Foreign matter invasion monitoring method and device, equipment, storage medium and program product

Abstract

The invention relates to the technical field of railway traffic transportation, in particular to a foreign matter invasion monitoring method, device and equipment, a storage medium and a program product, and the method comprises the steps: scanning a tunnel portal through laser radar equipment, and obtaining the real-time distance information of each detection point; obtaining abnormal detection points with differences based on the real-time distance information and the static distance information of each detection point; based on the abnormal detection point, acquiring edge distance data of the foreign matter; based on the edge distance data, obtaining a foreign matter type to which the foreign matter belongs and a risk of the foreign matter; and determining a processing strategy corresponding to the foreign matter based on the foreign matter type and danger. By comparing the real-time distance information and the static distance information of each detection point, an abnormal detection point can be found, so that whether foreign matter invasion exists at the tunnel portal can be accurately judged, the foreign matter invasion can be accurately monitored, a corresponding processing strategy can be automatically judged and selected, and the effective coping capacity under emergency conditions is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of railway transportation technology, and in particular to a foreign object intrusion monitoring method, device, equipment, storage medium and program product. Background Art

[0002] In modern railway systems, tunnel entrances are usually located under mountains, and their safety is of vital importance. Due to the special structure and location of tunnel entrances, foreign objects often intrude, such as falling rocks, accumulation of debris, or invasion of plants and animals. These foreign objects may not only cause train delays, but also pose a direct threat to the moving trains, and in serious cases may even cause train derailment accidents. Therefore, it is particularly important to monitor and deal with the problem of foreign objects intruding at railway tunnel entrances in a timely and accurate manner.

[0003] Traditional methods for monitoring foreign objects at railway tunnel entrances rely on manual inspections or simple video surveillance, which are not only time-consuming and labor-intensive, but also inefficient. Especially in bad weather or at night, their accuracy and reliability are greatly reduced. In addition, traditional methods for monitoring foreign objects are often difficult to respond in real time, and the assessment of the type and danger of foreign objects is not accurate enough, which greatly limits the ability to respond effectively in emergency situations. Summary of the invention

[0004] The present invention provides a foreign object intrusion monitoring method, device, equipment, storage medium and program product to improve the efficiency and accuracy of foreign object intrusion monitoring.

[0005] In a first aspect, the present disclosure provides a foreign body intrusion monitoring method, comprising:

[0006] Scanning the tunnel entrance using a laser radar device to obtain real-time distance information of each detection point at the tunnel entrance;

[0007] Based on the real-time distance information of each of the detection points and the pre-stored static distance information of each of the detection points, obtaining abnormal detection points where the real-time distance information and the static distance information are different;

[0008] Based on the real-time distance information and static distance information of the abnormal detection point, obtaining edge distance data of the foreign object invading the tunnel entrance;

[0009] Based on the edge distance data of the foreign object, obtaining the foreign object type to which the foreign object belongs and the danger of the foreign object;

[0010] Based on the foreign object type to which the foreign object belongs and the dangerousness of the foreign object, a treatment strategy corresponding to the foreign object is determined.

[0011] In some embodiments, based on the real-time distance information and the static distance information of the abnormal detection point, obtaining the edge distance data of the foreign object invading the tunnel entrance includes:

[0012] Acquire real-time distance information and static distance information of adjacent detection points of the abnormal detection point;

[0013] Based on the real-time distance information and static distance information of the abnormal detection point and the adjacent detection point, a spatial analysis algorithm is used to obtain edge distance data of the foreign object invading the tunnel entrance, and the edge distance data represents the distance from the edge of the foreign object to the lidar device.

[0014] In some embodiments, based on the edge distance data of the foreign object, obtaining the foreign object type to which the foreign object belongs and the danger of the foreign object includes:

[0015] Based on the edge distance data of the foreign object, calculating the plane two-dimensional positioning information and body shape parameters of the foreign object, wherein the body shape parameters are used to characterize the length and height of the foreign object;

[0016] Based on the two-dimensional positioning information and shape parameters of the foreign object, image data of the foreign object is acquired;

[0017] Based on the image data of the foreign object, using a convolutional neural network algorithm, obtaining the foreign object type to which the foreign object belongs;

[0018] Based on the body shape parameters and the foreign body type to which the foreign body belongs, the danger of the foreign body is calculated.

