Interlocking equipment detection method and system based on image recognition

Abstract

The present invention provides an interlocking device detection method and system based on image recognition, the system comprising: a data acquisition module, used to acquire a dispatch feedback image of an interlocking device to be detected; an image recognition module, which detects the state of the interlocking device to be detected according to the dispatch feedback image and an image standard library to determine whether the interlocking device to be detected is in a normal state; wherein the image standard library includes images corresponding to various states of the interlocking device to be detected. The interlocking device detection method and system based on image recognition provided by the present invention acquires an image of the device to be detected by sending a shooting instruction, and compares the image of the device to be detected with the image standard library, thereby realizing automatic detection of the state of the interlocking device and improving detection efficiency.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to an interlocking device detection method and system based on image recognition. Background Art

[0002] With the increase in railway speed and the construction of passenger dedicated lines, EMUs, as the main means of transportation, have high purchase and maintenance costs. In order to improve the utilization rate of EMUs, save investment and reduce costs, it is very necessary to inspect and repair the interlocking equipment in EMUs. When inspecting and repairing the interlocking equipment, a set of interlocking equipment detection system is needed to complete the inspection of the interlocking equipment.

[0003] In the prior art, the state detection method of the interlocking equipment in rail transit is that the test personnel frequently take state images of the equipment to be tested, manually determine whether the equipment to be tested is in a normal state, and send maintenance personnel to the site for confirmation. The operation process is complicated, especially when a certain equipment to be tested fails, it is necessary to go to the site to check all related equipment before determining the specific faulty equipment. This results in low work efficiency of the state detection task of the equipment to be tested, and it is also difficult to achieve the current automated detection requirements of industrial production and complex working environment.

[0004] Therefore, how to design a detection system that can quickly and automatically complete the detection of the interlocking device to be detected has become an urgent problem to be solved. Summary of the invention

[0005] The interlocking device detection system based on image recognition provided by the present invention is used to solve the defects of low detection efficiency and low automation of interlocking device detection in the prior art. It can realize automatic detection of the state of the interlocking device to be detected and improve the detection efficiency.

[0006] In a first aspect, the present invention provides an interlocking device detection system based on image recognition, comprising:

[0007] A data acquisition module, used to determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and to obtain a scheduling feedback image of the interlocking device to be detected;

[0008] An image recognition module detects the state of the interlocking device to be detected according to the scheduling feedback image and the image standard library to determine whether the interlocking device to be detected is in a normal state;

[0009] Wherein, the image standard library includes images corresponding to various states of the interlocking device to be detected; the data acquisition module includes:

[0010] A communication submodule, connected to the interlocking device to be detected, and used to obtain the line configuration data and the communication interface data;

[0011] a data processing submodule, connected to the communication submodule, for reading the line configuration data and the communication interface data, and packaging the line configuration data and the communication interface data according to a packaging rule provided by the interlocking device to be detected;

[0012] A data analysis submodule, connected to the data processing submodule, for analyzing the packaged data to obtain the network IP address, port number and location information;

[0013] The dispatch feedback image acquisition submodule is connected to the data analysis submodule and is used to determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and to obtain the dispatch feedback image of the interlocking device to be detected.

[0014] According to an interlocking device detection system based on image recognition provided by the present invention, the image recognition module includes:

[0015] The image preprocessing submodule is used to perform grayscale processing, binarization processing, enhancement processing and smoothing processing on the scheduling feedback image.

[0016] According to an interlocking device detection system based on image recognition provided by the present invention, the image recognition module further includes: an image analysis submodule for constructing a similarity comparison algorithm according to the Aforge.NET architecture class library;

[0017] The similarity comparison algorithm is used to perform comparative analysis based on the image standard library and the scheduling feedback image to determine whether the interlocking device to be detected is in a normal state.

[0018] An interlocking device detection system based on image recognition provided by the present invention also includes:

[0019] A logic processing module is connected to the image recognition module and is used to generate a state switching instruction when the interlocking device to be detected is in an abnormal state, and drive the interlocking device to be detected according to the state switching instruction to ensure that the interlocking device to be detected is in a normal state after executing the state switching instruction.

