Railway wagon underbody residue detection system, method and apparatus

Abstract

The application relates to a railway freight car bottom residual detection system, method and device. The railway freight car bottom residual detection system comprises a front-end acquisition module and a control device connected with the front-end acquisition module; the front-end acquisition module comprises a laser radar acquisition module arranged on a column and a cross beam of a portal frame respectively and a high-definition camera module arranged on the cross beam of the portal frame; the laser radar acquisition module is used for acquiring car body side scanning data and car body bottom scanning data, and the high-definition camera module is used for acquiring image data; the control device obtains residual mark information based on the car body bottom scanning data, and synthesizes the residual mark information and the image data into internal pre-synthesized pictures; the control device processes the car body side scanning data to obtain car body segmentation data, and outputs a single-carriage image used for representing an abnormal state of a car bottom. The application improves the accuracy and real-time performance of acquired car body information, and further improves the detection precision and detection quality of the car bottom residual, and reduces operation risks.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle detection, in particular to a railway freight car bottom residual detection system, method and device. BACKGROUND

[0002] With the development of vehicle detection technology, vehicle bottom residual detection technology has emerged. At present, empty car bottom residual detection mainly relies on manual on-site checking or simple man-machine combination, for example, whether there is foreign matter is confirmed according to the high-definition video provided by the freight loading video monitoring system, but the imaging is a planar image, which cannot estimate the volume of the residual object, accurately measure and issue warning information, and manual identification of the image is also needed. The data volume of video image is very large, manual identification not only has a large workload, but also is prone to fatigue, and the accuracy is not high, which is greatly affected by the responsibility, working attitude, physical condition and working period of the freight inspection personnel, and is prone to missed detection, false detection and even undetected, etc. Phenomenon, causing railway operation safety hazards, and cannot meet the requirement of rapid response to emergencies.

[0003] In the implementation process, the inventor found that at least the following problems exist in the prior art: the current vehicle bottom residual detection method or traditional method has the problems of low accuracy. SUMMARY

[0004] Therefore, it is necessary to provide a railway freight car bottom residual detection system, method and device capable of improving detection accuracy in view of the above technical problems.

[0005] In order to achieve the above purpose, the railway freight car bottom residual detection system provided by the embodiments of the present application comprises a front-end acquisition module and a control device connected to the front-end acquisition module; the front-end acquisition module is used to acquire point cloud data and image data of a railway freight car compartment; the point cloud data comprises compartment side scanning data and compartment bottom scanning data;

[0006] The front-end acquisition module comprises a laser radar acquisition module arranged on the column and the cross beam of the gantry respectively, and a high-definition camera module arranged on the cross beam of the gantry; the laser radar acquisition module is used to acquire the compartment side scanning data and the compartment bottom scanning data, and the high-definition camera module is used to acquire the image data;

[0007] The control device marks the bottom residual based on the compartment bottom scanning data to obtain residual marking information, and synthesizes the residual marking information and the image data into an internal pre-synthesis picture; the control device processes the compartment side scanning data to obtain compartment segmentation data, and outputs a single-compartment image representing an abnormal state of the bottom according to the compartment segmentation data and the internal pre-synthesis picture.

[0008] In one of the embodiments, the control device obtains corresponding car numbers according to the car segmentation data and the single-carriage image to track the corresponding freight carriages.

[0009] When the control device confirms the presence of the abnormal car bottom, the control device outputs the single-carriage image to the server; the server is configured to transmit the single-carriage image to the client.

[0010] In one of the embodiments, the high-definition camera module includes a face array camera.

[0011] A railway freight car bottom residue detection method includes the following steps:

[0012] The data receiving module is configured to receive point cloud data and image data of a railway freight carriage transmitted by the front-end acquisition module; the point cloud data includes car side scanning data and car bottom scanning data; the front-end acquisition module includes a laser radar acquisition module arranged on the column and the beam of the gantry, and a high-definition camera module arranged on the beam of the gantry; the laser radar acquisition module is configured to acquire the car side scanning data and the car bottom scanning data, and the high-definition camera module is configured to acquire the image data.