[0019] In some embodiments, calculating the two-dimensional positioning information and body shape parameters of the foreign object includes:

[0020] Based on the difference between the real-time distance information and the static distance information of the abnormal detection point, the dimension information of the foreign object is obtained, and the dimension information is used to indicate whether the foreign object is in the same dimension as the track at the tunnel entrance;

[0021] Based on the edge distance data and the dimensional information, the foreign object is mapped into a preset two-dimensional orbital plane map, and the two-dimensional plane positioning information and body parameters of the foreign object are calculated. The static distance information of each detection point is mapped onto the two-dimensional orbital plane map.

[0022] In some embodiments, calculating the danger of the foreign object based on the body shape parameter and the foreign object type to which the foreign object belongs includes:

[0023] Based on the foreign object type to which the foreign object belongs, obtaining the hazard weight corresponding to the foreign object; and based on the body shape parameters, obtaining the maximum value of the length interval and the maximum value of the height interval of the foreign object;

[0024] The hazard weight, the maximum value of the length interval and the maximum value of the height interval are weighted and combined to calculate the hazard of the foreign object.

[0025] In some embodiments, based on the type of foreign matter to which the foreign matter belongs and the dangerousness of the foreign matter, determining a corresponding treatment strategy for the foreign matter includes:

[0026] In the case that the foreign object belongs to a non-living object type and the danger is less than a preset threshold, based on the foreign object, updating the pre-stored static distance information of each of the detection points;

[0027] When the foreign object type to which the foreign object belongs is non-biological and the danger level is greater than or equal to a preset threshold, a foreign object handling reminder is issued to remind manual handling.

[0028] In a second aspect, the present disclosure provides a foreign body intrusion monitoring device, comprising:

[0029] A radar scanning module is used to scan the tunnel entrance using a laser radar device to obtain real-time distance information of each detection point at the tunnel entrance;

[0030] An abnormality detection module, used for acquiring abnormal detection points where the real-time distance information and the static distance information are different based on the real-time distance information of each detection point and the pre-stored static distance information of each detection point;

[0031] A first calculation module is used to obtain edge distance data of a foreign object invading the tunnel entrance based on the real-time distance information and static distance information of the abnormal detection point;

[0032] A second calculation module is used to obtain the foreign object type and the danger of the foreign object based on the edge distance data of the foreign object;

[0033] The strategy confirmation module is used to confirm the processing strategy corresponding to the foreign object based on the foreign object type to which the foreign object belongs and the dangerousness of the foreign object.

[0034] In a third aspect, the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the above aspects.

[0035] In a fourth aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0036] In a fifth aspect, the present disclosure provides a computer program product, including a computer program / instructions, which implements the steps of the method described in the above aspects when the computer program is executed by a processor.

[0037] The present invention provides a foreign object intrusion monitoring method, device, equipment, storage medium and program product. By comparing the real-time distance information and static distance information of each detection point, it is possible to accurately detect abnormal detection points, that is, abnormal distance changes at any position at the tunnel entrance, so as to accurately judge whether there is foreign object intrusion at the tunnel entrance, as well as the type and danger of the foreign object, thereby achieving accurate monitoring of foreign object intrusion, avoiding interference and further performing automatic judgment and selecting corresponding processing strategies, thereby improving the effective response capability in emergency situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0039] Figure 1 A flow chart of a foreign object intrusion monitoring method provided in an embodiment of the present disclosure.

[0040] Figure 2 A flow chart for obtaining the type and danger of foreign matter provided in an embodiment of the present disclosure;

[0041] Figure 3 An architectural diagram of a foreign object intrusion monitoring system provided in an embodiment of the present disclosure.

[0042] Figure 4 is a schematic diagram illustrating the structure of a foreign object intrusion monitoring device according to an embodiment of the present disclosure.