[0020] An interlocking device detection system based on image recognition provided by the present invention also includes:

[0021] A display module is connected to the logic processing module and is used to display in real time an image of the interlocking device to be detected after executing the state switching instruction.

[0022] The present invention also provides an interlocking device detection method based on image recognition, comprising:

[0023] Determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected;

[0024] Acquire a dispatch feedback image of the interlocking device to be detected;

[0025] According to the scheduling feedback image and the image standard library, the state of the interlocking device to be detected is detected to determine whether the interlocking device to be detected is in a normal state;

[0026] The standard image library includes images corresponding to various states of the interlocking device to be detected.

[0027] According to an interlocking device detection method based on image recognition provided by the present invention, the state of the interlocking device to be detected is detected according to the scheduling feedback image and the image standard library to determine whether the interlocking device to be detected is in a normal state, including:

[0028] Build a similarity comparison algorithm based on the Aforge.NET architecture class library;

[0029] Based on the similarity comparison algorithm, the image standard library and the scheduling feedback image are compared and analyzed to determine whether the interlocking device to be detected is in a normal state.

[0030] The interlocking device detection system based on image recognition provided by the present invention acquires the image of the device to be detected through a data acquisition module, and compares the image of the device to be detected with an image standard library in combination with an image recognition module, thereby realizing state detection and analysis of the interlocking device, and by utilizing a communication submodule to exchange data with the interlocking device to be detected, realizing automated detection of the state of the interlocking device to be detected, reducing errors caused by human observation, and improving detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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.

[0032] Figure 1 A schematic diagram of the structure of an interlocking device detection system based on image recognition provided by the present invention;

[0033] Figure 2A structural schematic diagram of a data acquisition module provided by the present invention;

[0034] Figure 3 A schematic diagram of the flow of the interlocking device detection method based on image recognition provided by the present invention;

[0035] Figure 4 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0036] 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.

[0037] The interlocking device detection system based on image recognition provided by the present invention realizes the state detection of the interlocking device to be detected based on the image recognition technology.

[0038] Image recognition technology refers to the technology of using computers to process, analyze and understand images to identify targets and objects of various different patterns. Its main processes are:

[0039] Acquisition of information data: Acquisition of information data is the basis of image recognition. The image features and special data are stored in the computer for subsequent steps.

[0040] Feature extraction and selection: extract the special features of different images, select the features that can distinguish the images, and store the selected features so that the computer can remember them;

[0041] Classifier design and classification decision: Classifier design refers to the use of an effective procedure to develop a recognition rule that can identify images according to a certain rule rather than blindly and chaotically. This recognition rule can highlight similar types of features, resulting in a higher recognition rate in the image recognition process. The image is then evaluated and confirmed by identifying special features.

[0042] Figure 1 The schematic diagram of the structure of the interlocking device detection system based on image recognition provided by the present invention is as follows: Figure 1 As shown, the system includes:

[0043] The data acquisition module 10 is used to determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and to obtain the scheduling feedback image of the interlocking device to be detected;

[0044] The image recognition module 11 detects the state of the interlocking device to be detected according to the scheduling feedback image and the image standard library to determine whether the interlocking device to be detected is in a normal state;

[0045] The image standard library includes images corresponding to various states of the interlocking device to be detected;

[0046] The data acquisition module 10 includes:

[0047] The communication submodule 101 is connected to the interlocking device to be detected and is used to obtain line configuration data and communication interface data;

[0048] The data processing submodule 102 is connected to the communication submodule 101, and is used to read the line configuration data and the communication interface data, and package the line configuration data and the communication interface data according to the package package rule provided by the interlocking device to be detected;

[0049] The data analysis submodule 103 is connected to the data processing submodule 102 and is used to analyze the packaged data to obtain the network IP address, port number and location information;

[0050] The dispatch feedback image acquisition submodule 104 is connected to the data analysis submodule 103 and is used to determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and to obtain the dispatch feedback image of the interlocking device to be detected.