[0013] The car bottom residue is marked based on the car bottom scanning data to obtain residue marking information, and the residue marking information and the image data are synthesized into an internal pre-synthesis picture.

[0014] The car segmentation data is obtained by processing the car side scanning data, and a single-carriage image used to represent an abnormal state of the car bottom is output according to the car segmentation data and the internal pre-synthesis picture.

[0015] In one of the embodiments, the method further includes the step of obtaining corresponding car numbers according to the car segmentation data and the single-carriage image to track the corresponding freight carriages.

[0016] In one of the embodiments, the method further includes the step of processing the car bottom scanning data by using 3D modeling to obtain the volume of the car bottom residue.

[0017] A railway freight car bottom residue detection device includes:

[0018] The data receiving module is configured to receive point cloud data and image data of a railway freight carriage transmitted by the front-end acquisition module; the point cloud data includes car side scanning data and car bottom scanning data; the front-end acquisition module includes a laser radar acquisition module arranged on the column and the beam of the gantry, and a high-definition camera module arranged on the beam of the gantry; the laser radar acquisition module is configured to acquire the car side scanning data and the car bottom scanning data, and the high-definition camera module is configured to acquire the image data.

[0019] The picture synthesis module is configured to mark the residues on the bottom of the carriage based on the bottom scanning data of the carriage, to obtain residue marking information, and to synthesize the residue marking information and the image data into an internal pre-synthesized picture.

[0020] The image output module is configured to process the side scanning data of the carriage to obtain carriage segmentation data, and to output a single-carriage picture representing the abnormal state of the bottom of the carriage according to the carriage segmentation data and the internal pre-synthesized picture.

[0021] In one of the embodiments, the system further comprises a car number tracking module configured to obtain the corresponding car number of the carriage according to the carriage segmentation data and the single-carriage picture, so as to track the corresponding carriage of the freight train.

[0022] A computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the method.

[0023] One of the above technical solutions has the following advantages and beneficial effects:

[0024] The railway freight train residue detection system provided by the present application can replace manual detection of residues on the bottom of the carriage, and can obtain point cloud data of the railway freight train carriage by using a laser radar acquisition module and obtain image data of the railway freight train carriage by using a high-definition camera module, thereby improving the accuracy and real-time performance of the railway freight train carriage information, and further improving the detection accuracy of residues on the bottom of the carriage, and solving the problem that residues on the bottom of the carriage of the existing railway freight train are not easy to be found, while greatly improving the detection quality of residues on the bottom of the carriage and reducing the operation risk. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0026] Figure 1 FIG. 1 is a schematic diagram of a railway freight train residue detection system in one embodiment;

[0027] Figure 2 FIG. 2 is a schematic diagram of a railway freight train residue detection system in another embodiment;

[0028] Figure 3 FIG. 3 is a flowchart of a railway freight train residue detection method in one embodiment;

[0029] Figure 4 FIG. 4 is a flowchart of a railway freight train residue detection method in another embodiment. DETAILED DESCRIPTION

[0030] For the purposes of this application, reference will be made to the accompanying drawings in which embodiments of the application are illustrated. The application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and fully convey the scope of the application to those skilled in the art.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application.

[0032] It is to be understood that the terms "first", "second", and the like, used herein do not connote any hierarchy or order, but are used to distinguish one element from another.

[0033] Spatially relative terms, such as "beneath", "below", "lower", "under", "above", "upper" and the like, can be used herein for ease of description to describe one element or feature's relationship to another element(s) or feature(s) as illustrated in the figures. It will be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device described is turned over, elements described as "below" or "beneath" other elements or features would then be oriented "above" the other elements or features. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device can also be oriented in the other direction, and the spatially relative terms used herein are intended to encompass such additional orientations. It is to be understood that the spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if a device described is turned over, elements described as "below" or "beneath" other elements or features would then be oriented "above" the other elements or features. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device can also be oriented in the other direction, and the spatially relative terms used herein are intended to encompass such additional orientations.

