is arranged on an AGV trolley, and the AGV trolley is inversely hung on a hanging rail above a train to be detected;
acquiring 3D Lei Dadian cloud data and camera data of a train roof to be detected based on the sensing device;
fitting an off-track region based on the camera data;
filtering out track areas in the 3D Lei Dadian cloud data;
clustering the 3D Lei Dadian cloud data after the track area is filtered, and detecting an obstacle if the target object is aggregated.
Further, configuring the sensing device includes:
configuring a detection area of a sensing device, wherein the sensing device comprises a 3D laser radar and an industrial camera;
calibrating external parameters of the 3D laser radar and the industrial camera in the sensing device so as to unify a coordinate system of 3D Lei Dadian cloud data acquired by the 3D laser radar and camera data acquired by the industrial camera;
the data acquisition frequencies of the 3D lidar and the industrial camera are configured to be the same frequency.
Further, the detection area is: x (0, D1+D2), y (- (W/2+D2), W/2+D2), z (- (R+D2), (H-R));
wherein, D1 is the braking distance of AGV dolly, and D2 is the redundant scope of predetermineeing, and W is the width of AGV dolly, and R is the distance of sensing device to wheel hub and track contact surface, and H is the height of AGV dolly.
Further, calibrating external parameters of the 3D laser radar and the industrial camera in the sensing device comprises the following steps:
taking the origin of the 3D laser radar as a coordinate reference, and simultaneously acquiring 3D Lei Dadian cloud data and camera data;
calibrating external parameters of the 3D laser radar and the industrial camera by using a Calibration Tool Kit tool kit in an automatic tool to obtain a 4*4 external parameter matrix;
the 4*4 extrinsic matrix is configured into the coordinate parameters of the 3D lidar.
Further, fitting an off-track region based on the camera data includes:
selecting RIO areas from the camera data;
edge detection is carried out in the RIO area by utilizing a sobel operator, so that contour data of an image are obtained;
performing multiple times of function fitting on the contour data of the image to obtain a rail trend;
and coloring the fitted rail track direction to obtain a fitted rail region.
Further, filtering out the track area in the 3D Lei Dadian cloud data includes:
and filtering out the track area in the 3D Lei Dadian cloud data by using a straight-through filtering algorithm.
Further, clustering the 3D Lei Dadian cloud data after filtering the track area includes:
based on European clustering algorithm, clustering is carried out on the 3D Lei Dadian cloud data after the track area is filtered.
Further, the suspension rail is a circular rail or a linear rail.
According to a second aspect of the present invention, a suspension rail based obstacle detecting apparatus includes:
the data acquisition module is used for acquiring the 3D Lei Dadian cloud data and the camera data of the train roof to be detected, which are acquired by the sensing device, wherein the sensing device is arranged on an AGV trolley which is inversely hung on a hanging rail above the train to be detected;
the track fitting module is used for fitting an out-of-track area based on the camera data;
and the obstacle detection module is used for filtering out the track area in the 3D Lei Dadian cloud data, clustering the 3D Lei Dadian cloud data after the track area is filtered out, and detecting an obstacle if the target object is aggregated.
According to a third aspect of the invention, a suspension track based obstacle detection system comprises:
the suspension rail is positioned above the train to be detected;
the AGV trolley is inversely hung on the hanging rail;
the sensing device is arranged on the AGV trolley and is used for collecting 3D Lei Dadian cloud data and camera data of the roof of the train to be detected;
the obstacle detection device is used for acquiring the 3D Lei Dadian cloud data and the camera data acquired by the sensing device, fitting out the track area based on the camera data, filtering the track area in the 3D Lei Dadian cloud data, clustering the 3D Lei Dadian cloud data after the track area is filtered, and detecting an obstacle if a target object is polymerized.
The beneficial effects of the invention are as follows:
(1) The method can accurately detect the obstacle on the roof of the train, thereby solving the problem of the operation safety of the AGV trolley caused by unpredictable obstacle invasion and other factors when adopting intelligent maintenance and intelligent cleaning equipment for auxiliary operation under specific scenes such as vehicle sections, machine service sections and the like in the field of rail transit;
(2) According to the invention, the data acquired by the 3D laser radar and the industrial camera in real time are used as obstacle avoidance data sources, the image algorithm is more mature and stable for track line fitting, the anti-interference capability of the 3D laser radar sensor is stronger, the recognition accuracy of a target is higher, and the obstacle detection function can be more reliable by adopting a multi-sensor fusion mode.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for detecting an obstacle according to the present invention;
FIG. 2 is a schematic view of one embodiment of a hanger rail of the present invention;
FIG. 3 is a schematic view of one embodiment of the position of the sensing device on the AGV of the present invention;
FIG. 4 is a block diagram illustrating an embodiment of an obstacle detecting apparatus according to the present invention;
in the figure, a 1-hanging track, a 2-AGV trolley, a 21-sensing device and a 3-train to be inspected.