[0043] Figure 5 is a schematic structural diagram illustrating an electronic device according to an embodiment of the present disclosure.

[0044] Figure 6 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0046] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure 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 data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0047] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0048] Embodiment 1

[0049] Figure 1 A flow chart of a foreign body intrusion monitoring method provided by an embodiment of the present disclosure. Figure 1 As shown, including the following S101-S105:

[0050] S101: Scan the tunnel entrance using a laser radar device to obtain real-time distance information of each detection point at the tunnel entrance.

[0051] Among them, the laser radar equipment uses a laser radar scanner, which can emit tens of thousands of laser pulses per second and accurately receive the reflected laser signals. Through these signals, the distance and angle information of each detection point are calculated, and then a three-dimensional spatial image of each part of the railway tunnel entrance is constructed based on the distance of the tunnel entrance relative to each detection point. The laser radar equipment continuously scans the railway tunnel entrance to obtain the current real-time distance information of the tunnel entrance. The real-time distance information reflects the precise distance from the laser radar to each detection point at the tunnel entrance, which is then converted into a real-time distance matrix and updated in real time to reflect the current physical state of the tunnel entrance.

[0052] S102: Based on the real-time distance information of each detection point and the pre-stored static distance information of each detection point, obtain abnormal detection points where the real-time distance information and the static distance information are different.

[0053] Among them, the static distance information of each detection point is obtained by performing a comprehensive scan of the tunnel entrance through the laser radar equipment under normal conditions without any external interference (no foreign objects intruding) at the tunnel entrance, measuring and recording the reflections of all detection points based on the position of the laser radar equipment, and obtaining the static distance information of each detection point based on the reflection distance and the position of the laser radar equipment.

[0054] By comparing real-time distance information with static distance information and monitoring for abnormal detection points, any unexpected distance changes can be detected. These abnormal detection points may indicate the presence of foreign objects such as fallen rocks, accumulated debris or other obstacles.

[0055] Optionally, a static distance matrix can be formed based on the static distance information of each detection point, and a real-time distance matrix can be formed based on the real-time distance information of each detection point. The static distance matrix can be used as a benchmark for future real-time monitoring to identify subsequent distance changes of each detection point. Comparing the two matrices can detect abnormal detection points with distance differences.

[0056] In some embodiments, in order to avoid errors caused by possible slight movements or tilts of the laser radar device, the present embodiment sets a calibration strategy based on overlapping detection points. For example, the detection points that mostly overlap in the static distance matrix and the real-time distance matrix are analyzed, that is, those detection points whose distance differences are extremely small or within the expected error range. Through these overlapping detection points, the configuration parameters of the laser radar device can be adjusted and optimized, including correcting its scanning angle and positioning to ensure the accuracy of the scanning data. During the calibration process, it is also necessary to analyze the non-overlapping detection points to determine whether the distance difference of the non-overlapping detection points is caused by the position offset of the laser radar device. If it is determined that it is caused by the position offset, the position or parameters of the laser radar device are automatically adjusted, and the scan is performed again until it is confirmed that the error is within the expected error range.

[0057] Further, optionally, before generating the static distance matrix, the laser radar device is first initialized and calibrated. This includes ensuring the precise positioning and installation of the laser radar device, and adjusting its measurement parameters to ensure that every part of the tunnel entrance can be accurately captured. The calibration process ensures that the laser radar device can achieve the expected measurement accuracy in actual operation. Determining the scanning range of the laser radar device is an important step in generating a static distance matrix. The scanning range should cover the entire entrance area of ​​the railway tunnel entrance, and set the appropriate scanning angle and frequency according to the width and height of the tunnel entrance. These parameters directly affect the accuracy of the data and the efficiency of subsequent processing. After confirming that there is no foreign body intrusion at the tunnel entrance, the laser radar device performs a comprehensive scan, emitting a laser beam and receiving the reflected laser to calculate the precise distance of each detection point in the tunnel entrance. During the scanning process, the laser radar device continuously records the reflection data of all detection points, which will be used to construct a static distance matrix. After the scan is completed, the collected raw data needs to be processed before it can be converted into useful information. Data processing includes filtering and denoising, data interpolation, and spatial geometric correction, etc. The purpose is to eliminate measurement noise and potential errors and ensure the authenticity and accuracy of the data. The processed data is organized into a static distance matrix according to the spatial position of each detection point.

