Rail fracture detection system and method suitable for automatic wharf

Abstract

The invention discloses a track fracture detection system and method suitable for an automatic wharf, and the system comprises at least three camera devices which are respectively arranged at the upstream end, the midstream end and the downstream end of a track, and are used for shooting position images of corresponding preset mark points on the track; and the processing unit is connected with the camera device and is configured to comprehensively analyze the moving directions of the preset mark points of the upstream end, the midstream end and the downstream end according to the position image to obtain a judgment result of the track, and the judgment result comprises a broken track or a non-broken track. According to the embodiment of the invention, real-time monitoring of the state of the cart track can be realized, and meanwhile, the requirement on human resources is reduced.

Description

Technical Field

[0001] The present application relates to a track fracture detection system and method applicable to automated terminals, belonging to the field of intelligent terminals. Background Art

[0002] In automated terminal yards, rail-mounted cranes operate entirely unmanned, but the tracks of large cranes can break due to frequent loads. Without real-time monitoring, continued pressure on the broken tracks can damage the wheels and bearings, and even cause derailments. Therefore, track condition monitoring is crucial.

[0003] Traditional inspection methods are mainly manual and have the following obvious limitations:

[0004] (1) Manual inspections require personnel to enter the operation area every week, which not only interferes with the operation of autonomous vehicles but also consumes a lot of human resources;

[0005] (2) Video monitoring has poor timeliness and the detection effect is difficult to guarantee. Summary of the Invention

[0006] In view of this, the present application provides a track fracture detection system and method suitable for automated terminals. At least one embodiment provided in the present application can realize real-time monitoring of the status of trolley tracks while reducing the requirements for human resources.

[0007] In a first aspect, an embodiment of the present application discloses a rail fracture detection system applicable to an automated terminal, the system comprising:

[0008] At least three camera devices are respectively arranged at the upstream end, the midstream end and the downstream end of the track to capture position images of corresponding preset marking points on the track;

[0009] A processing unit is connected to the camera device and is configured to comprehensively analyze the moving directions of the preset marking points at the upstream end, the midstream end and the downstream end based on the position image to obtain a determination result of the track, wherein the determination result includes whether the track is broken or not.

[0010] Furthermore, the track further includes a head end and a tail end, the head end is separated from the upstream end by a preset length, and the tail end is separated from the downstream end by a preset length.

[0011] Furthermore, the length of the track is 800m to 1200m, and the preset length is 10m to 30m.

[0012] Furthermore, the position image includes preceding and following frame images; and the track determination result is obtained by comprehensively analyzing the moving directions of the preset marking points at the upstream end, the midstream end, and the downstream end based on the position image, including:

[0013] Identify and compare the track identification boundary box based on the previous and next frame images to determine the moving direction of the preset marking point;

[0014] The determination result of the track is obtained according to the preset determination rules and the moving direction of the preset marking point.

[0015] Furthermore, determining the moving direction of the preset marking point includes:

[0016] When the displacement of the preset marking point satisfies a preset numerical value rule, a direction signal is obtained according to the moving direction.

[0017] Furthermore, obtaining the determination result of the track according to the preset determination rule and the moving direction of the preset marking point includes:

[0018] When the preset mark point at the upstream end or the preset mark point at the downstream end is determined to generate a first direction signal, and the preset mark point at the midstream end is determined to generate a second direction signal within a preset time, it is determined to be a broken track, and the moving direction represented by the first direction signal is opposite to the moving direction represented by the second direction signal.

[0019] Furthermore, when the displacement of the preset marking point satisfies a preset numerical rule, obtaining a direction signal according to the moving direction includes:

[0020] When the displacement exceeds 2 mm within 1 second, a direction signal is obtained according to the moving direction.

[0021] Furthermore, the processing unit includes:

[0022] a first processing subunit, connected to the camera device;

[0023] a second processing subunit, connected to the first processing subunit;

[0024] The position image includes front and rear frame images; and based on the position image, the moving directions of the preset marking points at the upstream end, the midstream end, and the downstream end are comprehensively analyzed to obtain the track determination result, including:

[0025] The first processing subunit identifies and compares the track identification boundary box based on the previous and next frame images to determine the moving direction of the preset marking point;

[0026] The second processing subunit obtains a determination result of the track according to a preset determination rule and the moving direction of the preset marking point.