[0034] It is to be understood that when an element is referred to as being "connected" to another element, it can be directly connected to the other element, or connected to the other element through intervening elements. Also, "connected" as used herein, if connected objects have transmission of electrical signals or data between them, should be understood as "electrically connected", "communicatively connected", and the like.

[0035] As used herein, the singular forms "a", "an" and "the" include plural referents unless the context clearly dictates otherwise. It will be further understood that the terms "comprises", "comprising", "includes" and / or "including", or the like, when used in this specification, specify the presence of stated features, integers, steps, operations, elements, components, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof. Also, the term "and / or" includes any and all combinations of associated items.

[0036] Taking a coal truck as an example, coal needs to go through the process of coal washing after mining, and the washed coal has a certain water content; when the temperature is low, the coal will freeze during the process of transportation by railway truck, and freeze together with the side wall and the bottom of the truck to form a "frozen truck" phenomenon. If the "frozen truck" phenomenon occurs, the coal will stick to the bottom of the truck, which not only easily causes waste, but also affects the unloading efficiency. The existing detection of residual materials on the bottom of the truck mainly relies on manual on-site inspection or simple man-machine combination, which is prone to miss detection, false detection or even no detection, causing potential safety hazards of railway operation and failing to meet the requirement of rapid response to emergencies. Therefore, it is necessary to improve the accuracy of detecting residual materials on the bottom of the railway truck to timely find the abnormality of the bottom of the railway truck, and thus improve the transportation efficiency of the railway truck.

[0037] It should be noted that the railway truck in the present application refers to an open wagon with an end and a side wall but no roof; the bottom of the truck refers to the bottom of the inner surface of the truck from the top-down perspective. The target truck can be stationary or moving, and can be in different climates and natural environments.

[0038] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0039] In one embodiment, as shown in Figure 1 The present application provides a railway truck residual material detection system, which comprises a front-end acquisition module 20 and a control device 40 connected to the front-end acquisition module 20; the front-end acquisition module 20 is used to acquire point cloud data and image data of the truck; the point cloud data comprises truck side wall scanning data and truck bottom scanning data;

[0040] The front-end acquisition module 20 comprises a laser radar acquisition module 220 arranged on the column and the cross beam of the gantry respectively, and a high-definition camera module 240 arranged on the cross beam of the gantry; the laser radar acquisition module 220 is used to acquire the truck side wall scanning data and the truck bottom scanning data, and the high-definition camera module 240 is used to acquire the image data;

[0041] The control device 40 marks the bottom residues of the car based on the bottom scanning data of the car, obtains residue marking information, and synthesizes the residue marking information and the image data into an internal pre-synthesis picture; the control device 40 processes the side scanning data of the car to obtain car segmentation data, and outputs a single-car image for representing an abnormal state of the car bottom according to the car segmentation data and the internal pre-synthesis picture.

[0042] Specifically, the laser radar acquisition module 220 can include a laser radar; the laser radar uses laser as a signal source, emits pulsed laser from the laser of the laser radar to the target car, and records the emission time by a timer; the pulsed laser is scattered on the surface of the target car, and is received by the receiver of the laser radar, while the return time is recorded by the timer; the distance between the laser radar and each target point on the target car is calculated according to the time difference between the reflection and the return; the pulsed laser continuously scans the target car, and the data (point cloud data) of all target points on the target car can be obtained; in some examples, the control device 40 can image process the point cloud data to obtain accurate three-dimensional point cloud; further, the control device 40 can synthesize process the point cloud data and the image data to obtain accurate three-dimensional image.

