Rail transit protection area inspection control system and method
Through drone automated cruise and intelligent identification technology, the problems of large labor consumption and low efficiency in rail transit protection areas have been solved, and efficient and all-weather automated patrols have been achieved, reducing blind spots in perspective.
Patent Information
- Application Number
- CN202410975504.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-12-06
AI Technical Summary
In the prior art, inspections of rail transit protection areas rely on manual means, consume a lot of manpower and are inefficient, and cannot guarantee all-weather inspections, especially when there are blocked areas of buildings, there may be blind spots in patrols.
UAVs are used to cruise along preset routes to shoot video streams and flight status information, and divide traffic protection areas through intelligent identification subsystems, identify target objects information, analyze and send alarm information in real time, and realize automated patrol inspections.
It effectively reduces labor costs, improves inspection efficiency, reduces blind spots in perspective, and achieves efficient inspections all-weather.
Smart Images

Figure CN119078911A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of rail transit technology, and in particular to a rail transit protection zone patrol control system and method. Background Art
[0002] The urban rail transit safety protection zone is an area legally demarcated along the urban rail transit line to protect the normal and safe operation of urban rail transit such as subways and light rails. This area is set up to prevent stations, tunnels, lines, piers, entrances and exits, ventilation booths, substations, parking lots, vehicle bases, etc. from invading rail transit structures, damaging rail transit equipment and facilities, blocking station entrances and exits, and other situations that affect operational safety.
[0003] Inspection of urban rail transit safety protection zones is an important part of ensuring the safe operation of urban rail transit. Currently, inspections are mainly carried out manually, with inspectors responsible for their respective inspection areas and inspecting mechanical devices that may damage the surface of the rail line. The inspection frequency is usually once a day or twice a day. Manual inspections require a lot of manpower and are inefficient, and cannot guarantee all-weather inspections. In addition, there may be blind spots when inspecting areas blocked by buildings. Summary of the invention
[0004] The present invention provides a rail transit protection zone inspection control system and method, which is used to solve the defects of the prior art that a large amount of manpower is required and the efficiency is low when inspecting the rail transit protection zone, and realizes efficient inspection of the rail transit protection zone by analyzing the video images taken by the cruise flight of the unmanned aerial vehicle, effectively reducing the manpower cost and improving the inspection efficiency.
[0005] The present invention provides a rail transit protection zone patrol control system, including a patrol control subsystem, an intelligent identification subsystem and a safety patrol subsystem.
[0006] The inspection control subsystem is used to control the UAV to cruise along a preset route, and transmit the video stream captured by the UAV during the cruise flight and the flight status information of the UAV back to the intelligent identification subsystem; The intelligent identification subsystem is used to divide the traffic protection zone based on the video stream and the flight status information; identify the target object information in the traffic protection zone based on the video stream, and analyze the target object information to obtain an analysis result, and when the analysis result reaches an alarm condition, send the alarm information to the safety inspection subsystem; The safety inspection subsystem is used to receive and display the alarm information in real time.
[0007] According to a rail transit protection zone inspection control system provided by the present invention, the flight status information includes the location information and the cruising path of the UAV; the traffic protection zone includes an impact protection zone and a strict protection zone, and the division of the traffic protection zone based on the video stream and the flight status information includes: identifying an area in the video stream by combining the location information and the cruise path,
[0008] When it is determined according to the recognition result that the area includes a preset location, a range with a first distance as a radius and centered on the preset location is divided into the impact protection zone, and a range with a second distance as a radius is divided into the strict protection zone.
[0009] According to a rail transit protection zone inspection control system provided by the present invention, the target object information of the traffic protection zone is identified based on the video stream, including: Acquire an image associated with the traffic protection zone in the video stream; Preprocessing the image to obtain a preprocessed image, and performing feature extraction processing on the preprocessed image to obtain image features; An image recognition model is called to perform classification processing based on the image features to obtain the type and position of the target object in the traffic protection zone, and the type and position of the target object are used as the target object information.
[0010] According to a rail transit protection zone inspection control system provided by the present invention, the preprocessing of the image to obtain the preprocessed image includes: The image is sequentially subjected to scaling processing, cropping processing, rotation processing and brightness adjustment processing to obtain the pre-processed image.