[0027] Furthermore, the first processing subunit is applied to the terminal local processing server; the second processing subunit is applied to the remote monitoring center;

[0028] The rail fracture detection system further comprises:

[0029] An alarm is connected to the remote monitoring center.

[0030] A second aspect of an embodiment of the present application discloses a rail fracture detection method applicable to an automated terminal, the method comprising:

[0031] Obtaining position images of preset marking points at the upstream, midstream, and downstream ends of the track;

[0032] According to the position image, the moving directions of the preset marking points are comprehensively analyzed to obtain a determination result of the track, wherein the determination result includes whether the track is broken or not.

[0033] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0034] The embodiment of the present application provides a rail fracture detection system and method suitable for automated terminals. The system includes: at least three cameras, respectively arranged at the upstream, midstream and downstream ends of the track, to capture position images of corresponding preset marking points on the track; a processing unit, connected to the camera, configured to comprehensively analyze the movement directions of the preset marking points at the upstream, midstream and downstream ends based on the position images, and obtain a determination result of the track, wherein the determination result includes whether the track is broken or not. The embodiment of the present application deploys three cameras at the upstream, midstream and downstream ends of the track to capture the position images of the preset marking points on the track in real time, and the processing unit comprehensively analyzes the displacement of each marking point to achieve automatic monitoring of the status of the trolley track. The system can operate 24 hours a day without human intervention, avoiding the safety risks and operational interference of traditional manual inspections, and significantly improving detection efficiency and accuracy, effectively preventing equipment damage and derailment accidents caused by track fractures, and providing a reliable and economical track health monitoring solution for automated terminals. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without any creative work.

[0036] Figure 1 A schematic diagram of a rail fracture detection system suitable for an automated terminal provided in an embodiment of the present application.

[0037] Figure 2A schematic diagram of a rail fracture detection system suitable for an automated terminal provided in an embodiment of the present application.

[0038] Figure 3 A schematic diagram of a trolley track monitoring arrangement provided in an embodiment of the present application.

[0039] Figure 4 A schematic diagram of a rail fracture detection method suitable for an automated terminal provided in an embodiment of the present application.

[0040] Figure 5 A schematic diagram of a rail fracture detection device suitable for an automated terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only 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 making creative efforts should fall within the scope of protection of the present invention.

[0042] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0043] Example 1:

[0044] Figure 1 This is a schematic diagram of a rail fracture detection system suitable for an automated terminal provided in an embodiment of the present application. Figure 1 As shown, the system may include: at least three camera devices 100, respectively positioned at the upstream, midstream, and downstream ends of a track, to capture position images of corresponding preset marker points on the track; a processing unit 200, connected to the camera devices 100, configured to comprehensively analyze the movement directions of the preset marker points at the upstream, midstream, and downstream ends based on the position images, and obtain a determination result of whether the track is broken or not.

[0045] Figure 2 A schematic diagram of another rail fracture detection system suitable for automated terminals provided in an embodiment of the present application. Figure 2 System and Figure 1 The difference between these systems lies in that the processing unit 200 includes a first processing subunit 201 connected to the camera device 100 and a second processing subunit 202 connected to the first processing subunit 201. For example, the first processing subunit is used in a local terminal processing server, while the second processing subunit is used in a remote monitoring center. The rail break detection system also includes an alarm connected to the remote monitoring center to alert terminal operators of a rail break. The default rail lifting starting point is the upstream source.

[0046] Figure 3 This is a schematic diagram of a vehicle track monitoring arrangement provided in an embodiment of the present application. Figure 3 As shown, the track further includes a head end and an end end, the head end and the upstream end are separated by a preset length, the end end and the downstream end are separated by a preset length, and the midstream end is arranged in the middle of the track. The total length of the track can be 800m, 850m, 900m, 950m, 1000m, 1050m, 1100m, 1150m or 1200m, and the preset length can be 10m, 15m, 20m, 25m or 30m. For example, the track is a rectangular structure, and the preset marking point A (or monitoring point or marking point or identification) is arranged on the side edge along its length direction. The marking point can be formed by the surface shape of a circular trough or a triangular trough on the track, or the marking point is a yellow circular marker installed on the side of the track.