[0043] Further, as shown in Figure 2 The laser radar acquisition module 220 can include a laser radar 222 arranged on the cross beam of the gantry, a laser radar 224 and a laser radar 226 arranged on the column of the gantry; the laser radar 222 scans the bottom of the car from top to bottom, and the scanning fan formed is perpendicular to the plane where the rail is located, and is used for collecting the bottom scanning data of the car; the laser radar 224 and the laser radar 226 scan the side of the car from both sides, and the projection line of the scanning fan on the ground is perpendicular to the direction line where the rail is located, and is used for collecting the side scanning data of the car; the image data collected by the high-definition camera module 240 arranged on the cross beam of the gantry is the image data of the bottom of the car; the control device 40 marks the bottom residues of the car based on the bottom scanning data of the car, obtains residue marking information, obtains the point cloud data of the residue marking information, and synthesizes the residue marking information and the image data into an internal pre-synthesis picture, which contains the residue marking information; the control device 40 processes the side scanning data of the car to obtain car segmentation data, which is data containing the boundary information of each car, and is used for outputting the internal pre-synthesis picture as a single-car image; further, the control device 40 outputs a single-car image for representing an abnormal state of the car bottom according to the car segmentation data and the internal pre-synthesis picture, and the single-car image contains the residue marking information.

[0044] In some examples, the laser radar scanning speed can be 3x400 lines / s, the distance accuracy can reach ±2.5 cm, and the angular resolution can be 0.22°; the laser radar detects the vehicle bottom residue, and the smallest residue that can be detected is 60 cmx60 cmx30 cm; the included angle formed by the scanning sector of the laser radar can be 60°; the vehicle compartment bottom scanning data can include vehicle compartment length data and vehicle compartment width data; the vehicle compartment bottom scanning data can also include the distance of each target point on the vehicle compartment bottom to the laser radar 222, and the control device 40 can compare the distance of each target point in the vehicle compartment bottom scanning data with the preset distance, and mark the target point with a distance less than the preset distance as a vehicle bottom residue; the vehicle compartment side scanning data can include vehicle entry or tail trigger information, and the control device 40 can obtain vehicle compartment segmentation data according to the vehicle entry or tail trigger information; the vehicle compartment side scanning data can also include vehicle compartment height data for overheight detection, and the vehicle compartment height data is compared with the preset vehicle compartment height to detect whether the train exceeds the limit height; the vehicle compartment side scanning data can also include vehicle compartment length data, and the train speed of the railway wagon is obtained, and the train speed measurement accuracy can reach ±0.2 km / h; the high-definition camera module can include a face array camera; the image data can include pictures and videos; the vehicle bottom abnormal state can include vehicle bottom residue abnormalities; the single wagon image can be a three-dimensional image; the single wagon image is scaled with the actual vehicle compartment in proportion, and there is no stretching or compression phenomenon on the vehicle compartment length, and the station staff can manually review the vehicle bottom abnormal state of the wagon by checking the single wagon image.

[0045] The present application provides a railway wagon bottom residue detection system, which replaces manual detection of vehicle bottom residues, and uses a laser radar acquisition module to obtain point cloud data of a railway wagon compartment and a high-definition camera module to obtain image data of the railway wagon compartment, thereby improving the accuracy and real-time performance of obtaining railway wagon compartment information, and further improving the detection accuracy of vehicle bottom residues, solving the problem that existing railway wagon bottom residues are not easy to be found, and greatly improving the detection quality of vehicle bottom residues and reducing the operation risk.

[0046] In one embodiment, the control device 40 obtains the corresponding vehicle compartment number according to the vehicle compartment segmentation data and the single wagon image to track the corresponding wagon compartment.

[0047] Specifically, the control device 40 can obtain the corresponding vehicle compartment number, and when detecting the vehicle bottom abnormal state, the corresponding wagon compartment can be tracked through the vehicle number. In some examples, the control device 40 can locate the corresponding wagon compartment according to the single wagon image and be used for alarm.

[0048] In one embodiment, a server connected to the control device 40 and a client connected to the server are further included.

[0049] The control device 40 outputs the single-carriage image to the server in the case of confirming the occurrence of the underframe abnormality; and the server is configured to transmit the single-carriage image to the client.

[0050] Specifically, the image of the railway freight car displayed by the client can include a two-dimensional image, a three-dimensional image, and a video; the two-dimensional image and the video can include image data obtained by the high-definition camera module; and the three-dimensional image can include a three-dimensional point cloud obtained by point cloud data imaging processing and a three-dimensional image obtained by point cloud data and image data synthesis processing.