[0011] According to a rail transit protection zone inspection control system provided by the present invention, the target object information is analyzed to obtain the analysis result, including: Performing type matching processing on the target object type and the preset object type to obtain a type matching result; Performing position matching processing based on the position of the target object and the position of the traffic protection zone to obtain a position matching result; The type matching result and the position matching result are used as the analysis result.
[0012] According to a rail transit protection zone inspection control system provided by the present invention, the alarm information includes the target object information and the location of the traffic protection zone corresponding to the target object; The warning condition includes: the type of the target object is one of the preset object types, and the target object is located in the traffic protection zone.
[0013] The present invention also provides a rail transit protection zone inspection method, comprising: Control the drone to cruise along a preset route, and transmit back the video stream captured by the drone during the cruise flight and the flight status information of the drone; Divide the traffic protection zone based on the video stream and the flight status information; identify target object information in the traffic protection zone based on the video stream, and analyze the target object information to obtain an analysis result; When the analysis result reaches the alarm condition, the alarm information is displayed in real time.
[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a rail transit protection zone inspection method as described above is implemented.
[0015] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the rail transit protection zone inspection method as described in any one of the above-mentioned methods is implemented.
[0016] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned rail transit protection zone inspection methods.
[0017] The present invention provides a rail transit protection zone inspection control system and method, which controls a drone to cruise along a preset route through a patrol control subsystem, and transmits the video stream shot by the drone during the cruise flight and the flight status information of the drone back to the intelligent recognition subsystem, and then the intelligent recognition subsystem divides the traffic protection zone based on the video stream and the flight status information, identifies the target object information of the traffic protection zone based on the video stream, and analyzes the target object information to obtain the analysis result. When the analysis result reaches the alarm condition, the alarm information is sent to the safety patrol subsystem, so that the safety patrol subsystem receives and displays the alarm information in real time. Through the cooperation of each subsystem, the inspection of the rail transit protection zone is automatically completed, which effectively improves the inspection efficiency, and because the drone has a flexible aerial perspective, the visual blind spot during the inspection can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0019] Figure 1 It is one of the structural schematic diagrams of the rail transit protection zone patrol control system provided by the present invention.
[0020] Figure 2 This is the second structural schematic diagram of the rail transit protection zone patrol control system provided by the present invention.
[0021] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0023] Figure 1 This is one of the structural schematic diagrams of the rail transit protection zone inspection control system provided by the present invention, such as Figure 1 As shown, the system includes a patrol control subsystem, an intelligent identification subsystem and a safety patrol subsystem.
[0024] The inspection control subsystem is used to control the UAV to cruise along a preset route, and transmit the video stream captured by the UAV during the cruise flight and the flight status information of the UAV back to the intelligent identification subsystem.
[0025] Specifically, the take-off and landing of the UAV is controlled by the patrol control subsystem. After the UAV takes off, the UAV is controlled to cruise along the pre-planned rail transit flight route. The preset flight route here can be a route flying directly above the track or a route flying along the side of the track. The flight route can be parallel to the track or cross the track. That is, the preset flight route of the UAV can be set arbitrarily, so that the UAV can avoid obstacles such as wires and clearly capture videos along the track.
[0026] It should be noted that when the drone is flying along a preset route, it can transmit the captured video stream and the flight status information of the drone in real time to the intelligent identification subsystem via wireless communication, or it can transmit it back to the intelligent identification subsystem periodically, or it can wait until the drone completes its flight along the preset route before transmitting it back to the intelligent identification subsystem.
[0027] In some embodiments, see Figure 2 , Figure 2 This is the second structural diagram of the inspection control system for the rail transit protection zone provided by the present invention. Figure 2The inspection control subsystem shown below sends airport control signals to the drone airport through the drone airport management platform to enable the drone to take off or land. In addition to shooting videos, drones can also take photos during flight to achieve efficient data collection. The videos and photos collected by the drone are first sent to the drone airport via wireless communication, and then the drone airport sends the real-time monitored flight status and video live stream to the intelligent recognition subsystem. It can also be transferred to the intelligent recognition subsystem via the drone airport management platform so that the intelligent recognition subsystem can perform real-time recognition and analysis of the video and photos.