[0058] S103: Based on the real-time distance information and static distance information of the abnormal detection point, edge distance data of the foreign object invading the tunnel entrance is obtained.

[0059] The edge distance data represents the distance from the edge of the foreign object to the laser radar device. Specifically, the following steps are included:

[0060] The real-time distance information and static distance information of the adjacent detection points of the abnormal detection point are obtained; based on the real-time distance information and static distance information of the abnormal detection point and the adjacent detection points, the edge distance data of the foreign objects invading the tunnel entrance are obtained by using the spatial analysis algorithm.

[0061] Among them, the adjacent detection points of the abnormal detection points are used to calculate and identify those areas with close and continuous distance difference values. These areas indicate the physical boundaries of the foreign objects. After determining these areas, the edge distance data of the foreign objects can be generated, that is, the precise distance from the edge of the foreign object to the LiDAR device. Through in-depth analysis of the edge distance data, not only the specific location of the foreign object can be determined, but also its volume and shape can be inferred.

[0062] S104: Based on the edge distance data of the foreign object, the foreign object type and the dangerousness of the foreign object are obtained.

[0063] Among them, the types of foreign objects include stones, animals, waste, etc., or living things, non-living things, etc. The specific types can be selected according to the actual situation. Figure 2As shown, S104 includes the following steps 1-4:

[0064] Step 1: Based on the edge distance data of the foreign object, calculate the two-dimensional positioning information and shape parameters of the foreign object.

[0065] The body shape parameters are used to characterize the length and height of the foreign body. Step 1 includes:

[0066] Step 1-1: Based on the difference between the real-time distance information and the static distance information of the abnormal detection point, the dimension information of the foreign object is obtained.

[0067] Among them, the dimensional information is used to characterize whether the foreign object is in the same dimension as the track at the tunnel entrance. The possible location of the foreign object is determined by the difference between the real-time distance information and the static distance information of the abnormal detection point. For example, an area with a large difference value indicates that a foreign object may exist here. Through these difference values, the specific dimensions of the foreign object can be further analyzed. According to the spatial distribution and size of the difference value, the dimension of the foreign object is judged, and it is determined whether it is on the track plane. The dimensional information of the foreign object is crucial to the subsequent processing strategy because it directly affects the triggering of the alarm and the implementation of emergency measures.

[0068] Optionally, the difference value of the bottom of the foreign object contour is compared with a preset fitting value interval. If the difference value is within the fitting value interval, it is determined that the foreign object and the orbital plane are of the same dimension; if the difference value is outside the fitting value interval, it is determined that the foreign object and the orbital plane do not belong to the same dimension.

[0069] The static distance information (static distance matrix) of each detection point reflects the distance from the laser radar device to each detection point at the tunnel entrance, where the distance value will gradually increase with the increase of the observation angle (from bottom to top), forming a gradient distance distribution. This distance distribution is caused by the geometric relationship between the scanning angle and distance of the laser radar device. The farther the object is, the higher the position in the static distance matrix is, and the distance value is relatively large. In normal operation, the laser radar device continues to scan in real time, generates real-time distance information (real-time distance matrix) of each detection point, and compares the real-time distance matrix with the static distance matrix to detect any abnormal distance values. Abnormal values ​​mainly refer to the sudden decrease in the distance data of certain detection points in the real-time distance matrix, indicating that foreign objects may have invaded these areas. In dimensional judgment, special attention is paid to the abnormal values ​​at the bottom of the foreign object. If the distance between the bottom abnormal value and the track plane is not much different or close to 0, it indicates that the foreign object may be attached to the track surface. In this case, the bottom distance value of the foreign object will be very close to the distance value of the corresponding position in the static distance matrix, because there is almost no distance difference between the foreign object and the track surface. By setting a suitable fitting value interval, it is possible to further accurately determine whether the foreign object is in the same dimension as the orbital plane. This interval takes into account the measurement errors of the lidar equipment and possible slight altitude changes. If the anomaly value at the bottom of the foreign object is lower than this interval, the foreign object is likely to be on the same horizontal line as the orbital surface; if it is higher than this interval, it indicates that the foreign object may be a suspended object, such as a flying bird or a fluttering leaf.