Detailed Description
The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by a person skilled in the art without any inventive effort, are intended to be within the scope of the present invention, based on the embodiments of the present invention.
Referring to fig. 1-4, the present embodiment provides a method, a device and a system for detecting an obstacle based on a suspension track:
a first aspect of the present invention provides a method for detecting an obstacle based on a hanging track, as shown in fig. 1, including steps S100 to S500. The following is a detailed description.
Step S100, configuring a sensing device 21, wherein the sensing device 21 is arranged on an AGV trolley 2, and the AGV trolley 2 is reversely hung on a hanging rail 1 above a train 3 to be checked.
Specifically, the AGV trolley 2 is configured to drive the sensing device 21 to move on the hanging rail 1.
When the suspension track 1 is a circular track or a linear track, the detection of two trains can be realized without moving the train 3 to be detected. As shown in fig. 2, two trains to be detected 3 are arranged in parallel below the circular track, and the agc trolley 2 moves one circle on the circular track, so that the two trains can be detected.
In some embodiments, configuring the sensing device 21 includes:
step s110. Configuring a detection area of a sensing device 21, wherein the sensing device 21 comprises a 3D lidar and an industrial camera.
Specifically, according to the overall dimension of the AGV trolley 2, a region (namely a detection region) which needs to be detected by the 3D laser radar and the industrial camera is set, and the detection regions of the 3D laser radar and the industrial camera are the same. For example, as shown in fig. 3, the size of the AGV trolley 2 is length, width, height=l×w×h, the distance from the sensing device 21 to the hub and track contact surface is R, the braking distance of the AGV trolley 2 is D1, the redundant range of the detection area is D2, and then the detection area is: x (0, D1+D2), y (- (W/2+D2), W/2+D2), z (- (R+D2), (H-R)). The redundant range is increased when the detection area is set in the present embodiment, and the influence of the detection accuracy of the sensing device 21 is avoided. The detection area range is based on a 3D laser radar coordinate system, and the description of the 3D laser radar coordinate system is as follows: taking the forward direction of the AGV trolley as the positive direction of the x-axis, the right side of the AGV as the positive direction of the y-axis, and the upper side of the AGV as the positive direction of the z-axis, as shown in FIG. 3; the relationship between the AGV coordinate system and the 3D lidar coordinate system in FIG. 3 is fixed and can be converted to each other. In the embodiment, the data volume is reduced by setting the detection area, so that the data processing time is shortened, and the real-time performance of obstacle detection is improved; meanwhile, the detection area is arranged, so that the influence of foreign matters outside the track can be eliminated, and the false alarm rate is reduced.
And S120, calibrating external parameters of the 3D laser radar and the industrial camera in the sensing device 21 so as to unify a coordinate system of the 3D Lei Dadian cloud data acquired by the 3D laser radar and the camera data acquired by the industrial camera.
Specifically, the origin of the 3D laser radar is used as a coordinate reference, 3D Lei Dadian cloud data and camera data are collected at the same time, the external parameters of the 3D laser radar and the industrial camera are calibrated by using a Calibration Tool Kit tool kit in an automatic tool to obtain 4*4 external parameter matrixes, and the 4*4 external parameter matrixes are configured in the coordinate parameters of the 3D laser radar.
And S130, configuring the data acquisition frequencies of the 3D laser radar and the industrial camera to be the same frequency.
Specifically, in this embodiment, the data acquisition frequencies of the 3D lidar and the industrial camera are configured to be the same frequency, so that the two data acquired by the 3D lidar and the industrial camera (the 3D Lei Dadian cloud data and the camera data) are data with matched time stamps.
Step S200, acquiring 3D Lei Dadian cloud data and camera data of the roof of the train 3 to be inspected based on the sensing device 21.