[0028] In an embodiment of the present invention, a drone is used to cruise along a preset route to collect videos and photos related to rail transit in real time, and then the data collected by the drone is analyzed later, which can effectively improve the inspection efficiency.
[0029] In some embodiments, the intelligent identification subsystem is used to divide the traffic protection zone based on the video stream and the flight status information; identify the target object information of the traffic protection zone based on the video stream, and analyze the target object information to obtain an analysis result, and when the analysis result reaches an alarm condition, send the alarm information to the safety inspection subsystem.
[0030] In some embodiments, the flight status information includes the location information and cruising path of the UAV; the traffic protection zone includes an impact protection zone and a strict protection zone.
[0031] The division of the traffic protection zone based on the video stream and the flight status information can be achieved in the following manner: the area in the video stream is identified in combination with the position information and the cruise path, and when it is determined according to the identification result that the area includes a preset location, the range with the preset location as the center and the first distance as the radius is divided into the impact protection zone, and the range with the second distance as the radius is divided into the strict protection zone.
[0032] Specifically, the flight status information may also include information such as the flight speed, flight altitude and location of the UAV. After the intelligent identification subsystem receives the status information and video stream sent by the UAV inspection control subsystem, it combines the location information and route path of the UAV, and adopts intelligent algorithms and intelligent identification technologies to identify the area in the video stream based on the video stream or images extracted from the video stream, as well as the location information of the UAV. If it is determined according to the identification results that the area in the video stream includes preset locations such as stations, substations, and high-voltage lines, then these preset locations are used as the center, and the range of the second distance (for example, 10 meters) is extended outward as a strict protection zone, and these preset locations are used as the center, and the range of the first distance (for example, 50 meters) is extended outward as an impact protection zone. There are different requirements for targets that can be parked in different protection zones.
[0033] Exemplarily, the scope of the urban rail transit safety protection zone includes underground, surface and above ground, and is divided into impact protection zones and strict protection zones; the area within 50 meters outside the outer edge of underground stations, underground passages, and tunnel structures is the impact protection zone, and the area within 10 meters outside is the strict protection zone; the area within 30 meters outside the horizontal projection line of elevated stations and line projects, ground stations, and the line embankment or cutting edge line is the impact protection zone, and the area within 10 meters outside is the strict protection zone; the area within 10 meters outside the outer edge of station entrances and exits, ventilation booths, substations, cooling towers and other buildings and structures, equipment, and the control center, vehicle base building structure outer edge line is the strict protection zone; the area within 3 meters outside the horizontal projection of urban rail transit high-voltage cable trenches, overhead lines and other power supply facilities, as well as outdoor water supply and drainage facilities including drainage inspection wells, water supply meter wells, septic tanks, fire hydrants, water pump connectors, water supply and drainage pipes and valves is the strict protection zone.
[0034] In the embodiment of the present invention, the traffic protection zone is identified and divided based on the video stream sent back by the drone, which can effectively improve the inspection efficiency of the rail transit protection zone.
[0035] In some embodiments, identifying the target object information in the traffic protection zone based on the video stream can be achieved in the following manner: obtaining an image associated with the traffic protection zone in the video stream; preprocessing the image to obtain a preprocessed image, performing feature extraction processing on the preprocessed image to obtain image features; calling an image recognition model to perform classification processing based on the image features to obtain the type and position of the target object in the traffic protection zone, and using the type and position of the target object as the target object information.
[0036] In some embodiments, preprocessing the image to obtain the preprocessed image includes: sequentially performing scaling, cropping, rotation and brightness adjustment on the image to obtain the preprocessed image.
[0037] Specifically, images associated with the traffic protection zone are captured from the video stream for image recognition, or images transmitted by the drone are directly received for image recognition. The image is first scaled, such as horizontal scaling, vertical scaling, fixed scaling, etc., to change the size of the image. The scaled image is then cropped to remove redundant parts of the image, thereby improving the clarity and resolution of the image. The cropped image is then rotated to change the viewing angle or arrangement of the image. Finally, the rotated image is brightness adjusted to obtain a preprocessed image that meets the model input requirements.
[0038] It should be noted that the above preprocessing process may include partial steps of scaling, cropping, rotation and brightness adjustment, or all steps; it may be performed in the above processing order or in a random order, and no specific limitation is made here.