[0070] Step 1-2: Based on the edge distance data and dimension information, the foreign object is mapped into a preset track plane two-dimensional map, and the plane two-dimensional positioning information and body parameters of the foreign object are calculated.

[0071] Specifically, a two-dimensional track plane map is pre-constructed, on which the static distance information of each detection point is mapped. The two-dimensional track plane map is designed based on the actual geometric layout of the railway track and reflects the plan view of the railway track and its surrounding area. The two-dimensional track plane map will be used as a basic platform for subsequent mapping and analysis, providing a visual reference to help identify and locate the position of foreign objects at the entrance of the railway tunnel. The static distance information of each detection point (i.e., the static distance matrix) is mapped to the pre-constructed two-dimensional track plane map.

[0072] The two-dimensional positioning information of the foreign object is the position of the foreign object on the two-dimensional map of the track plane, and the size parameters are the length and width of the foreign object. The specific dimensions of the foreign object can be further analyzed through the difference between the real-time distance information and the static distance information of the abnormal detection point, and the length and width of the foreign object can be calculated based on the pixel distance difference corresponding to the preset distance gradient.

[0073] Step 2: Based on the two-dimensional positioning information and shape parameters of the foreign object, image data of the foreign object is obtained.

[0074] Specifically, the image capture range can be calculated based on the body shape parameters, and the image acquisition angle can be adjusted based on the plane two-dimensional positioning information, thereby controlling the video acquisition device (such as a camera) to track the foreign object in real time and obtain the image data of the foreign object through the image capture range.

[0075] Step 3: Based on the image data of the foreign object, use the convolutional neural network algorithm to obtain the foreign object type to which the foreign object belongs.

[0076] Among them, the specific calculation process of the convolutional neural network algorithm includes:

[0077] (1) Preprocessing the image data of the foreign body, including image cropping, pixel normalization, and adjusting image brightness and contrast;

[0078] (2) constructing a training data set based on image data labeled with foreign body types;

[0079] (3) training a convolutional neural network model based on the training data set, including determining the prediction error through forward propagation and adjusting the network parameters through back propagation;

[0080] (4) The trained convolutional neural network model outputs the foreign object type to which the foreign object belongs.

[0081] In some embodiments, the primary task of preprocessing is to ensure the quality and consistency of the input data to meet the requirements of the convolutional neural network model. This includes:

[0082] Image cropping: Crop the area of ​​interest from the original image data, usually the location of the detected foreign object, to reduce the interference of background noise and irrelevant information.

[0083] Pixel normalization: Normalize the pixel values ​​of image data to between 0 and 1, which helps the model converge faster and avoids numerical instability during model training.

[0084] Adjust image brightness and contrast: Improve the visual effect of image data and ensure that the features of foreign objects are more obvious in the image, which is convenient for network recognition and learning.

[0085] Subsequently, the preprocessed image data is used to construct a training dataset. Each image data needs to be annotated, and the annotation information includes the type of foreign matter. The preprocessed and annotated image data is input into the convolutional neural network model for forward propagation, and the error between the output of the convolutional neural network model and the actual annotation is calculated. The cross entropy loss function is usually used to measure this error. Back propagation is performed according to the loss function to automatically calculate the gradient of each network parameter and update these parameters to minimize the loss function.

[0086] Step 4: Calculate the dangerousness of the foreign body based on the body size parameters and the foreign body type to which the foreign body belongs.

[0087] Specifically, based on the type of foreign object to which the foreign object belongs, the corresponding hazard weight of the foreign object is obtained; and based on the body parameters, the maximum value of the length interval and the maximum value of the height interval are obtained; the hazard weight, the maximum value of the length interval and the maximum value of the height interval are weighted and combined to calculate the hazard of the foreign object.