For example, the AGV trolley 2 runs on the hanging rail 1, the 3D lidar in the sensing device 21 collects point cloud data of the roof of the train 3 to be inspected to obtain 3D Lei Dadian cloud data, and the industrial camera in the sensing device 21 collects image data of the roof of the train 3 to be inspected to obtain camera data.
And S300, fitting an derailment area based on the camera data.
In some embodiments, fitting an off-track region based on the camera data includes:
and S310, selecting RIO areas from the camera data.
And S320, performing edge detection in the RIO area by utilizing a sobel operator to obtain the contour data of the image.
S330, performing multiple function fitting on the contour data of the image to obtain the track trend.
And S340, coloring the fitted rail track direction to obtain a fitted rail region.
And S400, filtering out the track area in the 3D Lei Dadian cloud data.
In some embodiments, a cut-through filtering algorithm is utilized to filter out track regions in the 3D Lei Dadian cloud data.
And S500, clustering the 3D Lei Dadian cloud data after the track area is filtered, and detecting an obstacle if the target object is aggregated.
Specifically, if the target object is polymerized, an obstacle is detected, which means that the part of the roof of the train 3 to be detected, which is positioned in the moving direction of the AGV trolley 2, has an obstacle, the AGV trolley 2 stops moving, and the sensing device 21 sends out an alarm; if the target object is not polymerized, no obstacle is detected, which means that the part of the roof of the train 3 to be detected, which is positioned in the moving direction of the AGV 2, is free of the obstacle, and the detection operation can be continued.
In some embodiments, 3D Lei Dadian cloud data after filtering out the track region is clustered based on an euro-type clustering algorithm. For example, for a certain point P in space, k points closest to the point P are found through a KD-Tree neighbor search algorithm, and the points with the distances smaller than a set threshold value are clustered into a set Q. If the number of elements in the set Q is not increasing, the whole clustering process is ended; otherwise, the points other than p points are selected from the set Q, and the process is repeated until the number of elements in the set Q is not increased.
A second aspect of the present invention provides an obstacle detection device based on a hanging track, as shown in fig. 4, including a step data acquisition module, a track fitting module, and an obstacle detection module.
The data acquisition module is used for acquiring the 3D Lei Dadian cloud data and the camera data of the roof of the train to be detected 3, which are acquired by the sensing device 21, wherein the sensing device 21 is arranged on the AGV trolley 2, and the AGV trolley 2 is hung on the hanging rail 1 above the train to be detected 3 in an inverted mode. In this embodiment, a specific description of the method for collecting 3D Lei Dadian cloud data and camera data may refer to the description of step S100 and step S200.
And the track fitting module is used for fitting an out-track area based on the camera data. In this embodiment, the track fitting module may be used to perform step S300 shown in fig. 1, and specific description of the track fitting module may refer to step S300.
And the obstacle detection module is used for filtering out the track area in the 3D Lei Dadian cloud data, clustering the 3D Lei Dadian cloud data after the track area is filtered out, and detecting an obstacle if the target object is aggregated. In this embodiment, the obstacle detection module may be used to perform step S400 and step S500 shown in fig. 1, and specific description of the obstacle detection module may refer to step S400 and step S500.
A third aspect of the present invention provides a suspension rail based obstacle detection system comprising a suspension rail 1, an AGV car 2, a sensing device 21 and an obstacle detection device.
The suspension rail 1 is located above the train 3 to be inspected. In particular, the suspension rail 1 may be a circular rail or a linear rail.
The sensing device 21 is installed on the AGV trolley 2, and the sensing device 21 is used for collecting 3D Lei Dadian cloud data and camera data of the roof of the train 3 to be detected. Specifically, the sensing device 21 includes a 3D lidar and an industrial camera, the detection areas of the 3D lidar and the industrial camera are the same, the frequencies of data collected by the 3D lidar and the industrial camera are the same, the 3D lidar is used for collecting 3D Lei Dadian cloud data, and the industrial camera is used for collecting camera data.
The obstacle detection device is used for acquiring the 3D Lei Dadian cloud data and the camera data acquired by the sensing device 21, fitting an orbit area based on the camera data, filtering the orbit area in the 3D Lei Dadian cloud data, clustering the 3D Lei Dadian cloud data after filtering the orbit area, and detecting an obstacle if a target object is polymerized.
Specifically, fitting an off-track region based on the camera data includes: and selecting an RIO region from the camera data, performing edge detection on the RIO region by using a sobel operator to obtain contour data of an image, performing multiple function fitting on the contour data of the image to obtain a rail trend, and coloring the fitted rail trend to obtain a fitted rail region.