[0051] In some examples, the client can view a video playback, can play back the video of the entire train of railway freight cars, and supports synchronous playing, multi-picture synchronous playing, playback (slow playing, fast playing, and reverse playing), positioning, zooming (zooming in and zooming out), and the like; the client can view the three-dimensional point cloud or the three-dimensional image of the freight car, the three-dimensional point cloud or the three-dimensional image can clearly display the underframe residues, and the client can view the car number corresponding to the freight car with the underframe residues; the client can view the volume calculation value of the underframe residues; the client can view the operation log of the railway freight car underframe residue detection system, and can comprehensively query the operation log according to the train number, the car number, the date, and the like; the client can provide a function of manually marking a problem part during playback, and the client can also provide several kinds of data dictionaries for quick inspection, and can measure the inspection part and determine whether the loading state meets the requirements.

[0052] In one of the embodiments, the high-definition camera module 240 includes a face array camera.

[0053] Specifically, the image collected by the face array camera is a one-time acquired face array image, and the face array image is composed of multiple rows. In some examples, the face array image collected by the face array camera can be synthesized into a continuous railway freight car underframe image.

[0054] In some examples, the railway freight car underframe residue detection system can be connected with a freight transportation measurement safety monitoring system through a network interface, realize integration with existing freight transportation platform information, and enable the picture and video information of the loading state of the freight car to be centrally displayed through the freight transportation measurement safety monitoring system, and also enable the loading state detection information of the railway freight car, the picture information of the railway freight car, the video information, and the like to be remotely viewed by the client through the client. The railway freight car underframe residue detection system and the freight transportation measurement safety monitoring system realize information sharing through the network interface, and thus realize railway freight car abnormal state detection, uploading and downloading of the picture information and the video information of the railway freight car.

[0055] In some examples, the railway wagon bottom residue detection system can back up data, for example, back up various types of data in a centralized manner, and the backup range can cover the data of the railway wagon bottom residue detection system and the system connected thereto, as well as the data of various related applications. The data backup can support manual backup and automatic backup according to the operation and maintenance requirements, and further can provide backup task scheduling function; can support full backup and incremental backup; can support off-site backup, and can completely recover to the data state at the time of the last backup command execution according to the existing data backup; the railway wagon bottom residue detection system can provide storage and transmission encryption function, and end-to-end encryption for key information, and further can provide sensitive data security and desensitization function; the railway wagon bottom residue detection system can provide data access permission control function, maintain data access personnel and role related information, strictly authenticate and authorize the access of data, and record data access log; the system can set corresponding permissions according to the role, divide users with the same user permissions into corresponding user groups, and manage users through user groups and user roles.

[0056] In some examples, as shown in Table 1, for the bottom detection, the bottom scanning data of the carriage is obtained for the wagon bottom residue detection; for the top detection, the side scanning data of the carriage is obtained for the overheight detection and overload detection.

[0057] Table 1

[0058]

[0059]

[0060] The present application can greatly reduce the operation labor cost, effectively improve the operation quality, and save the operation evidence by using the railway wagon bottom residue detection system to replace the manual standardized inspection operation, and provide the basis for subsequent data search and railway wagon line tracing; the point cloud data and image data of the railway wagon carriage are obtained to detect the railway wagon carriage in all directions, make up for the one-sidedness of manual operation, and fill the visual angle blind spot of manual detection, and further reduce the risk of railway wagon operation under abnormal state.

[0061] A railway wagon bottom residue detection method, as shown in Figure 3 , includes the steps of:

[0062] S310, receiving the point cloud data and the image data of the railway wagon car transmitted by the front-end acquisition module 20; the point cloud data includes the car side scanning data and the car bottom scanning data; the front-end acquisition module 20 includes a laser radar acquisition module 220 arranged on the column and the beam of the gantry, and a high-definition camera module 240 arranged on the beam of the gantry; the laser radar acquisition module 220 is used to acquire the car side scanning data and the car bottom scanning data, and the high-definition camera module 240 is used to acquire the image data;

[0063] S320, marking the car bottom residues based on the car bottom scanning data to obtain residue marking information, and synthesizing the residue marking information and the image data into an internal pre-synthesis picture;

[0064] S330, processing the car side scanning data to obtain car segmentation data, and outputting a single wagon image for representing the car bottom abnormal state according to the car segmentation data and the internal pre-synthesis picture.