[0047] A. The camera takes high-speed photos of three marking points on the track in real time. After shooting, the images are transmitted to the terminal's local processing server for image processing and intelligent algorithm analysis.

[0048] A color segmentation algorithm is used to preserve the track markers in the image, facilitating subsequent target tracking. The program first converts the image from RGB to HSV color space, then calculates the maximum and minimum values ​​of each HSV channel for each pixel, and sets a threshold to binarize the image. Morphological operations are then used to remove noise, ultimately yielding the segmentation result.

[0049] First, convert the RGB values ​​to between 0 and 1:

[0050] R=R / 255,G=G / 255,B=B / 255

[0051] Then, calculate the HSV value:

[0052] V=max(R,G,B)

[0053]

[0054] If the calculated H value is less than 0, add 360 to get the final H value:

[0055] H=H+360

[0056] Finally, convert each value to between 0 and 255:

[0057] H=H / 2

[0058] S=S*255

[0059] V=V*255

[0060] In this embodiment, the track marker color is yellow. The common HSV range of yellow is (25, 70, 50)-(35, 255, 255). The HSV value of the pixel in the image is compared with it. If it falls within the range, the pixel is set to 1, otherwise it is set to 0. This can obtain a binary image that only retains the yellow part. The image is then eroded to remove isolated noise points, and then the reverse dilation operation is performed. The principle of erosion is: for a pixel, it is an AND operation with the other 8 pixels in its neighborhood, while dilation is an OR operation. The erosion process is as follows:

[0061] p=p1&p2&p3&p4&p5&p6&p7&p8&p9

[0062] Where: p is the target pixel, p1, p2, p3, p4, p5, p6, p7, p8, p9 are the pixels around the target pixel, and & is the AND operation.

[0063] After obtaining the binary image, we first count the x and y coordinates of the binarized image to determine the coordinates of each pixel. We then identify the region where the moving target is located, where the maximum and minimum x-values ​​of the pixels in the target region are used as the right and left edges of the rectangular bounding box, respectively, and the maximum and minimum y-values ​​of the pixels are used as the bottom and top edges of the rectangular bounding box, respectively. Finally, we mark the target region and add a bounding box. This creates a bounding box, representing the moving target region.

[0064] After that, the target needs to be tracked, and the SORT algorithm is used to calculate the estimated value b predicted by the Kalman filter. p and the measurement value b obtained by the target detection algorithm m , use the Hungarian algorithm to match, and then use b p and b m Update the current state and get b o , as a result of tracking, where bp It is to predict the moving target bounding rectangle bbox of frame t based on the information from 1 to t-1, b m is the bbox of frame t measured by the motion target detection algorithm, b o Is the optimal estimate. Kalman filter recursive principle: First calculate the state prediction value, the error covariance matrix between the state prediction value and the state true value, the formula is as follows:

[0065]

[0066] Where, is the predicted value of the state vector at time k-1, is the estimated value at time k-1, u k-1 is the acceleration at time k-1 and is also the input variable, A is the state transfer matrix, and B is the control matrix used to convert the input into state.

[0067] Calculate the Kalman gain K based on the above two values ​​and then get the estimated value. The formula is as follows:

[0068] z k =Hx k +v k

[0069] Where K k is the Kalman gain at time k, z k is the state measurement value at time k, v k is the measurement noise, H is the state variable to measurement conversion matrix, is the estimated value at time k.

[0070] Finally, the error covariance matrix between the estimated value and the true value is calculated to prepare for the next recursion:

[0071]

[0072] The task of the Hungarian algorithm is to match the bbox of frame t with the bbox of frame t-1 to complete the tracking. The matching criterion is "minimum loss". The loss is represented by the loss matrix. The loss matrix in the SORT algorithm is expressed by b p and b m The loss matrix is ​​defined by the IOU (intersection-over-union) of

[0073] As objects enter and leave the image, unique identities need to be created or destroyed accordingly. To create the tracker, SORT considers any detection with an overlap less than IOUmin to indicate the presence of an untracked object. The tracker is initialized with the geometry of a bounding box with velocity set to zero.