Specifically, a direct filtering algorithm is utilized to filter out the track area in the 3D Lei Dadian cloud data; based on European clustering algorithm, clustering is carried out on the 3D Lei Dadian cloud data after the track area is filtered.
The foregoing is merely a preferred embodiment of the invention, and it is to be understood that the invention is not limited to the form disclosed herein but is not to be construed as excluding other embodiments, but is capable of numerous other combinations, modifications and environments and is capable of modifications within the scope of the inventive concept, either as taught or as a matter of routine skill or knowledge in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (8)
1. An obstacle detection method based on a suspension track, comprising:
the method comprises the steps of configuring a sensing device, wherein the sensing device is arranged on an AGV trolley, and the AGV trolley is inversely hung on a hanging rail above a train to be detected; the suspension track is an annular track or a linear track;
acquiring 3D Lei Dadian cloud data and camera data of a train roof to be detected based on the sensing device;
fitting an off-track region based on the camera data;
filtering out track areas in the 3D Lei Dadian cloud data;
clustering the 3D Lei Dadian cloud data after the track area is filtered, and if the target object is polymerized, detecting an obstacle;
configuring a sensing device comprising:
configuring a detection area of a sensing device, wherein the sensing device comprises a 3D laser radar and an industrial camera;
calibrating external parameters of the 3D laser radar and the industrial camera in the sensing device so as to unify a coordinate system of 3D Lei Dadian cloud data acquired by the 3D laser radar and camera data acquired by the industrial camera;
the data acquisition frequencies of the 3D lidar and the industrial camera are configured to be the same frequency.
2. The obstacle detection method based on suspended tracks as claimed in claim 1, wherein the detection area is: x (0, D1+D2), y (- (W/2+D2), W/2+D2), z (- (R+D2), (H-R));
wherein, D1 is the braking distance of AGV dolly, and D2 is the redundant scope of predetermineeing, and W is the width of AGV dolly, and R is the distance of sensing device to wheel hub and track contact surface, and H is the height of AGV dolly.
3. The obstacle detection method based on suspended tracks as claimed in claim 1, wherein calibrating external parameters of the 3D lidar and the industrial camera in the sensing device comprises:
taking the origin of the 3D laser radar as a coordinate reference, and simultaneously acquiring 3D Lei Dadian cloud data and camera data;
calibrating external parameters of the 3D laser radar and the industrial camera by using a Calibration Tool Kit tool kit in an automatic tool to obtain a 4*4 external parameter matrix;
the 4*4 extrinsic matrix is configured into the coordinate parameters of the 3D lidar.
4. The hanging track based obstacle detection method of claim 1, wherein fitting an derailment region based on the camera data comprises:
selecting RIO areas from the camera data;
edge detection is carried out in the RIO area by utilizing a sobel operator, so that contour data of an image are obtained;
performing multiple times of function fitting on the contour data of the image to obtain a rail trend;
and coloring the fitted rail track direction to obtain a fitted rail region.
5. The hanging track-based obstacle detection method of claim 1, wherein filtering out track areas in the 3D Lei Dadian cloud data comprises:
and filtering out the track area in the 3D Lei Dadian cloud data by using a straight-through filtering algorithm.
6. The obstacle detection method based on hanging rails according to claim 1, wherein clustering the 3D Lei Dadian cloud data after filtering out the rail region comprises:
based on European clustering algorithm, clustering is carried out on the 3D Lei Dadian cloud data after the track area is filtered.
7. Obstacle detection device based on hang track, its characterized in that includes:
the data acquisition module is used for acquiring the 3D Lei Dadian cloud data and the camera data of the train roof to be detected, which are acquired by the sensing device, wherein the sensing device is arranged on an AGV trolley which is inversely hung on a hanging rail above the train to be detected;
the track fitting module is used for fitting an out-of-track area based on the camera data;
the obstacle detection module is used for filtering out the track area in the 3D Lei Dadian cloud data, clustering the 3D Lei Dadian cloud data with the track area filtered out, and detecting an obstacle if a target object is aggregated;
the configuration method of the sensing device comprises the following steps: configuring a detection area of a sensing device, wherein the sensing device comprises a 3D laser radar and an industrial camera; calibrating external parameters of the 3D laser radar and the industrial camera in the sensing device so as to unify a coordinate system of 3D Lei Dadian cloud data acquired by the 3D laser radar and camera data acquired by the industrial camera; the data acquisition frequencies of the 3D lidar and the industrial camera are configured to be the same frequency.