[0088] In some embodiments, detailed data about foreign objects can be collected in advance, including the type of foreign object (such as stone, animal, waste, etc.) and its size information in space (such as length and height). The specific way to obtain these data can be through laser scanning equipment or image analysis, which ensures the accuracy and reliability of the data. Then, these data are input into a pre-designed evaluation formula, which calculates its potential danger based on the type of foreign object and its size parameters.

[0089] Each type of foreign object has a preset hazard weight, which can be set based on historical data and expert experience. For example, large solid objects (such as large rocks or metal fragments) may be assigned a higher hazard weight because they can cause direct physical damage to the train; while lighter objects (such as plastic bags or leaves) may affect the train's sensors, but the probability of directly causing significant damage is lower, so their weight is lower. The length and height of foreign objects are also important factors in assessing their hazard. By calculating the maximum value of the foreign object's length interval and the maximum value of the height interval, and then weighted merging, a comprehensive hazard score can be obtained to determine the hazard of the foreign object. The maximum value of the length interval and the height interval are intuitive indicators of the impact of foreign objects on railway operations. Larger foreign objects often mean higher risks. Based on the calculated hazard score, foreign objects can be classified into different safety levels, such as "low risk" and "high risk". Each level corresponds to a set of predefined corresponding measures, such as simple monitoring, regular inspection (low risk), immediate alarm and emergency disposal (high risk), etc. In this way, it can be ensured that appropriate safety measures are taken for each foreign object to minimize potential safety risks.

[0090] S105: Based on the foreign object type and the dangerousness of the foreign object, determine the corresponding treatment strategy for the foreign object.

[0091] Specifically, the processing strategies include:

[0092] (1) When the foreign object type to which the foreign object belongs is non-biological and the danger level is less than a preset threshold, based on the foreign object, the pre-stored static distance information of each detection point is updated.

[0093] (2) When the foreign object type is non-biological and the danger level is greater than or equal to a preset threshold, a foreign object handling reminder is issued to remind manual handling.

[0094] When the danger of the non-biological foreign objects detected is less than the preset threshold, such as light garbage or small stones, these foreign objects need attention but will not immediately threaten railway safety. At this time, the static distance information (static distance matrix) of each detection point will be updated to record the existence of these foreign objects. This will help subsequent monitoring and maintenance decisions, allowing these objects to coexist with the railway until they are cleaned up during the daily maintenance cycle.

[0095] For non-biological foreign objects whose danger level is greater than or equal to the preset threshold, such as large rocks, broken branches or other objects that may hinder the safety of the train, more active measures will be taken. At this time, the information of the foreign objects can be transmitted to the railway management center through the cloud to prompt manual processing. Emergency notifications can also be sent to the on-site maintenance team to ensure that maintenance personnel can arrive at the scene quickly for processing to avoid possible train accidents or other safety issues.

[0096] In some embodiments, the processing strategy further includes:

[0097] (3) If the foreign object is a person, the light is controlled to focus on the person and audio is played to drive the person away.

[0098] (4) If the foreign object is an animal, the light is controlled to focus on the animal’s location and the audio plays the sound of the wild animal to drive it away.

[0099] When a human foreign object is detected at the tunnel entrance, the first priority is to ensure the safety of the person and to drive him away quickly to prevent potential accidents. Specific measures include automatically adjusting the light to focus on the person's position and playing a voice warning. The voice warning can be pre-recorded, such as "Warning: You are in a dangerous area, please leave immediately!" This measure is intended to attract people's attention and prompt them to quickly evacuate the track area to reduce safety risks. For animal foreign objects, the handling method needs to be effective enough to ensure that the animal leaves quickly while avoiding harm to the animal. Specific measures include focusing the light on the animal's position and using the audio playback to use animal frightening sounds, such as the roar of a wild beast, in order to use the animal's instinctive reaction to make it leave the rails. The choice of this sound is based on the principles of animal behavior and is intended to solve the problem quickly and non-violently.