[0039] After preprocessing the image, key features in the image, such as grayscale features, texture features, shape features, color features, and higher-level HoG features and SIFT features, are extracted through a deep learning model (such as a convolutional neural network).
[0040] Then, the image recognition model is used to perform classification processing based on the above image features, so as to obtain the type and location of the target object in the traffic protection zone in the image. The target objects include large equipment that may be used in the construction and operation of rail transit, such as large road maintenance machinery, drilling machines, cutting machines, explosion-proof equipment, etc. After identifying the location of the target object in the image, the frame can be marked to determine whether the target object is located in the impression protection zone or the strict protection zone, or is not located in the traffic protection zone.
[0041] In some embodiments, the target object information is analyzed to obtain an analysis result, including: performing type matching processing on the type of the target object and a preset object type to obtain a type matching result; performing position matching processing based on the position of the target object and the position of the traffic protection zone to obtain a position matching result; and using the type matching result and the position matching result as the analysis result.
[0042] Specifically, when the above model recognizes that there is a target object in the image, the type of the target object is first matched with the preset object type to determine whether the target object is a large-scale equipment that affects the safety of rail transit, such as large-scale road maintenance machinery, drilling machines, cutting machines, explosion-proof equipment, etc.; then the position of the target object is matched with the position of the traffic protection zone to determine whether the above-mentioned large-scale equipment is located in the traffic protection zone, and then the type matching result and the position matching result are used as the analysis result, so as to facilitate the subsequent determination of whether to issue an alarm based on the analysis result.
[0043] In some embodiments, the warning information includes the target object information and the location of the traffic protection zone corresponding to the target object; the warning condition includes: the type of the target object is one of the preset object types, and the target object is located in the traffic protection zone.
[0044] For example, when the target object is a large road maintenance machine and is located in an impact protection area, an alarm is issued; when the target object is a cutting machine and is located in a strict protection area, an alarm is issued.
[0045] In some embodiments, the safety inspection subsystem is used to receive and display the alarm information in real time.
[0046] When the safety inspection subsystem receives the alarm information push, it displays the alarm information in real time to facilitate manual confirmation and processing, so as to clear the above-mentioned targets in the traffic protection zone in time to ensure the safe operation of rail transit.
[0047] For example, see Figure 2 The intelligent recognition subsystem can include an AI reasoning server and an AI application server, which perform the above-mentioned image processing and analysis operations respectively. When the analysis result reaches the alarm condition, the alarm information is sent to the server of the safety inspection subsystem and displayed on the display terminal of the safety inspection subsystem.
[0048] The rail transit protection zone inspection method provided by the present invention is described below. The rail transit protection zone inspection method described below and the rail transit protection zone inspection control system described above can be referenced to each other.
[0049] In some embodiments, the rail transit protection zone inspection method provided by the present invention includes the following steps.
[0050] Control the drone to cruise along a preset route, and transmit back the video stream captured by the drone during the cruise flight and the flight status information of the drone; Divide the traffic protection zone based on the video stream and the flight status information; identify target object information in the traffic protection zone based on the video stream, and analyze the target object information to obtain an analysis result; When the analysis result reaches the alarm condition, the alarm information is displayed in real time.
[0051] The above-mentioned rail transit protection zone inspection method and the rail transit protection zone inspection control system described above can be referenced to each other, and will not be repeated here.
[0052] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the rail transit protection zone inspection method, which includes: controlling the drone to cruise along a preset route, and returning the video stream shot by the drone during the cruise flight and the flight status information of the drone; dividing the traffic protection zone based on the video stream and the flight status information; identifying the target object information of the traffic protection zone based on the video stream, and analyzing the target object information to obtain the analysis result; when the analysis result reaches the alarm condition, displaying the alarm information in real time.
[0053] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0054] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the rail transit protection zone inspection method provided by the above-mentioned methods, which includes: controlling a drone to cruise along a preset route, and transmitting back a video stream captured by the drone during cruising flight and the flight status information of the drone; dividing a traffic protection zone based on the video stream and the flight status information; identifying target object information in the traffic protection zone based on the video stream, and analyzing the target object information to obtain an analysis result; when the analysis result meets the alarm condition, displaying the alarm information in real time.