[0065] Specifically, a pulsed laser is emitted to the target car, and the emission time is recorded. The pulsed laser is scattered on the surface of the target car, and the return time is recorded. The target car is continuously scanned to obtain the data (point cloud data) of all target points on the target car; in some examples, imaging processing of the point cloud data can obtain accurate three-dimensional point cloud; further, the point cloud data and the image data can be synthesized to obtain accurate three-dimensional images.

[0066] Further, the car bottom is scanned from top to bottom, and the scanning fan is perpendicular to the plane where the rail is located, which is used to acquire the car bottom scanning data; the car side is scanned from both sides, and the projection line of the scanning fan on the ground is perpendicular to the direction line where the rail is located, which is used to acquire the car side scanning data; the acquired image data is the image data of the car bottom; the car bottom residues are marked based on the car bottom scanning data to obtain residue marking information, the point cloud data of the residue marking information is obtained, and the residue marking information and the image data are synthesized into an internal pre-synthesis picture, which contains the residue marking information; the car segmentation data is obtained by processing the car side scanning data, which is data containing the boundary information of each wagon, and is used to output the internal pre-synthesis picture as a single wagon image; further, according to the car segmentation data and the internal pre-synthesis picture, a single wagon image for representing the car bottom abnormal state is outputted, which contains the residue marking information.

[0067] It should be understood that, although Figure 3The steps in the flowchart are shown in sequence according to the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the steps are not strictly limited in sequence, and the steps can be executed in other sequences. Moreover, Figure 3 At least one of the steps in the flowchart can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of the sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least one part of other steps or sub-steps or stages of other steps.

[0068] In one embodiment, the method further includes the step of obtaining a corresponding car number according to the car segmentation data and the single-car image to track the corresponding freight car.

[0069] Specifically, the corresponding car number can be obtained according to the car segmentation data and the single-car image, and when an abnormal state of the car bottom is detected, the corresponding freight car can be tracked through the car number. In some examples, the corresponding freight car can be located according to the single-car image and used for alarm.

[0070] In one embodiment, the method further includes the step of using 3D modeling to process the car bottom scanning data to obtain the volume of the car bottom residue.

[0071] Specifically, the car bottom scanning data is data of all target points of the car bottom (car bottom point cloud data), and 3D modeling is used to process the car bottom scanning data (for example, imaging processing of the car bottom scanning data, or synthesis processing of the car bottom scanning data and image data). The accurate three-dimensional point cloud or three-dimensional image of the car bottom can be obtained, which includes the shape and size information of the car bottom residue. According to the real-time measurement of the car bottom three-dimensional point cloud or three-dimensional image, the volume of the car bottom residue can be obtained. In some examples, the volume of the car bottom ice when the "frozen car" phenomenon occurs can be effectively detected, and the tonnage estimation of the railway freight car can be more accurate according to the density, and the occurrence of overload can be reduced. By obtaining the volume of the car bottom residue, the overload of the railway freight car can be found in time, and personal safety accidents and railway accidents caused by factors such as insufficient manual safety inspection of railway freight cars can be prevented.

[0072] In some examples, as Figure 4As shown, when the truck passes, the area array camera captures the bottom of the truck compartment, obtains image data of the truck compartment, synthesizes the image and stores it; at the same time, the laser radar scans the side and bottom of the truck compartment, obtains the point cloud data of the truck compartment, synthesizes the point cloud and stores it; further, the point cloud includes the point cloud data of the side of the truck compartment and the point cloud data of the bottom of the truck compartment, according to the point cloud data of the side of the truck compartment, the truck compartment can be segmented and analyzed, according to the point cloud data of the bottom of the truck compartment, the foreign matter detection and abnormality determination of the bottom of the truck compartment can be performed; according to the synthesized image and point cloud of the truck compartment, feature positioning (for example, positioning the residual material in the truck compartment which exceeds the preset volume) can be realized, and the detection result is output to the client for display.