[0051] Specifically, the interlocking device detection system may specifically include a control center server, and the control center server sends a start or stop command to control the start or stop of the interlocking device detection system to detect the state of the interlocking device. For example, when the interlocking device detection system receives a start command sent from the control center server, the data acquisition module 10 in the interlocking device detection system determines the interlocking device to be detected, and obtains the scheduling feedback image of the interlocking device to be detected.

[0052] According to the dispatching feedback image of the interlocking device to be detected obtained as above, combined with the image recognition module 11 in the interlocking device detection system, by analyzing the dispatching feedback image with the images corresponding to the various states of the interlocking device to be detected in the image standard library, the state of the interlocking device to be detected can be determined, and it can be judged whether the interlocking device to be detected is in a normal state.

[0053] For example, if it is determined that the interlocking device to be detected is in a normal state, after a preset time interval, such as 10S to 30S, the data acquisition module 10 obtains the scheduling feedback image of the next interlocking device to be detected, and again combines with the image recognition module 11 to compare and analyze the scheduling feedback image of the interlocking device to be detected with the images corresponding to each state of the interlocking device to be detected in the image standard library, and again determines whether the device to be detected is in a normal state. Repeat the above operation until the state detection of all interlocking devices to be detected in the interlocking concentration area is completed.

[0054] It should be noted that the image standard library mentioned in the present invention is images of the interlocking concentrated area corresponding to various states of the interlocking equipment to be detected, which are taken in advance; in addition, the images in the image standard library can be images taken in advance by maintenance personnel, or can be images taken in advance by smart devices with shooting functions such as cameras, mobile phones, etc., and the present invention does not make specific limitations on this.

[0055] It should be noted that the various states of the interlocking equipment to be tested may specifically include: handling the approach, whether the signal is open, whether the switch is in the positioning state after sending the switch positioning command, switch reversal, switch squeezing, switch four-way opening, pressing the emergency stop button, whether the emergency and recovery stop buttons are in the pressed or restored state, etc.

[0056] Specifically, in the present invention, the data acquisition module 10 is further used to determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected.

[0057] For example, when the interlocking device detection system receives a startup instruction issued by the control center server, the data acquisition module 10 uniquely determines the interlocking device to be detected in the interlocking concentration area based on the IP address and port number of the interlocking device to be detected, and determines the device name and location of the interlocking device to be detected in combination with the obtained location information of the interlocking device to be detected, and obtains the scheduling feedback image of the interlocking device to be detected at the corresponding position to carry out subsequent detection work.

[0058] In the present invention, the dispatching feedback image of the interlocking device to be detected can be obtained by sending a shooting instruction to the dispatching device to control the dispatching device to move to the position of the interlocking device to be detected in time to take pictures, obtain the dispatching feedback image, and send the dispatching feedback image to the data acquisition module to obtain the dispatching feedback image of the interlocking device to be detected.

[0059] It should be noted that the dispatching equipment mentioned in the present invention can specifically be a digital camera, a high-speed camera, an ultra-high-speed camera or other equipment with a shooting function that can complete the static and dynamic image shooting of the interlocking equipment to be inspected.

[0060] It should be noted that the network IP address and port number of the interlocking device to be detected mentioned in the present invention can be the network IP address and port number of the interlocking device to be detected in the interlocking device concentration area that are artificially specified in advance for external communication, and the network IP address and port number of each interlocking device to be detected are unique.

[0061] Further, Figure 2 The structural diagram of the data acquisition module provided by the present invention is as follows: Figure 2 As shown, the data acquisition module 10 may specifically include:

[0062] The communication submodule 101 is connected to the interlocking device to be detected and is used to obtain line configuration data and communication interface data;

[0063] The data processing submodule 102 is connected to the communication submodule, and is used to read the line configuration data and the communication interface data, and to package the line configuration data and the communication interface data according to the packaging rules provided by the interlocking device to be detected;

[0064] The data analysis submodule 103 is connected to the data processing submodule and is used to analyze the packaged data to obtain the network IP address, port number and location information;

[0065] The dispatch feedback image acquisition submodule 104 is connected to the data analysis submodule, and is used to determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and to obtain the dispatch feedback image of the interlocking device to be detected.