[0055] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the rail transit protection zone inspection method provided by the above-mentioned methods. The method includes: controlling a drone to cruise along a preset route, and transmitting back a video stream captured by the drone during cruising flight and flight status information of the drone; dividing a traffic protection zone based on the video stream and the flight status information; identifying target object information in the traffic protection zone based on the video stream, and analyzing the target object information to obtain an analysis result; when the analysis result meets an alarm condition, displaying the alarm information in real time.
[0056] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0057] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A rail transit protection zone inspection control system, characterized in that: It includes inspection control subsystem, intelligent identification subsystem and safety inspection subsystem. The inspection control subsystem is used to control the UAV to cruise along a preset route, and transmit the video stream captured by the UAV during the cruise flight and the flight status information of the UAV back to the intelligent identification subsystem; The intelligent identification subsystem is used to divide the traffic protection zone based on the video stream and the flight status information; Identify target information in the traffic protection zone based on the video stream, analyze the target information to obtain an analysis result, and send the alarm information to the safety inspection subsystem when the analysis result reaches an alarm condition; The safety inspection subsystem is used to receive and display the alarm information in real time.
2. The rail transit protection zone inspection control system according to claim 1 is characterized in that: The flight status information includes the location information and the cruising path of the UAV, and the traffic protection zone includes an impact protection zone and a strict protection zone; The dividing of the traffic protection zone based on the video stream and the flight status information includes: identifying an area in the video stream by combining the location information and the cruise path, When it is determined according to the recognition result that the area includes a preset location, a range with a first distance as a radius and centered on the preset location is divided into the impact protection zone, and a range with a second distance as a radius is divided into the strict protection zone.
3. The rail transit protection zone inspection control system according to claim 1 is characterized in that: The identifying target object information of the traffic protection zone based on the video stream includes: Acquire an image associated with the traffic protection zone in the video stream; Preprocessing the image to obtain a preprocessed image, and performing feature extraction processing on the preprocessed image to obtain image features; An image recognition model is called to perform classification processing based on the image features to obtain the type and position of the target object in the traffic protection zone, and the type and position of the target object are used as the target object information.
4. The rail transit protection zone inspection control system according to claim 3 is characterized in that: The preprocessing of the image to obtain a preprocessed image includes: The image is sequentially subjected to scaling processing, cropping processing, rotation processing and brightness adjustment processing to obtain the pre-processed image.
5. The rail transit protection zone inspection control system according to claim 3 is characterized in that: The step of analyzing the target object information to obtain an analysis result includes: Performing type matching processing on the target object type and the preset object type to obtain a type matching result; Performing position matching processing based on the position of the target object and the position of the traffic protection zone to obtain a position matching result; The type matching result and the position matching result are used as the analysis result.
6. The rail transit protection zone inspection control system according to claim 5, characterized in that: The warning information includes the target object information and the location of the traffic protection zone corresponding to the target object; The warning condition includes: the type of the target object is one of the preset object types, and the target object is located in the traffic protection zone.
7. A rail transit protection zone inspection method, characterized in that: include: Control the drone to cruise along a preset route, and transmit back the video stream captured by the drone during the cruise flight and the flight status information of the drone; Divide the traffic protection zone based on the video stream and the flight status information; identify target object information in the traffic protection zone based on the video stream, and analyze the target object information to obtain an analysis result; When the analysis result reaches the alarm condition, the alarm information is displayed in real time.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the rail transit protection zone inspection method as described in claim 7 is implemented.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the rail transit protection zone inspection method as claimed in claim 7 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by the processor, the rail transit protection zone inspection method as claimed in claim 7 is implemented.
Citation Information
Patent Citations
Unmanned aerial vehicle inspection method, device and system and storage medium
CN111726576A
Rail transit protection area automatic patrol method and device based on artificial intelligence
CN112487894A
Full-automatic unmanned aerial vehicle inspection method and system for high-speed railway
CN114373138A
Track traffic protection area patrol device
CN214151720U
Cited By
Unmanned aerial vehicle public security scene patrol inspection system and method based on three-dimensional map
CN120088680A
Rail traffic control protection area inspection warning method based on black and white lists
CN122574690A