[0100] Embodiment 2

[0101] Based on the above embodiments, this embodiment provides a foreign body intrusion monitoring system. Figure 3 The figure shows the architecture of the foreign body intrusion monitoring system. The foreign body intrusion monitoring system includes field equipment and a monitoring center. Specifically, the field equipment includes:

[0102] LiDAR equipment: used to scan the tunnel entrance of the railway and generate static distance matrix and real-time distance matrix.

[0103] Video acquisition device: such as a camera, used to capture video of the foreign object, such as obtaining image data of the foreign object.

[0104] Front-end control equipment: used to complete the processing, storage and distribution of front-end collected data, generate comprehensive alarm information, control on-site alarm equipment and upload alarm data, and issue alarm instructions.

[0105] On-site alarm equipment: including alarm speakers, alarm lights and wireless array voice alarm devices. The system will complete on-site sound and light alarm warnings when an alarm occurs.

[0106] The monitoring center includes a central server, monitoring terminals, etc., which are used to realize on-site equipment parameter setting, status monitoring, alarm information processing, sending alarm SMS and remote control functions.

[0107] When the laser radar equipment detects an obstacle, the collected data is transmitted to the front-end control equipment in real time. After algorithm calculation and analysis, if it is confirmed that a foreign object has intruded, the monitored foreign object data is stored in the database of the central server in real time, and the alarm data is uploaded to the railway dispatching command center through the client software. At the same time, the camera target tracking mode is triggered, and the video acquisition device moves in real time to track the position of the foreign object, and stores and records the basic properties, pictures, videos and other information of the foreign object.

[0108] When the foreign object disappears, the front-end control device determines that the foreign object disappears, and the disappearance information is transmitted to the client software via the database. The client software issues a cancel warning instruction and the alarm is lifted; at the same time, the camera target tracking mode is released, and the video acquisition device returns to normal video monitoring status.

[0109] The foreign object intrusion monitoring system provided by the embodiment of the present disclosure and the foreign object intrusion monitoring method provided by the above-mentioned embodiment are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0110] Embodiment 3

[0111] Based on the above embodiments, this embodiment provides a foreign body intrusion monitoring device, such as Figure 4 As shown, including:

[0112] The radar scanning module 101 is used to scan the tunnel entrance using a laser radar device to obtain real-time distance information of each detection point of the tunnel entrance;

[0113] The abnormality detection module 102 is used to obtain abnormal detection points where the real-time distance information and the static distance information are different based on the real-time distance information of each detection point and the pre-stored static distance information of each detection point;

[0114] A first calculation module 103 is used to obtain edge distance data of a foreign object invading the tunnel entrance based on the real-time distance information and static distance information of the abnormal detection point;

[0115] A second calculation module 104 is used to obtain the foreign object type and the danger of the foreign object based on the edge distance data of the foreign object;

[0116] The strategy confirmation module 105 is used to confirm the processing strategy corresponding to the foreign object based on the foreign object type to which the foreign object belongs and the danger of the foreign object.

[0117] In one or more embodiments, the first calculation module 103 is used to:

[0118] Acquire real-time distance information and static distance information of adjacent detection points of the abnormal detection point;

[0119] Based on the real-time distance information and static distance information of the abnormal detection point and the adjacent detection point, a spatial analysis algorithm is used to obtain edge distance data of the foreign object invading the tunnel entrance, and the edge distance data represents the distance from the edge of the foreign object to the lidar device.

[0120] In one or more embodiments, the second calculation module 104 is configured to:

[0121] Based on the edge distance data of the foreign object, calculating the plane two-dimensional positioning information and body shape parameters of the foreign object, wherein the body shape parameters are used to characterize the length and height of the foreign object;

[0122] Based on the two-dimensional positioning information and shape parameters of the foreign object, image data of the foreign object is acquired;

[0123] Based on the image data of the foreign object, using a convolutional neural network algorithm, obtaining the foreign object type to which the foreign object belongs;

[0124] Based on the body shape parameters and the foreign body type to which the foreign body belongs, the danger of the foreign body is calculated.