[0073] In some examples, the railway truck bottom residual detection method can include learning strategy based on artificial intelligence, realizing automatic accumulation and dynamic optimization of detection experience, and combining with actual railway truck bottom sampling data, simplifying the detection model autonomously, further, reducing the participation of on-site personnel to the greatest extent in the detection process, improving the efficiency of railway truck bottom residual detection, and shortening the operation time.

[0074] A railway truck bottom residual detection device, comprising:

[0075] A data receiving module for receiving point cloud data and image data of a railway truck compartment transmitted by a front-end acquisition module 20; the point cloud data includes truck compartment side scanning data and truck compartment bottom scanning data; the front-end acquisition module 20 includes a laser radar acquisition module 220 arranged on the column and beam of the gantry, and a high-definition camera module 240 arranged on the beam of the gantry; the laser radar acquisition module 220 is used to acquire the truck compartment side scanning data and the truck compartment bottom scanning data, and the high-definition camera module 240 is used to acquire the image data;

[0076] A picture synthesis module for marking the truck bottom residual based on the truck bottom scanning data to obtain residual marking information, and synthesizing the residual marking information and the image data into an internal pre-synthesized picture;

[0077] An image output module for processing the truck compartment side scanning data to obtain truck compartment segmentation data, and outputting a single truck compartment image for representing the truck bottom abnormal state according to the truck compartment segmentation data and the internal pre-synthesized picture.

[0078] In one embodiment, it further includes a car number tracking module for obtaining the corresponding truck compartment car number to track the corresponding truck compartment according to the truck compartment segmentation data and the single truck compartment image.

[0079] The specific limitations of the railway wagon bottom residue detection device can refer to the limitations of the railway wagon bottom residue detection method described above, which will not be repeated here. Each module in the above railway wagon bottom residue detection device can be realized by software, hardware and their combination. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor calls and executes the operations corresponding to each module. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical function division. Actual implementation can have another division method.

[0080] A computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the above method.

[0081] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of the method. In the embodiments provided in the present application, any reference to memory, storage, database or other medium can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0082] In the description of the present specification, the description of the terms "some embodiments", "other embodiments", "ideal embodiments" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example.

[0083] Each technical feature of the above embodiments can be combined arbitrarily. In order to make the description simple, each technical feature in the above embodiments is not described in all possible combinations, however, as long as the combination of these technical features does not exist, it should be considered as the scope of the present specification.

[0084] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a more specific and detailed manner, but should not be construed as limiting the scope of the patent. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A railcar underframe residue detection system, characterized by, The system comprises a front-end acquisition module and a control device connected to the front-end acquisition module; the front-end acquisition module is used to acquire point cloud data and image data of a railway wagon; the point cloud data comprises wagon side scanning data and wagon bottom scanning data; The front-end acquisition module comprises a laser radar acquisition module arranged on a column and a cross beam of a gantry, and a high-definition camera module arranged on a cross beam of the gantry; the laser radar acquisition module is used to acquire the wagon side scanning data and the wagon bottom scanning data, and the high-definition camera module is used to acquire the image data; The control device marks wagon bottom residues based on the wagon bottom scanning data, obtains residue marking information, and synthesizes the residue marking information and the image data into an internal pre-synthesis picture; the control device processes the wagon side scanning data to obtain wagon segmentation data, and outputs a single wagon image representing an abnormal state of a wagon bottom according to the wagon segmentation data and the internal pre-synthesis picture; the single wagon image is a three-dimensional image; The laser radar acquisition module arranged on the column of the gantry is used to scan the wagon side at both sides of the railway wagon to acquire wagon side scanning data; the wagon side scanning data comprises entering or tailing trigger information of the railway wagon; The control device obtains wagon segmentation data according to the entering or tailing trigger information of the railway wagon.