[0066] Specifically, the communication submodule 101 can be connected to each interlocking device to be detected by wireless connection, and obtain the line configuration data and communication interface data of each interlocking device to be detected in real time.

[0067] It should be noted that the communication submodule 101 mentioned in the present invention can be compatible with multiple communication protocols at the same time to meet the communication requirements of different rail transit interlocking devices. In addition, the communication submodule 101 provides an interface for communicating with rail transit interlocking devices. When the data communication protocols in the rail transit equipment are inconsistent, the corresponding communication protocol can be selected according to the current needs, which increases the applicability and flexibility of the communication submodule 101.

[0068] It should be noted that the various interlocking devices to be detected in the interlocking device concentration area mentioned in the present invention can be connected to the communication sub-module 101 through a wireless connection method connected to the same local area network or Ethernet, or through other wireless connection methods. The present invention does not make specific limitations on this.

[0069] It should be noted that the line configuration data mentioned in the present invention is the line configuration data of the interlocking devices to be detected corresponding to the various states of each interlocking device to be detected, and may specifically include: location information of each interlocking device to be detected such as link position, signal position, etc., use case data, etc.

[0070] It should be noted that the communication interface data mentioned in the present invention may specifically include: the network IP address and port number used by each interlocking device to be detected to communicate with the outside.

[0071] The data processing submodule 102 can be connected to the communication submodule 101 through the above-mentioned wireless connection method, read the line configuration data and communication interface data sent by the communication submodule 101, and perform packet processing on the line configuration data and the communication interface data according to the packet grouping rules corresponding to each interlocking device to be detected. It should be noted that the packet grouping rules mentioned in the present invention can be determined to adopt TCP packet grouping rules or UDP packet grouping rules according to the communication protocols adopted by each interlocking device to be detected, such as TCP, UDP, etc.

[0072] The data analysis submodule 103 can be connected to the data processing submodule 102 via the above-mentioned wireless connection method, and determine the analysis rules corresponding to the analysis rules of each interlocking device to be detected and the analysis rules according to the above-mentioned analysis rules adopted by each interlocking device to be detected. The data analysis submodule 103 parses the communication interface data after packaging according to the analysis rules to obtain the network IP address and port number of each interlocking device to be detected; and parses the line configuration data after packaging according to the analysis rules to obtain the location information of each interlocking device to be detected.

[0073] The scheduling feedback image acquisition submodule 104 can be connected to the data analysis submodule 103 through the above-mentioned wireless connection method, and determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected according to the above-mentioned data acquisition module 10, and obtain the scheduling feedback image of the interlocking device to be detected based on the above-mentioned data acquisition module 10.

[0074] The interlocking device detection system based on image recognition provided by the present invention acquires the image of the device to be detected through a data acquisition module, and compares the image of the device to be detected with an image standard library in combination with an image recognition module, thereby realizing state detection and analysis of the interlocking device, and by utilizing a communication submodule to exchange data with the interlocking device to be detected, realizing automated detection of the state of the interlocking device to be detected, reducing errors caused by human observation, and improving detection efficiency.

[0075] Furthermore, in one embodiment, the image recognition module 11 includes: an image preprocessing submodule, which is used to perform grayscale processing, binarization processing, enhancement processing and smoothing processing on the scheduling feedback image.

[0076] Specifically, after the dispatch feedback image of the interlocking device to be detected is acquired by the above-mentioned data acquisition module 10, before the dispatch feedback image of the interlocking device to be detected and the image of the image standard library are analyzed by the image recognition module 11, first, the color image of the interlocking device to be detected taken by the dispatching device is grayed and binarized to convert the color image into a gray image; then the gray image is preprocessed to highlight the features and important information of the dispatch feedback image. The preprocessing can specifically include: image enhancement processing and image smoothing processing.

[0077] In real application scenarios, when the control dispatching equipment is used to capture images of interlocking equipment to be detected in the concentrated area of ​​interlocking equipment, the visual effect of the image capture will be poor due to various factors such as the positional relationship of each interlocking equipment to be detected and the shooting accuracy of the dispatching equipment. This requires image enhancement technology to improve the visual effect, such as highlighting certain state characteristics of the interlocking equipment to be detected in the image, extracting characteristic parameters of the interlocking equipment to be detected from the digital image, etc. These are all conducive to the recognition, tracking and understanding of the state information of the interlocking equipment to be detected in the dispatching feedback image, and finally highlighting the part of interest in the image and weakening or removing unnecessary information. Among them, the dispatching feedback image can be enhanced by image rotation.