[0074] Next, we need to detect the magnitude and direction of the track marker's movement. The criterion is that the displacement exceeds 2 mm within 1 second. If it moves to the left, a "+" is output; if it moves to the right, a "-" is output. Displacement and direction can be monitored by comparing the identified track marker bounding box in the current image with the center point or boundary of the bounding box from 1 second ago.

[0075] In other embodiments, a neural network algorithm may be used to identify the marker points, and an image registration algorithm may be used to obtain the corresponding displacement and direction.

[0076] B. After receiving trigger signals from each monitoring point, the remote monitoring center performs a verification and judgment. Specifically, when the upstream and downstream monitoring points trigger a "+" or "-" signal, the center verifies the signal with the trigger signal from the midstream monitoring point. For example, if the midstream monitoring point triggers opposite signals within 2 seconds, the track is judged to be broken and an alarm is reported to the remote monitoring system, along with comparison images before and after the judgment.

[0077] Table 1 Preset judgment rules

[0078] Upstream monitoring point Midstream monitoring point Downstream monitoring points Judgment results + - / Broken Track + + / Non-broken rail - - / Non-broken rail - + / Broken Track / - + Broken Track / - - Non-broken rail / + + Non-broken rail / + - Broken Track

[0079] Example 2:

[0080] Figure 4 This is a schematic diagram of a rail fracture detection method applicable to an automated terminal provided in an embodiment of the present application. Figure 4 As shown, the method may include the following steps:

[0081] S401 acquires position images of preset marking points at the upstream end, midstream end, and downstream end of the track.

[0082] S402 comprehensively analyzes the moving directions of the preset marking points according to the position image to obtain a determination result of the track, wherein the determination result includes whether the track is broken or not.

[0083] Example 3:

[0084] Figure 5 This is a schematic diagram of a track fracture detection device suitable for an automated terminal provided in an embodiment of the present application. Figure 5 As shown, the device may include the following modules:

[0085] The acquisition module 501 is used to acquire position images of preset marking points at the upstream end, midstream end and downstream end of the track.

[0086] The analysis module 502 is configured to comprehensively analyze the moving directions of the preset marking points according to the position image to obtain a determination result of the track, wherein the determination result includes whether the track is broken or not.

[0087] Example 4:

[0088] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention when running.

[0089] The above-mentioned memory may refer to a device inside a computer for storing data and programs, and may include memory, hard disk, etc., wherein the memory may be used to temporarily store running programs and data, the hard disk may be used to store programs and data for a long time, and the memory may be used to enable the computer to read and write data, as well as execute programs; the above-mentioned processor may be responsible for executing instructions in computer programs and performing data processing, and may be responsible for controlling and executing various operations, including arithmetic operations, logical operations, data transmission, etc.

[0090] Example 5:

[0091] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0092] The above-mentioned computer storage medium may refer to a medium in a computer memory used to store certain discontinuous physical quantities. Computer storage media mainly include semiconductors, magnetic cores, magnetic drums, magnetic tapes, laser disks, etc. The stored program included in the computer-readable storage medium may be a set of instructions that can be recognized and executed by a computer, running on an electronic computer, and serving as an information tool to meet certain needs of people.

[0093] Example 6:

[0094] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0095] The above-mentioned computer program product may refer to a software program that has been written, tested and released, which can be run on a computer or other device. The computer program product may include an application, an operating system, tool software, etc., which is used to implement specific functions or solve specific problems.

[0096] Example 7:

[0097] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0098] The above-mentioned non-volatile computer-readable storage medium may refer to a medium for storing data. The non-volatile computer-readable storage medium can keep the data from being lost when the power is off, and can be used to store long-term data, such as operating systems, applications and user files. The non-volatile storage medium may include hard disk drives, solid-state drives, optical disks and flash memory storage devices, etc.

[0099] Example 8:

[0100] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0101] The above-mentioned computer program may refer to a collection of instructions used to tell a computer to perform a specific task or operation. A computer program may be written by a programmer using a specific programming language and may include algorithms, data structures, logic, and control flows. Computer programs may be used for a variety of purposes, including application software, operating systems, and the like.

[0102] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0104] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0105] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or 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, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0107] In summary, this embodiment has the following advantages over the prior art:

[0108] (1) Real-time monitoring and alarm: The visual inspection system can realize real-time monitoring of the track status, and an alarm can be triggered immediately when a break occurs to avoid the escalation of the accident.

[0109] (2) Efficient monitoring point design: Only three monitoring points are required, 20 meters at each end and 500 meters in the middle of the entire track (1000 meters). This monitoring point design is based on mechanical analysis. The 20-meter area at each end of the track has a very low risk of fracture due to uniform stress distribution, while the middle section is a stress-concentrated and vulnerable area, so fracture signals can be accurately captured without full coverage monitoring.

[0110] (3) Algorithm-based accurate judgment: Based on the displacement changes of three marking points, the algorithm comprehensively judges the track fracture status with low false alarm rate and high reliability.

[0111] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A rail fracture detection system suitable for automated terminals, characterized in that: include: At least three camera devices are respectively arranged at the upstream end, the midstream end and the downstream end of the track to capture position images of corresponding preset marking points on the track; A processing unit is connected to the camera device and is configured to comprehensively analyze the moving directions of the preset marking points at the upstream end, the midstream end and the downstream end based on the position image to obtain a determination result of the track, wherein the determination result includes whether the track is broken or not.

2. The rail fracture detection system according to claim 1, characterized in that: The track further includes a head end and a tail end, wherein the head end is spaced from the upstream end by a preset length, and the tail end is spaced from the downstream end by a preset length.

3. The rail fracture detection system according to claim 2, characterized in that: The length of the track is 800m to 1200m, and the preset length is 10m to 30m.

4. The rail fracture detection system according to claim 1, characterized in that: The position image includes front and rear frame images; and based on the position image, the moving directions of the preset marking points at the upstream end, the midstream end, and the downstream end are comprehensively analyzed to obtain the track determination result, including: Identify and compare the track identification boundary box based on the previous and next frame images to determine the moving direction of the preset marking point; The determination result of the track is obtained according to the preset determination rules and the moving direction of the preset marking point.

5. The rail fracture detection system according to claim 4, characterized in that: Determining the moving direction of the preset marking point includes: When the displacement of the preset marking point satisfies a preset numerical value rule, a direction signal is obtained according to the moving direction.

6. The rail fracture detection system according to claim 5, characterized in that: Obtaining the determination result of the track according to the preset determination rule and the moving direction of the preset marking point includes: When the preset mark point at the upstream end or the preset mark point at the downstream end is determined to generate a first direction signal, and the preset mark point at the midstream end is determined to generate a second direction signal within a preset time, it is determined to be a broken track, and the moving direction represented by the first direction signal is opposite to the moving direction represented by the second direction signal.

7. The rail fracture detection system according to claim 5, characterized in that: When the displacement of the preset marking point satisfies a preset numerical rule, obtaining a direction signal according to the moving direction includes: When the displacement exceeds 2 mm within 1 second, a direction signal is obtained according to the moving direction.

8. The rail fracture detection system according to claim 1, characterized in that: The processing unit includes: a first processing subunit, connected to the camera device; a second processing subunit, connected to the first processing subunit; The position image includes front and rear frame images; and based on the position image, the moving directions of the preset marking points at the upstream end, the midstream end, and the downstream end are comprehensively analyzed to obtain the track determination result, including: The first processing sub-unit identifies and compares the track identification boundary box based on the previous and next frame images to determine the moving direction of the preset marking point; The second processing subunit obtains a determination result of the track according to a preset determination rule and the moving direction of the preset marking point.

9. The rail fracture detection system according to claim 8, characterized in that: The first processing subunit is applied to the local processing server of the terminal; the second processing subunit is applied to the remote monitoring center; The rail fracture detection system further comprises: An alarm is connected to the remote monitoring center.

10. A rail fracture detection method suitable for automated terminals, characterized in that: include: Obtaining position images of preset marking points at the upstream, midstream, and downstream ends of the track; According to the position image, the moving directions of the preset marking points are comprehensively analyzed to obtain a determination result of the track, wherein the determination result includes whether the track is broken or not.

Images