8. Obstacle detecting system based on hanging track, characterized by comprising:
the suspension rail is positioned above the train to be detected;
the AGV trolley is inversely hung on the hanging rail;
the sensing device is arranged on the AGV trolley and is used for collecting 3D Lei Dadian cloud data and camera data of the roof of the train to be detected;
the obstacle detection device is used for acquiring the 3D Lei Dadian cloud data and the camera data acquired by the sensing device, fitting out a track area based on the camera data, filtering the track area in the 3D Lei Dadian cloud data, clustering the 3D Lei Dadian cloud data after the track area is filtered, and detecting an obstacle if a target object is polymerized;
the configuration method of the sensing device comprises the following steps: configuring a detection area of a sensing device, wherein the sensing device comprises a 3D laser radar and an industrial camera; calibrating external parameters of the 3D laser radar and the industrial camera in the sensing device so as to unify a coordinate system of 3D Lei Dadian cloud data acquired by the 3D laser radar and camera data acquired by the industrial camera; the data acquisition frequencies of the 3D lidar and the industrial camera are configured to be the same frequency.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211598638.0A CN115598656B (en) | 2022-12-14 | 2022-12-14 | Obstacle detection method, device and system based on suspension track |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211598638.0A CN115598656B (en) | 2022-12-14 | 2022-12-14 | Obstacle detection method, device and system based on suspension track |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115598656A CN115598656A (en) | 2023-01-13 |
CN115598656B true CN115598656B (en) | 2023-06-09 |
Family
ID=84854100
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211598638.0A Active CN115598656B (en) | 2022-12-14 | 2022-12-14 | Obstacle detection method, device and system based on suspension track |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115598656B (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112613424A (en) * | 2020-12-27 | 2021-04-06 | 盛视达(天津)科技有限公司 | Rail obstacle detection method, rail obstacle detection device, electronic apparatus, and storage medium |
Family Cites Families (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000214928A (en) * | 1999-01-22 | 2000-08-04 | Shinko Electric Co Ltd | Automated guided vehicle |
CN207828776U (en) * | 2017-08-15 | 2018-09-07 | 中铁二院工程集团有限责任公司 | Suspension type monorail traffic track beam external smart maintenance and inspection vehicle |
CN108583733B (en) * | 2018-07-02 | 2024-02-23 | 宝鸡赫威特机械科技有限公司 | AGV transport vehicle for carrying heavy tubular materials |
CN112351928B (en) * | 2018-07-10 | 2023-11-10 | 铁路视像有限公司 | Railway obstacle detection method and system based on track segmentation |
DE102019206719A1 (en) * | 2019-05-09 | 2020-11-12 | Robert Bosch Gmbh | Method and device for reducing the risk to the driver of a single-track motor vehicle in the event of a collision |
CN210591922U (en) * | 2019-07-01 | 2020-05-22 | 比亚迪股份有限公司 | Detection vehicle suitable for track and track detection system |
CN110501719B (en) * | 2019-08-27 | 2024-02-09 | 湖南九域同创高分子新材料有限责任公司 | Laser radar-based train obstacle detection method |
CN110705358B (en) * | 2019-09-03 | 2023-09-26 | 湖南九域同创高分子新材料有限责任公司 | Tunnel scene control decision method for train AEB system |
CN110471085B (en) * | 2019-09-04 | 2023-07-04 | 深圳市镭神智能***有限公司 | Track detecting system |
CN110481601B (en) * | 2019-09-04 | 2022-03-08 | 深圳市镭神智能***有限公司 | Track detection system |
CN110900626A (en) * | 2019-11-28 | 2020-03-24 | 北京荣盛时代科技发展有限公司 | Railway roof insulating part safety cleaning detection robot system |
CN211388808U (en) * | 2019-11-28 | 2020-09-01 | 北京荣盛时代科技发展有限公司 | Railway roof insulating part safety cleaning detection robot system |
CN111951305B (en) * | 2020-08-20 | 2022-08-23 | 重庆邮电大学 | Target detection and motion state estimation method based on vision and laser radar |
CN115236694A (en) * | 2021-04-15 | 2022-10-25 | 阿里巴巴新加坡控股有限公司 | Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium |
CN214586559U (en) * | 2021-05-07 | 2021-11-02 | 苏州元子智能科技有限公司 | AGV dolly with safety inspection function |