2. The railway wagon bottom residue detection system according to claim 1, wherein The control device acquires corresponding wagon numbers according to the wagon segmentation data and the single wagon image to track corresponding railway wagons.

3. The railway car underbody residue detection system of claim 1 or 2, wherein, The system further comprises a server connected to the control device, and a client connected to the server; The control device outputs the single wagon image to the server when it is confirmed that there is an abnormal state of a wagon bottom; The server is used to transmit the single wagon image to the client.

4. The railway wagon bottom residue detection system according to claim 1, wherein The high-definition camera module comprises a planar array camera.

5. A method of detecting residue on a railway car floor, the method comprising: The method comprises the following steps: Receiving point cloud data and image data of a railway wagon transmitted by a front-end acquisition module; the point cloud data comprises wagon side scanning data and wagon bottom scanning data; the front-end acquisition module comprises a laser radar acquisition module arranged on a column and a cross beam of a gantry, and a high-definition camera module arranged on a cross beam of the gantry; the laser radar acquisition module is used to acquire the wagon side scanning data and the wagon bottom scanning data, and the high-definition camera module is used to acquire the image data; Marking wagon bottom residues based on the wagon bottom scanning data to obtain residue marking information, and synthesizing the residue marking information and the image data into an internal pre-synthesis picture; The vehicle compartment side scanning data is processed to obtain vehicle compartment segmentation data, and a single-compartment vehicle image representing an abnormal state of the vehicle bottom is output according to the vehicle compartment segmentation data and the internal pre-combined picture; the single-compartment vehicle image is a three-dimensional image; the laser radar collecting module arranged on the column of the gantry is used to scan the vehicle compartment sides to collect vehicle compartment side scanning data; the vehicle compartment side scanning data includes entry or tail trigger information of the railway freight car; The vehicle compartment segmentation data is obtained according to the entry or tail trigger information of the railway freight car.

6. The railway car underbody residue detection method of claim 5, wherein, Further comprising steps: According to the vehicle compartment segmentation data and the single-compartment vehicle image, the corresponding vehicle number is obtained to track the corresponding freight car compartment.

7. The railway car underframe residue detection method of claim 5 or 6, wherein, Further comprising steps: The 3D modeling is used to process the vehicle bottom scanning data to obtain the volume of the vehicle bottom residues.

8. A railway car underframe residue detection apparatus, characterized by, Comprise: The data receiving module is used to receive the point cloud data and image data of the railway freight car compartment transmitted by the front-end collecting module; the point cloud data includes vehicle compartment side scanning data and vehicle bottom scanning data; the front-end collecting module includes laser radar collecting modules arranged on the columns and beams of the gantry, and a high-definition camera module arranged on the beam of the gantry; the laser radar collecting module is used to collect the vehicle compartment side scanning data and the vehicle bottom scanning data, and the high-definition camera module is used to collect the image data; the laser radar collecting module arranged on the column of the gantry is used to scan the vehicle compartment sides to collect vehicle compartment side scanning data; the vehicle compartment side scanning data includes entry or tail trigger information of the railway freight car; The picture combining module is used to mark the vehicle bottom residues based on the vehicle bottom scanning data to obtain residue marking information, and combine the residue marking information and the image data into an internal pre-combined picture; The image output module is used to process the vehicle compartment side scanning data to obtain vehicle compartment segmentation data, and output a single-compartment vehicle image representing an abnormal state of the vehicle bottom according to the vehicle compartment segmentation data and the internal pre-combined picture; the single-compartment vehicle image is a three-dimensional image; the vehicle compartment segmentation data is obtained according to the entry or tail trigger information of the railway freight car.

9. The railcar underbody residue detection apparatus of claim 8, wherein, Further comprising: The vehicle number tracking module is used to obtain the corresponding vehicle number according to the vehicle compartment segmentation data and the single-compartment vehicle image to track the corresponding freight car compartment.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 5 to 7.

Images