[0078] The dispatch feedback image may be polluted by noise during the acquisition and transmission process. Common noises include Gaussian noise and salt and pepper noise. Among them, Gaussian noise is mainly generated by the sensor components of the dispatch equipment, and salt and pepper noise is mainly the black and white light and dark point noise generated by image cutting. It is necessary to perform image smoothing on the dispatch feedback image to reduce the noise or distortion on the image and obtain a high-quality image.

[0079] The interlocking device detection system based on image recognition provided by the present invention performs grayscale processing, smoothing processing, etc. on the scheduling feedback image of the interlocking device to be detected through an image preprocessing submodule to ensure that a high-quality and distinctive scheduling feedback image is obtained, thereby improving the accuracy of matching the scheduling feedback image with the image standard library and the images corresponding to the various states of the interlocking device to be detected, thereby improving the detection accuracy of the state information of the interlocking device to be detected.

[0080] Furthermore, in one embodiment, the image recognition module 11 further includes: an image analysis submodule for constructing a similarity comparison algorithm according to the Aforge.NET architecture class library;

[0081] Among them, the similarity comparison algorithm is used to perform comparative analysis based on the image standard library and the scheduling feedback image to determine whether the interlocking device to be detected is in a normal state.

[0082] Specifically, AForge.NET is a C#-based framework designed for developers and researchers in the field of computer vision and artificial intelligence.

[0083] Through the image analysis submodule in the image recognition module 11 and writing a similarity comparison algorithm based on the Aforge.NET architecture class library, the scheduling feedback image of the interlocking device to be detected is compared and analyzed with the images corresponding to the various states of the interlocking device to be detected in the image standard library to determine whether the interlocking device to be detected is in a normal state.

[0084] For example, the image standard library includes images of the start and stop states corresponding to the interlocking device to be detected, such as pressing the emergency stop button. The image of pressing the emergency stop button obtained by the dispatching device shows that the state of pressing the emergency stop button at this time is the stop state. If it is judged that pressing the emergency stop button should be in the stop state, it is determined that pressing the emergency stop button is in a normal state; if it is judged that pressing the emergency stop button should be in the start state, it is determined that pressing the emergency stop button is in an abnormal state.

[0085] The interlocking device detection system based on image recognition provided by the present invention determines whether the interlocking device to be detected is in a normal state by comparing the scheduling feedback image of the state of the device to be detected with the images corresponding to the various states of the interlocking device to be detected in the image standard library, thereby realizing automatic detection of the state of the interlocking device, saving the time of maintenance personnel to go to the on-site detection and improving the detection efficiency.

[0086] Furthermore, in one embodiment, the interlocking device detection system based on image recognition also includes: a logic processing module, connected to the image recognition module 11, for generating a state switching instruction when the interlocking device to be detected is in an abnormal state, and driving the interlocking device to be detected according to the state switching instruction to ensure that the interlocking device to be detected is in a normal state after executing the state switching instruction.

[0087] Specifically, the logic processing module is connected to the image recognition module 11, and uses the image analysis submodule in the image recognition module 11 to compare the scheduling feedback image of the interlocking device to be detected with the image in the image standard library, and finally determine whether the interlocking device to be detected is in a normal state; if it is determined that the interlocking device to be detected is in a normal state, the logic processing module continues to perform state detection on the next interlocking device to be detected; if it is determined that the interlocking device to be detected is in an abnormal state, the logic processing module generates a state switching instruction, and sends the state switching instruction to the controller or control center, and the controller or control center drives the interlocking device to be detected to switch the interlocking device to be detected that was originally in an abnormal state to a normal state according to the state switching instruction.

[0088] For example, if it is determined that pressing the emergency stop button in a stopped state is an abnormal state, the logic processing module generates a state switching instruction, such as a stop-to-start switching instruction, and sends the stop-to-start switching instruction to the controller or control center. The controller or control center completes the switching from the stop state to the start state by pressing the emergency stop button.

[0089] It should be noted that the logic processing module mentioned in the present invention may specifically be a detection case of each interlocking device to be detected. When it is determined that the interlocking device to be detected is in an abnormal state, a state switching instruction is generated through the detection case.

[0090] The interlocking device detection system based on image recognition provided by the present invention determines whether the interlocking device to be detected is in a normal state by comparing the scheduling feedback image of the state of the device to be detected with the images corresponding to the various states of the interlocking device to be detected in the image standard library, thereby realizing automatic detection of the state of the interlocking device, and generating a state switching instruction through a logic processing module to drive the interlocking device to be detected in an abnormal state to change to a normal state according to the state switching instruction, thereby saving the time of maintenance personnel to go to the on-site maintenance and improving the detection efficiency.

[0091] Furthermore, in one embodiment, the interlocking device detection system based on image recognition further includes:

[0092] The display module is connected to the logic processing module and is used to display in real time the image of the interlocking device to be detected after executing the state switching instruction.

[0093] Specifically, the display module is connected to the logic processing module and is used to display the detection process and execution results of the interlocking device detection system; the display content of the display module can specifically include: the image of the interlocking device to be detected obtained by the scheduling device for providing image data to the image recognition module 11, the image of the image standard library, and the image of the interlocking device to be detected obtained again by the scheduling device after the logic processing module executes the state switching instruction.

[0094] The interlocking device detection system based on image recognition provided by the present invention realizes the visual display of the detection process and execution results of the interlocking device detection system by setting a display module, which allows the detection staff to observe the status image of the interlocking device to be detected in real time and intuitively, and helps to realize the refined management of the interlocking device detection system.

[0095] Figure 3 A schematic diagram of the flow of the interlocking device detection method based on image recognition provided by the present invention is shown in FIG. Figure 3 As shown, the method includes:

[0096] S1. Determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected;

[0097] S2, obtaining a dispatch feedback image of the interlocking device to be detected;

[0098] S3, according to the scheduling feedback image and the image standard library, the state of the interlocking device to be detected is detected to determine whether the interlocking device to be detected is in a normal state;

[0099] The image standard library includes images corresponding to various states of the interlocking device to be detected.

[0100] Specifically, the process of determining the interlocking device to be detected in step S1 is consistent with the process of determining the interlocking device to be detected by the above-mentioned data acquisition module 10, and the process of obtaining the scheduling feedback image of the interlocking device to be detected in step S2 is consistent with the process of obtaining the scheduling feedback image by the above-mentioned data acquisition module 10. According to the obtained scheduling feedback image of the interlocking device to be detected, the state of the interlocking device to be detected is determined by analyzing the scheduling feedback image with the images corresponding to each state of the interlocking device to be detected in the image standard library, and it is determined whether the interlocking device to be detected is in a normal state.

[0101] If it is determined that the interlocking device to be detected is in a normal state, the scheduling feedback image of the next interlocking device to be detected is obtained at a preset interval, such as 10S to 30S, and the scheduling feedback image of the interlocking device to be detected is compared and analyzed again with the images corresponding to each state of the interlocking device to be detected in the image standard library, and it is determined again whether the device to be detected is in a normal state. Repeat the above operation until the state detection of all interlocking devices to be detected in the interlocking concentration area is completed.

[0102] It should be noted that the image standard library used in the present invention is consistent with the image standard library used in the above interlocking device detection system. In addition, the various states of the interlocking device to be detected mentioned in the present invention are consistent with the various states of the interlocking device to be detected mentioned in the above interlocking device detection system.

[0103] For example, based on the IP address and port number of the interlocking device to be detected, the interlocking device to be detected in the interlocking concentration area is uniquely determined, and combined with the obtained location information of the device to be detected, the device name and location of the interlocking device to be detected are determined, and the scheduling feedback image of the interlocking device to be detected at the corresponding position is obtained to carry out subsequent detection work.

[0104] It should be noted that the network IP address and port number of the interlocking device to be detected used in the present invention are consistent with the network IP and port number of the interlocking device to be detected used in the above-mentioned interlocking device detection system.

[0105] The interlocking device detection system based on image recognition provided by the present invention realizes status detection and analysis of the interlocking device by acquiring the image of the device to be detected and comparing the image of the device to be detected with an image standard library, completes data interaction with the interlocking device to be detected through the network IP address, port number and location information of the device to be detected, realizes automatic detection of the status of the interlocking device to be detected, reduces errors caused by human observation, and improves detection efficiency.

[0106] Furthermore, in one embodiment, step S3 may specifically include:

[0107] S31. Construct similarity comparison algorithm based on Aforge.NET architecture class library;

[0108] S32: performing comparative analysis on the image standard library and the dispatch feedback image based on a similarity comparison algorithm to determine whether the interlocking device to be detected is in a normal state.

[0109] Specifically, after obtaining the dispatch feedback image of the interlocking device to be detected, before analyzing the dispatch feedback image of the interlocking device to be detected with the image of the image standard library, first, the color image of the interlocking device to be detected photographed by the dispatching device is grayed and binarized to convert the color image into a gray image; then the gray image is preprocessed to highlight the features and important information of the dispatch feedback image. The preprocessing may specifically include: image enhancement processing and image smoothing processing.

[0110] A similarity comparison algorithm was written based on the Aforge.NET architecture class library to compare and analyze the scheduling feedback image of the interlocking device to be detected with the images corresponding to the various states of the interlocking device to be detected in the image standard library to determine whether the interlocking device to be detected is in a normal state.

[0111] For example, the image standard library includes images of the start and stop states corresponding to the interlocking device to be detected, such as pressing the emergency stop button. The image of pressing the emergency stop button obtained by the dispatching device shows that the state of pressing the emergency stop button at this time is the stop state. If it is judged that pressing the emergency stop button should be in the stop state, it is determined that pressing the emergency stop button is in a normal state; if it is judged that pressing the emergency stop button should be in the start state, it is determined that pressing the emergency stop button is in an abnormal state.

[0112] The interlocking device detection system based on image recognition provided by the present invention performs grayscale processing, smoothing processing, etc. on the dispatching feedback image of the interlocking device to be detected to ensure that a high-quality and distinctive dispatching feedback image is obtained, thereby improving the accuracy of matching the dispatching feedback image with the image standard library and the images corresponding to the various states of the interlocking device to be detected, thereby improving the detection accuracy of the state information of the interlocking device to be detected, realizing automatic detection of the state of the interlocking device, saving the time of maintenance personnel to go to the on-site detection, and improving the detection efficiency.

[0113] Figure 4 A schematic diagram of the physical structure of an electronic device provided by the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the following method:

[0114] Determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected;

[0115] Obtain the dispatch feedback image of the interlocking device to be detected;

[0116] According to the dispatch feedback image and the image standard library, the state of the interlocking device to be detected is detected to determine whether the interlocking device to be detected is in a normal state;

[0117] The image standard library includes images corresponding to various states of the interlocking device to be detected.

[0118] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several 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 and other media that can store program codes.

[0119] Furthermore, the present invention discloses a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, and when the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments, for example, including:

[0120] Determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected;

[0121] Obtain the dispatch feedback image of the interlocking device to be detected;

[0122] According to the dispatch feedback image and the image standard library, the state of the interlocking device to be detected is detected to determine whether the interlocking device to be detected is in a normal state;

[0123] The image standard library includes images corresponding to various states of the interlocking device to be detected.

[0124] On the other hand, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the transmission method provided in the above embodiments, for example, including:

[0125] Determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected;

[0126] Obtain the dispatch feedback image of the interlocking device to be detected;

[0127] According to the dispatch feedback image and the image standard library, the state of the interlocking device to be detected is detected to determine whether the interlocking device to be detected is in a normal state;

[0128] The image standard library includes images corresponding to various states of the interlocking device to be detected.

[0129] 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. Those of ordinary skill in the art may understand and implement it without creative work.

[0130] 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, it 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.