CN112991347B (en) * | 2021-05-20 | 2021-08-03 | 西南交通大学 | Three-dimensional-based train bolt looseness detection method |
CN113568002A (en) * | 2021-06-24 | 2021-10-29 | 中车南京浦镇车辆有限公司 | Rail transit active obstacle detection device based on laser and image data fusion |
CN113569915B (en) * | 2021-06-30 | 2024-04-02 | 广西大学 | Multi-strategy rail transit obstacle recognition method based on laser radar |
CN113799852B (en) * | 2021-09-22 | 2022-12-02 | 天津津航计算技术研究所 | Intelligent active obstacle identification protection method supporting dynamic mode switching |
CN114266891A (en) * | 2021-11-17 | 2022-04-01 | 京沪高速铁路股份有限公司 | Railway operation environment abnormity identification method based on image and laser data fusion |
CN114241447A (en) * | 2021-12-27 | 2022-03-25 | 凌云光技术股份有限公司 | Real-time obstacle detection method based on vehicle-mounted equipment |
CN114564009A (en) * | 2022-01-21 | 2022-05-31 | 首都医科大学 | Surgical robot path planning method and system |
CN217499985U (en) * | 2022-04-11 | 2022-09-27 | 中冶南方城市建设工程技术有限公司 | Inverted mobile flushing system and drainage box culvert with flushing function |
CN115032651B (en) * | 2022-06-06 | 2024-04-09 | 合肥工业大学 | Target detection method based on laser radar and machine vision fusion |
CN115056619A (en) * | 2022-06-30 | 2022-09-16 | 重庆宙达机器人科技有限公司 | Adjustable electromagnetic suspension trolley |
CN115359021A (en) * | 2022-08-29 | 2022-11-18 | 上海大学 | Target positioning detection method based on laser radar and camera information fusion |
-
2022
- 2022-12-14 CN CN202211598638.0A patent/CN115598656B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112613424A (en) * | 2020-12-27 | 2021-04-06 | 盛视达(天津)科技有限公司 | Rail obstacle detection method, rail obstacle detection device, electronic apparatus, and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN115598656A (en) | 2023-01-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6768551B2 (en) | Contactless wheel measurement system and method | |
CN107966307B (en) | Train operation safety on-line monitoring method based on vibration acceleration | |
CN109238756B (en) | Dynamic image detection equipment and detection method for freight car operation fault | |
AU2022349296A1 (en) | Road surface technical condition detection method and device based on three-dimensional contour | |
CN110412601A (en) | A kind of head extension integral type semitrailer gabarit measurement method of parameters based on laser radar | |
CN109489584A (en) | A kind of tunnel clearance detection system and tunnel clearance recognition methods based on 3D technology | |
CN108921164B (en) | Contact net locator gradient detection method based on three-dimensional point cloud segmentation | |
CN105241679A (en) | Method for detecting hidden fault of motor train unit | |
CN115236682A (en) | Improved contact net vehicle-mounted limit measurement method based on machine vision | |
CN112082770A (en) | Rail vehicle body detection system and method based on artificial intelligence technology | |
CN103422417A (en) | Dynamic identification system and method for detecting road surface damages | |
CN113448333A (en) | Bottom routing inspection positioning method and device based on sensor combination and electronic equipment | |
CN115598656B (en) | Obstacle detection method, device and system based on suspension track | |
CN207725421U (en) | Vehicle wheel is to dynamic detection system | |
CN110803198B (en) | Rail vehicle derailment detection method based on bogie contour line | |
CN112285111A (en) | Pantograph front carbon sliding plate defect detection method, device, system and medium | |
WO2018025329A1 (en) | Current collector monitoring system | |
CN215037536U (en) | Track traffic vehicle side patrols and examines robot system | |
CN116519703A (en) | System and method for detecting carbon slide plate image of collector shoe based on line scanning 3D image | |
CN114659457A (en) | Track gauge dynamic measurement method based on structured light | |
CN210591925U (en) | Axle box vibrating wheel diameter difference detection system | |
CN208721586U (en) | A kind of locomotive wheel thread defect image detecting system | |
CN114683235A (en) | Human body automatic following method of robot | |
CN113514848B (en) | Railway crossing locomotive detecting system based on laser scanning | |
CN216208691U (en) | Train tread defect detection system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |