CN115601719B - Climbing robot and method for detecting invasion of foreign objects in subway tunnel - Google Patents
Climbing robot and method for detecting invasion of foreign objects in subway tunnel Download PDFInfo
- Publication number
- CN115601719B CN115601719B CN202211593281.7A CN202211593281A CN115601719B CN 115601719 B CN115601719 B CN 115601719B CN 202211593281 A CN202211593281 A CN 202211593281A CN 115601719 B CN115601719 B CN 115601719B
- Authority
- CN
- China
- Prior art keywords
- image
- tunnel
- climbing robot
- detection
- prior
- 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
- 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
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning, or like safety means along the route or between vehicles or vehicle trains
- B61L23/04—Control, warning, or like safety means along the route or between vehicles or vehicle trains for monitoring the mechanical state of the route
- B61L23/041—Obstacle detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Mechanical Engineering (AREA)
- Image Processing (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention belongs to the technical field of tunnel traffic safety, and discloses a climbing robot-based method for detecting invasion of foreign matters in a subway tunnel, which comprises the following steps: controlling the climbing robot to run along the tunnel direction on the inner wall of the tunnel, and continuously acquiring tunnel images as prior images under the condition of no foreign objects and storing the images; meanwhile, matching the prior image with the corresponding position by using an inertial navigation system; the climbing robot is used for driving above the inner wall of the tunnel along the tunnel direction and acquiring a detection image and the position of the detection image in real time; and matching the real-time detection image with the corresponding prior image to obtain a superposed region of the monitoring image and the prior image as a detection region, carrying out gray value difference to obtain a differential image, and judging whether the intrusion occurs according to the differential image.
Description
Technical Field
The invention relates to the technical field of tunnel traffic safety, in particular to a climbing robot and a method for detecting invasion of foreign matters in a subway tunnel.
Background
Foreign matters such as rolling stones and animals invade the boundary of the tunnel steel rail, so that the method has the advantages of sudden, irregular and unpredictable behavior, frequent railway traffic accidents, disturbance of normal transportation order, huge loss of lives and properties of people, influence on social stability, timely invasion of the foreign matters in the tunnel, elimination of hidden dangers and effective reduction of accident risks. Traditional track detects mainly relies on the manpower, examines the orbital invasion condition through set up a large amount of personnel of patrolling and examining nationwide, and is not only inefficient, comparatively consumes manpower and financial resources moreover to, not rapid enough to urgent accident response.
The video detection system has the advantages of simple structure, visual content, high precision and the like, can be applied to the detection of the invasion limit foreign matters of the track traffic tunnel line, can immediately judge whether the foreign matters exist or not, and can further feed back images of the foreign matters, so that the detection result is more comprehensive, and the video detection system has a wide application prospect. In the prior art, a video detection system, unmanned aerial vehicles and other technical equipment are used for routing inspection, but the effect is poor, the routing inspection range of a fixed camera detection system is limited, and the full tunnel coverage investment is high; unmanned aerial vehicle patrols and examines there is not enough problem in space, and when subway vehicle passed through, the crack space in vehicle and tunnel was little, and had the train wind, influences unmanned aerial vehicle stable flight, has the crash risk even, influences driving safety. At present, foreign matter intrusion detection in subway tunnels has a plurality of problems and is always an industry pain point.
Disclosure of Invention
The invention overcomes the defects of the prior art, and solves the technical problems that: the climbing robot and the method for detecting the invasion limit of the foreign matters in the subway tunnel are provided, so that the detection efficiency of the rail traffic invading foreign matters is improved, and the rail traffic driving safety is improved.
In order to solve the technical problems, the invention adopts the technical scheme that: a climbing robot-based method for detecting intrusion of foreign objects in a subway tunnel comprises the following steps:
s1, carrying an image acquisition unit on a climbing robot;
s2, controlling the climbing robot to drive along the tunnel direction on the inner wall of the tunnel, and continuously acquiring tunnel images as prior images under the condition of no foreign objects and storing the images; meanwhile, recording the position of the climbing robot in the tunnel in real time by using an inertial navigation system, and matching the prior image with the corresponding position;
s3, during detection, the climbing robot is used for driving above the inner wall of the tunnel along the tunnel direction and acquiring a detection image in real time, the position of the climbing robot in the tunnel is recorded through an inertial navigation system embodiment, and a prior image corresponding to the position of the monitoring image is extracted;
s4, carrying out image matching on the real-time detection image and the corresponding prior image to obtain a superposed region of the monitoring image and the prior image as a detection region;
and S5, carrying out gray value difference on the matching area of the detection image and the corresponding prior image to obtain a difference image, setting a gray threshold value, judging that the foreign matter is too large if the area of which the gray value exceeds the gray threshold value in the difference image is larger than a first area threshold value, and judging that the foreign matter is too large and the invasion limit occurs if the area of which the gray value exceeds the gray threshold value in the difference image is larger than a second area threshold value.
In the step S2, after tunnel images are continuously acquired under the condition of no foreign objects, a steel rail in the images is identified by utilizing straight line detection, and the area where the steel rail is located is used as a detection area of a prior image;
in the step S3, after the detection image is collected in real time, the steel rail in the image is identified by using the straight line detection, and the area where the steel rail is located is used as the detection area of the real-time detection image.
In the step S3, if the rail is not identified and the pixel proportion of the gray value difference between the detected image and the prior image within a continuous period of time exceeding the gray threshold exceeds the proportional threshold, it is determined that the train passes through and the inspection is suspended.
In step S4, the specific method for performing image matching between the detection image and the corresponding prior image is as follows:
s401, carrying out Gaussian transformation on the detection image to obtain a variable-scale image
The transformation formula is:
wherein the content of the first and second substances,I(μ,ν) A matrix of pixel values representing the input image (a)μ,ν) Is the coordinates of the pixels and is the coordinates of the pixels,L(μ,ν) Is a scale-variable image which is subjected to Gaussian transformation,σis a scale parameter of (A)x,y) Is the position coordinate within the two-dimensional gaussian window;
then, for the variable-scale imageL(mu, v) repeating the Gaussian transformation again to obtain a multi-scale image sequence;
s402, constructing a Gaussian difference image sequence through the multi-scale image sequence;
s403, comparing the pixel points in the image with the adjacent points thereof, simultaneously comparing the corresponding pixels of the Gaussian difference images of the adjacent layers with the adjacent points thereof, and taking the points existing in the scale space and the two-dimensional image space as extreme points;
and S404, matching the obtained extreme point of the detection image as a characteristic point with the characteristic point of the prior image to obtain a superposed region of the monitoring image and the prior image as a detection region.
In step S5, the first area threshold is smaller than the second area threshold.
And in the step S2 and the step S3, the climbing robot is controlled to move along the tunnel direction at the top of the tunnel.
In addition, the invention also provides a climbing robot, which is used for realizing the climbing robot-based method for detecting the intrusion of foreign objects in the subway tunnel, and the climbing robot-based method comprises the following steps:
climbing robot body: the device is used for driving on the inner wall of the tunnel along the tunnel direction;
an image acquisition unit: the system is used for acquiring a real-time image of a steel rail at the bottom of the tunnel;
an image processing unit: the image acquisition unit is used for comparing the detection image sent by the image acquisition unit with the corresponding prior image to judge whether the limit invasion occurs or not;
an inertial navigation system: the position corresponding to the image acquired by the image acquisition unit is identified;
a storage unit: for storing the prior image and its corresponding location.
The climbing robot further comprises: the gravity sensor is fixedly arranged on the climbing robot body; the gravity sensor includes: the climbing robot comprises a shell, wherein a spherical cavity is arranged in the shell, a gravity ball is freely arranged in the spherical cavity, and pressure sensors which are distributed in an annular mode are arranged on a cross-section of a sphere center parallel to a longitudinal section of the climbing robot on the inner wall of the spherical cavity.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a climbing robot-based method for detecting the intrusion of foreign matters in a subway tunnel, which is characterized in that the climbing robot carrying video detection equipment is used for carrying out routing inspection on the intrusion foreign matters in the tunnel, so that the detection range can be ensured to cover all areas to be detected, repeated detection is avoided, intelligent monitoring can be realized on the whole track line, and the interference on the existing train signal and communication system can be avoided; the method can not only identify and position the invasion limit foreign matters, but also comprehensively cover all-weather and all-scene conditions; the inspection and measurement efficiency and the detection precision are obviously improved.
Drawings
Fig. 1 is a schematic diagram of a detection scenario model for detecting intrusion of a foreign object in a subway tunnel according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a train passing scene according to an embodiment of the present invention;
FIG. 3 is a no foreign object prior image of an embodiment of the present invention;
FIG. 4 is a detection image of the occurrence of foreign object intrusion;
FIG. 5 is the image difference result;
FIG. 6 is a gravity sensor configuration;
figure 7 is a front view of the climbing robot of the present invention;
figure 8 is a top view of the climbing robot of the present invention;
FIG. 9 is a flow chart of the inspection of the climbing robot in the embodiment of the present invention;
in the figure: 1 is climbing robot, 2 is the rail, 3 is the visual field of robot, 4 is the tunnel, 5 is the train, 6 is the foreign matter, 7 is the image acquisition unit, 8 is the shell, 9 is the gravity ball, 10 is pressure sensor.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments; all other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example one
The embodiment of the invention provides a climbing robot-based method for detecting invasion of foreign matters in a subway tunnel, which comprises the following steps:
s1, carrying an image acquisition unit on the climbing robot 1. As shown in fig. 1 to 2, the diagrams are schematic diagrams of detection of a climbing robot in a tunnel. The image information in the tunnel is acquired through the image acquisition unit. 2 is the rail, 3 is the field of view of the robot, 4 is the tunnel. In fig. 2, when a train 5 passes through, the climbing robot is blocked.
S2, controlling the climbing robot to run along the tunnel direction on the inner wall of the tunnel, and continuously acquiring tunnel images as prior images under the condition of no foreign objects and storing the images; meanwhile, the position of the climbing robot in the tunnel is recorded in real time by using an inertial navigation system, and the prior image is preliminarily matched with the corresponding position.
In the step S2, after tunnel images are continuously acquired under the condition of no foreign matters, the steel rails in the images are identified by utilizing straight line detection, the detection range of the foreign matters in the images is determined through the steel rails, and the areas near and in the middle of the two steel rails are used as the detection areas of the prior images. Meanwhile, the steel rail straight line is used as important data for matching the real-time detection image and the prior image. Fig. 3 is a schematic diagram of a prior image without foreign matter.
And S3, during detection, the climbing robot is used for driving above the inner wall of the tunnel along the tunnel direction and acquiring a detection image in real time, the position of the climbing robot in the tunnel is recorded through an embodiment of the inertial navigation system, and a prior image corresponding to the position of the monitoring image is extracted. Fig. 4 is a schematic diagram of a detection image when a foreign object intrusion occurs.
In the step S3, after the detection image is collected in real time, the steel rail in the identified image is identified by using the line detection, and the area where the steel rail is located is used as the detection area of the real-time detection image.
In the step S3, if the steel rail is not identified, the detection images within a period of time are continuously detected
And the prior image->
Gray value difference of->
Exceeding the threshold of grey scaletExceeds a scaling thresholdbIf the train passes, the inspection is suspended. The specific judgment formula is as follows:
wherein (x, y) is a pixel coordinate,Pto vary the pixel function, P max The total number of pixels of the image is taken as the train passing discriminant function, and when the train passes, the train passing discriminant function is determined b And if the signal is =1, judging that no train passes through.
Further, in the step S2 and the step S3, the climbing robot is controlled to move along the tunnel direction at the top of the tunnel.
And S4, carrying out image matching on the real-time detection image and the corresponding prior image to obtain a superposed region of the monitoring image and the prior image as a detection region.
In step S4, the specific method for performing image matching between the detection image and the corresponding prior image is as follows:
s401, carrying out Gaussian transformation on the detection image to obtain a variable-scale image
The transformation formula is:
wherein, the first and the second end of the pipe are connected with each other,I(μ,ν) A matrix of pixel values representing an input image (a)μ,ν) Is a coordinate of a pixel, and is,L(μ,ν) Is a scale-variable image which is subjected to Gaussian transformation,σis a scale parameter of (A)x,y) Is the position coordinate within the two-dimensional gaussian window;
and then repeating Gaussian transformation on the variable-scale image L (mu, v) to obtain a multi-scale image sequence.
S402, constructing a Gaussian Difference (DOG) image sequence through the multi-scale image sequence.
The characteristic points are composed of local extreme points of DOG space, and the detection of the characteristic points is completed by comparing two adjacent layers of DOG images. In this embodiment, a gaussian difference sequence is obtained through adjacent multi-scale image differences, and a calculation formula of the gaussian difference sequence is as follows:
in the formula (I), the compound is shown in the specification,krepresenting the number of layers of the image in the multi-scale space.
S403, comparing the pixel points in the image with the adjacent points thereof to determine the extreme points of the image layer, simultaneously comparing the corresponding pixels of the Gaussian difference images of the adjacent layers with the adjacent points thereof to determine the extreme points of the adjacent image layers, and taking the extreme points existing at the corresponding positions of the adjacent image layers in the scale space as feature points. And determining the characteristic points of the prior image by the same method, and accurately matching the detected image with the prior image by the method corresponding to the characteristic points.
In this embodiment, each pixel point needs to be compared with all its neighboring points, and also needs to be compared with the corresponding pixel of the gaussian difference image of the adjacent layer and its neighboring points, to see whether it is larger or smaller than its image domain and its neighboring points of the scale domain, so as to ensure that the extreme points are detected in both the scale space and the two-dimensional image space.
And S404, matching the obtained extreme point of the detection image as a characteristic point with the characteristic point of the prior image to obtain a superposed region of the monitoring image and the prior image as a detection region.
And S5, carrying out gray value difference on the matching area of the detection image and the corresponding prior image to obtain a difference image, setting a gray threshold value, judging that the foreign matter is too large if the area of which the gray value exceeds the gray threshold value in the difference image is larger than a first area threshold value, and judging that the foreign matter is too large and the invasion limit occurs if the area of which the gray value exceeds the gray threshold value in the difference image is larger than a second area threshold value. As shown in fig. 5, the foreign object 6 can be obtained from a differential image, which is a schematic diagram of a differential image between a detection image and a prior image when the foreign object infringement occurs.
Example two
The second embodiment of the invention provides a climbing robot, which is used for realizing the foreign matter intrusion detection method in the subway tunnel based on the climbing robot in the first embodiment, and comprises the following steps:
climbing robot body: the device is used for flying into the tunnel and driving on the inner wall of the tunnel along the tunnel direction;
an image acquisition unit: the method is used for detecting the images of the steel rails at the bottom of the tunnel;
an image processing unit: the image acquisition unit is used for acquiring a detection image of the image to be detected;
an inertial navigation system: the position corresponding to the image acquired by the image acquisition unit is identified;
a storage unit: for storing the prior image and its corresponding location.
The climbing robot of this embodiment still includes: the gravity sensor is fixedly arranged on the climbing robot body; as shown in fig. 6, the gravity sensor includes: the climbing robot comprises a shell 8, wherein a spherical cavity is arranged in the shell, a gravity ball 9 is freely arranged in the spherical cavity, pressure sensors 10 distributed in an annular shape are arranged on the cross-section of the spherical center of the inner wall of the spherical cavity, which is parallel to the longitudinal section of the climbing robot, and the output ends of the pressure sensors are connected with a control center of the climbing robot body. In the embodiment, the gravity direction sensor is fixed on the robot, the gravity ball can freely roll in the cavity of the shell, and when the walking direction of the climbing robot is consistent with the planning direction (along the tunnel direction), the gravity ball presses the pressure sensor on the inner wall of the cavity to send out an electric signal under the action of gravity, which indicates that the advancing direction of the robot is consistent with the planning direction; when the body posture of the robot changes in a three-dimensional space, the shell changes along with the body, the gravity ball rolls to deviate from the plane of the pressure sensor, and the pressure sensor does not output an electric signal, so that the robot deviates from the track. The output end of the pressure sensor is connected with the control center of the climbing robot body, and the climbing robot is controlled to move linearly along the tunnel direction without deviation through signals of the pressure sensor.
As shown in fig. 7 to 8, the climbing robot is a schematic structural diagram of the climbing robot adopted in the present invention, wherein 11 is a frame, 12 is a wheel, and 13 is a rotor, and the climbing robot has two capabilities of climbing and flying. The image acquisition unit 7 is arranged in the center of the robot. When climbing robot walked at tunnel wall top, rotated through the rotor and produced pressure and paste closely to the tunnel wall, climbing robot's wheel rotates and makes it walk at tunnel wall top.
Fig. 9 is a flowchart illustrating a work flow of the climbing robot during inspection according to the embodiment of the present invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not depart from the spirit of the corresponding technical solutions of the embodiments of the present invention.
Claims (6)
1. A foreign matter intrusion detection method in a subway tunnel based on a climbing robot is characterized by comprising the following steps:
s1, carrying an image acquisition unit on a climbing robot;
s2, controlling the climbing robot to drive along the tunnel direction on the inner wall of the tunnel, and continuously acquiring tunnel images as prior images under the condition of no foreign objects and storing the images; meanwhile, recording the position of the climbing robot in the tunnel in real time by using an inertial navigation system, and matching the prior image with the corresponding position;
s3, during detection, the climbing robot is used for driving above the inner wall of the tunnel along the tunnel direction, detection images are collected in real time, the position of the climbing robot in the tunnel is recorded through an inertial navigation system embodiment, and a priori image corresponding to the position of the monitoring image is extracted;
s4, carrying out image matching on the real-time detection image and the corresponding prior image to obtain a superposed region of the monitoring image and the prior image as a detection region;
s5, carrying out gray value difference on the matching area of the detection image and the corresponding prior image to obtain a difference image, setting a gray threshold value, if the area of which the gray value exceeds the gray threshold value in the difference image is larger than a first area threshold value, judging that the foreign matter is overlarge, and if the area of which the gray value exceeds the gray threshold value in the difference image is larger than a second area threshold value, judging that the limit invasion occurs;
in the step S2, after tunnel images are continuously acquired under the condition of no foreign objects, a steel rail in the images is identified by utilizing straight line detection, and the area where the steel rail is located is used as a detection area of a prior image;
in the step S3, after the detection image is collected in real time, the steel rail in the image is identified by utilizing linear detection, and the area where the steel rail is located is used as the detection area of the real-time detection image;
in the step S3, if no steel rail is identified and the pixel proportion of the gray value difference between the detected image and the prior image in a continuous period of time exceeds the gray threshold exceeds the proportion threshold, it is determined that the train passes through and the inspection is suspended.
2. The method for detecting the intrusion of the foreign object in the subway tunnel based on the climbing robot as claimed in claim 1, wherein in said step S4, the specific method for image matching between the detection image and the corresponding prior image is as follows:
s401, carrying out Gaussian transformation on the detection image to obtain a variable-scale image
The transformation formula is:
wherein the content of the first and second substances,I(μ,ν) A matrix of pixel values representing the input image (a)μ,ν) Is the coordinates of the pixels and is the coordinates of the pixels,L(μ,ν) Is a scale-variable image which is subjected to Gaussian transformation,σis a scale parameter of (A), (B)x,y) Is the position coordinate within the two-dimensional gaussian window;
then, for the variable-scale imageL(mu, v) repeating the Gaussian transformation again to obtain a multi-scale image sequence;
s402, constructing a Gaussian difference image sequence through the multi-scale image sequence;
s403, comparing the pixel points in the image with the adjacent points thereof, simultaneously comparing the corresponding pixels of the Gaussian difference images of the adjacent layers with the adjacent points thereof, and taking the points existing in the scale space and the two-dimensional image space as extreme points;
and S404, matching the obtained extreme point of the detection image as a characteristic point with the characteristic point of the prior image to obtain a superposed region of the monitoring image and the prior image as a detection region.
3. The method for detecting the invasion of foreign objects in the subway tunnel based on the climbing robot as claimed in claim 1, wherein in said step S5, the first area threshold is smaller than the second area threshold.
4. The method for detecting the intrusion of foreign objects in the subway tunnel based on the climbing robot as claimed in claim 1, wherein in said step S2 and step S3, the climbing robot is controlled to move along the tunnel direction at the top of the tunnel.
5. A climbing robot for realizing the climbing robot-based method for detecting the intrusion of foreign objects in a subway tunnel, which is disclosed in claim 1, is characterized by comprising the following steps:
climbing robot body: the device is used for driving on the inner wall of the tunnel along the tunnel direction;
an image acquisition unit: the system is used for acquiring a real-time image of a steel rail at the bottom of the tunnel;
an image processing unit: the image acquisition unit is used for acquiring a detection image of the image to be detected;
an inertial navigation system: the image acquisition unit is used for acquiring images;
a storage unit: for storing the prior image and its corresponding location.
6. The climbing robot of claim 5, further comprising: the gravity sensor is fixedly arranged on the climbing robot body; the gravity sensor includes: the climbing robot comprises a shell (8), wherein a spherical cavity is arranged in the shell, a gravity ball (9) is freely arranged in the spherical cavity, and pressure sensors (10) which are distributed in an annular mode are arranged on a cross-spherical center section parallel to the longitudinal section of the climbing robot on the inner wall of the spherical cavity.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211593281.7A CN115601719B (en) | 2022-12-13 | 2022-12-13 | Climbing robot and method for detecting invasion of foreign objects in subway tunnel |
| ZA2023/05835A ZA202305835B (en) | 2022-12-13 | 2023-05-31 | Climbing robot and method for detecting foreign object intrusion in metro tunnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211593281.7A CN115601719B (en) | 2022-12-13 | 2022-12-13 | Climbing robot and method for detecting invasion of foreign objects in subway tunnel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115601719A CN115601719A (en) | 2023-01-13 |
| CN115601719B true CN115601719B (en) | 2023-03-31 |
Family
ID=84854041
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211593281.7A Active CN115601719B (en) | 2022-12-13 | 2022-12-13 | Climbing robot and method for detecting invasion of foreign objects in subway tunnel |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115601719B (en) |
| ZA (1) | ZA202305835B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0301586A1 (en) * | 1987-07-29 | 1989-02-01 | Phoenix Software Development Co. | Vision system and method for automated painting equipment |
| CN107433952A (en) * | 2017-05-12 | 2017-12-05 | 北京瑞途科技有限公司 | A kind of intelligent inspection robot |
| CN108549087A (en) * | 2018-04-16 | 2018-09-18 | 北京瑞途科技有限公司 | A kind of online test method based on laser radar |
| CN110821560A (en) * | 2019-10-18 | 2020-02-21 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Tunnel inspection system |
| CN114312877A (en) * | 2022-01-26 | 2022-04-12 | 株洲时代电子技术有限公司 | Railway comprehensive inspection system |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108248635B (en) * | 2018-02-05 | 2019-03-22 | 刘春梅 | A kind of intelligent checking system for rail tunnel |
| CN108491758B (en) * | 2018-02-08 | 2020-11-20 | 深圳市睿灵创新科技开发有限公司 | Track detection method and robot |
| US11738785B2 (en) * | 2018-02-15 | 2023-08-29 | Yaakov Frucht | System and method for detecting an intruder on tracks |
| CN111626204B (en) * | 2020-05-27 | 2022-01-11 | 汪海洋 | Railway foreign matter invasion monitoring method and system |
| CN112743559A (en) * | 2020-12-29 | 2021-05-04 | 上海市东方海事工程技术有限公司 | Suspension type tunnel inspection robot, system and method |
| CN113673614B (en) * | 2021-08-25 | 2023-12-12 | 北京航空航天大学 | Metro tunnel foreign matter intrusion detection device and method based on machine vision |
| CN114494161A (en) * | 2022-01-12 | 2022-05-13 | 成都唐源电气股份有限公司 | Pantograph foreign matter detection method and device based on image contrast and storage medium |
| CN114527752A (en) * | 2022-01-25 | 2022-05-24 | 浙江省交通投资集团有限公司智慧交通研究分公司 | Accurate positioning method for detection data of track inspection robot in low satellite signal environment |
| CN115600124A (en) * | 2022-09-07 | 2023-01-13 | 昆明地铁运营有限公司（Cn） | Subway tunnel inspection system and inspection method |
-
2022
- 2022-12-13 CN CN202211593281.7A patent/CN115601719B/en active Active
-
2023
- 2023-05-31 ZA ZA2023/05835A patent/ZA202305835B/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0301586A1 (en) * | 1987-07-29 | 1989-02-01 | Phoenix Software Development Co. | Vision system and method for automated painting equipment |
| CN107433952A (en) * | 2017-05-12 | 2017-12-05 | 北京瑞途科技有限公司 | A kind of intelligent inspection robot |
| CN108549087A (en) * | 2018-04-16 | 2018-09-18 | 北京瑞途科技有限公司 | A kind of online test method based on laser radar |
| CN110821560A (en) * | 2019-10-18 | 2020-02-21 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Tunnel inspection system |
| CN114312877A (en) * | 2022-01-26 | 2022-04-12 | 株洲时代电子技术有限公司 | Railway comprehensive inspection system |
Also Published As
| Publication number | Publication date |
|---|---|
| ZA202305835B (en) | 2023-08-30 |
| CN115601719A (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | A review of applications of visual inspection technology based on image processing in the railway industry | |
| CN110532889B (en) | Track foreign matter detection method based on rotor unmanned aerial vehicle and YOLOv3 | |
| CN103593678B (en) | A kind of long-span bridge vehicle dynamic load distribution detection method | |
| CN109766746B (en) | Track foreign matter detection method for aerial video of unmanned aerial vehicle | |
| CN111626203B (en) | Railway foreign matter identification method and system based on machine learning | |
| CN108197610A (en) | A kind of track foreign matter detection system based on deep learning | |
| CN109064495A (en) | A kind of bridge floor vehicle space time information acquisition methods based on Faster R-CNN and video technique | |
| CN111626204B (en) | Railway foreign matter invasion monitoring method and system | |
| CN107576667A (en) | A kind of railway rail clip abnormality detection system based on linear array thermal camera | |
| CN109489584B (en) | Tunnel clearance detection system and tunnel clearance identification method based on 3D technology | |
| CN110862033A (en) | Intelligent early warning detection method applied to coal mine inclined shaft winch | |
| CN107480653A (en) | passenger flow volume detection method based on computer vision | |
| CN107239746B (en) | Obstacle identification and tracking method for road rescue safety monitoring | |
| CN105260719A (en) | Railway platform line-crossing detection method | |
| CN102346844B (en) | Device and method for identifying fault of losing screw bolts for truck center plates | |
| CN106741008B (en) | Railway line foreign matter identification method and system | |
| CN102496275B (en) | Method for detecting overload of coach or not | |
| CN111783579B (en) | Unmanned aerial vehicle visual analysis-based detection system for crossing fence by constructors | |
| CN113011252A (en) | Track foreign matter intrusion detection system and method | |
| CN115601719B (en) | Climbing robot and method for detecting invasion of foreign objects in subway tunnel | |
| CN104006804A (en) | Method for detecting offset of contact net based on observation benchmark instability compensation | |
| CN114913131A (en) | Vertical absolute and relative vertical deformation detection method for ballastless track structure | |
| CN111754477B (en) | Railway perimeter foreign matter intrusion detection method based on dynamic candidate area multi-scale image | |
| Nichoha et al. | Development of modern methods and directions of rapid diagnostics of railway tracks defects by television methods | |
| CN112966636A (en) | Automatic identification method for passenger elevator car approach aircraft in flight area of civil aviation airport |
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 |