[0131] 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. An interlocking device detection system based on image recognition, characterized in that: include: A data acquisition module, used to determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and to obtain a scheduling feedback image of the interlocking device to be detected; An image recognition module detects the state of the interlocking device to be detected according to the scheduling feedback image and the image standard library to determine whether the interlocking device to be detected is in a normal state; The image standard library includes images corresponding to various states of the interlocking device to be detected; the various states at least include whether the signal is open, whether the turnout is in a positioning state after sending a turnout positioning command, and whether the emergency and recovery stop buttons are in a pressed or restored state; The data acquisition module comprises: A port number communication submodule, connected to the interlocking device to be detected, for acquiring line configuration data and communication interface data; a data processing submodule, connected to the communication submodule, for reading the line configuration data and the communication interface data, and packaging the line configuration data and the communication interface data according to a packaging rule provided by the interlocking device to be detected; A data analysis submodule, connected to the data processing submodule, for analyzing the packaged data to obtain the network IP address, port number and location information; A dispatch feedback image acquisition submodule, connected to the data analysis submodule, for determining the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and acquiring the dispatch feedback image of the interlocking device to be detected; Wherein, the image recognition module further includes: an image analysis submodule, which is used to construct a similarity comparison algorithm according to the Aforge.NET architecture class library; the similarity comparison algorithm is used to analyze the scheduling feedback image with the images corresponding to the various states of the interlocking device to be detected in the image standard library, determine the state of the interlocking device to be detected, and determine the state of the interlocking device to be detected; if the determined state of the interlocking device to be detected is the same as the state of the interlocking device to be detected, it is determined that the interlocking device to be detected is in a normal state; Wherein, the system further comprises: A logic processing module is connected to the image recognition module and is used to generate a state switching instruction when the interlocking device to be detected is in an abnormal state, and drive the interlocking device to be detected according to the state switching instruction to ensure that the interlocking device to be detected is in a normal state after executing the state switching instruction.

2. The interlocking device detection system based on image recognition according to claim 1 is characterized in that: The image recognition module includes: an image preprocessing submodule for The scheduling feedback image is subjected to grayscale processing, binarization processing, enhancement processing and smoothing processing.

3. The interlocking device detection system based on image recognition according to claim 2 is characterized in that: Also includes: A display module is connected to the logic processing module and is used to display in real time an image of the interlocking device to be detected after executing the state switching instruction.

4. An interlocking device detection method based on image recognition, characterized in that: include: Determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected; Acquire a dispatch feedback image of the interlocking device to be detected; According to the scheduling feedback image and the image standard library, the state of the interlocking device to be detected is detected to determine whether the interlocking device to be detected is in a normal state; The image standard library includes images corresponding to various states of the interlocking device to be detected; the various states at least include whether the signal is open, whether the turnout is in a positioning state after sending a turnout positioning command, and whether the emergency and recovery stop buttons are in a pressed or restored state; Wherein, determining the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected includes: Obtain line configuration data and communication interface data; Reading the line configuration data and the communication interface data, and packaging the line configuration data and the communication interface data according to a packaging rule provided by the interlocking device to be detected; Parsing the packaged data to obtain the network IP address, port number and location information; Determine the interlocking device to be detected according to the network IP address, port number and location information of the interlocking device to be detected, and obtain the scheduling feedback image of the interlocking device to be detected; The step of detecting the state of the interlocking device to be detected according to the scheduling feedback image and the image standard library to determine whether the interlocking device to be detected is in a normal state includes: Build a similarity comparison algorithm based on the Aforge.NET architecture class library; Based on the similarity comparison algorithm, the image standard library and the scheduling feedback image are compared and analyzed to determine the state of the interlocking device to be detected, and determine the state that the interlocking device to be detected should be in; If the determined state of the interlocking device to be detected is the same as the state that the interlocking device to be detected should be in, then it is determined that the interlocking device to be detected is in a normal state; Wherein, the method further comprises: When the interlocking device to be detected is in an abnormal state, a state switching instruction is generated, and the interlocking device to be detected is driven according to the state switching instruction to ensure that the interlocking device to be detected is in a normal state after executing the state switching instruction.

Images