[0125] In one or more embodiments, the second calculation module 104 is further configured to:

[0126] Based on the difference between the real-time distance information and the static distance information of the abnormal detection point, the dimension information of the foreign object is obtained, and the dimension information is used to indicate whether the foreign object is in the same dimension as the track at the tunnel entrance;

[0127] Based on the edge distance data and the dimensional information, the foreign object is mapped into a preset two-dimensional orbital plane map, and the two-dimensional plane positioning information and body parameters of the foreign object are calculated. The static distance information of each detection point is mapped onto the two-dimensional orbital plane map.

[0128] In one or more embodiments, the second calculation module 104 is further configured to:

[0129] Based on the foreign object type to which the foreign object belongs, obtaining the hazard weight corresponding to the foreign object; and based on the body shape parameters, obtaining the maximum value of the length interval and the maximum value of the height interval of the foreign object;

[0130] The hazard weight, the maximum value of the length interval and the maximum value of the height interval are weighted and combined to calculate the hazard of the foreign object.

[0131] In one or more embodiments, the policy confirmation module 105 is used to:

[0132] In the case that the foreign object belongs to a non-living object type and the danger is less than a preset threshold, based on the foreign object, updating the pre-stored static distance information of each of the detection points;

[0133] When the foreign object type to which the foreign object belongs is non-biological and the danger level is greater than or equal to a preset threshold, a foreign object handling reminder is issued to remind manual handling.

[0134] The foreign object intrusion monitoring device provided in the embodiment of the present disclosure and the foreign object intrusion monitoring method provided in the above embodiment are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0135] Embodiment 4

[0136] Based on the above embodiments, this embodiment provides an electronic device to execute the above foreign object intrusion monitoring method, including a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the method described in the above embodiments.

[0137] Please refer to Figure 5 It shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Figure 5As shown, the electronic device 8 includes: a processor 800, a memory 801, a bus 802 and a communication interface 803, and the processor 800, the communication interface 803 and the memory 801 are connected via the bus 802; the memory 801 stores a computer program that can be run on the processor 800, and when the processor 800 runs the computer program, it executes the foreign object intrusion monitoring method provided by any of the aforementioned embodiments of the present disclosure.

[0138] The memory 801 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 803 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0139] The bus 802 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 801 is used to store programs, and the processor 800 executes the programs after receiving execution instructions. The foreign object intrusion monitoring method disclosed in any implementation of the aforementioned embodiment of the present disclosure may be applied to the processor 800, or implemented by the processor 800.

[0140] The processor 800 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 800. The above processor 800 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-made programmable gate array (FPTA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 801, and the processor 800 reads the information in the memory 801 and completes the steps of the above method in combination with its hardware.

[0141] The electronic device provided by the embodiment of the present disclosure and the foreign object intrusion monitoring method provided by the above embodiment are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0142] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0143] In some implementations of this embodiment, a computer program product is provided, including a computer program / instruction, and when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented. Figure 6 The computer program product 600 carries a program code, namely a computer program 601. The instructions included in the computer program 601 can be used to execute the steps of the foreign object intrusion monitoring method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0144] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the method in the above embodiments.

[0145] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof. The computer-readable storage medium may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CDROM, DVDROM, Blu-ray disc, etc.).

[0146] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0147] In addition, the electronic device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0148] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0149] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0150] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0151] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0152] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0153] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0154] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0155] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0156] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A foreign body intrusion monitoring method, characterized in that: include: Scanning the tunnel entrance using a laser radar device to obtain real-time distance information of each detection point at the tunnel entrance; Based on the real-time distance information of each of the detection points and the pre-stored static distance information of each of the detection points, obtaining abnormal detection points where the real-time distance information and the static distance information are different; Based on the real-time distance information and static distance information of the abnormal detection point, obtaining edge distance data of the foreign object invading the tunnel entrance; Based on the edge distance data of the foreign object, obtaining the foreign object type to which the foreign object belongs and the danger of the foreign object; Based on the foreign object type to which the foreign object belongs and the dangerousness of the foreign object, a treatment strategy corresponding to the foreign object is determined.

2. The method according to claim 1, characterized in that Based on the real-time distance information and the static distance information of the abnormal detection point, edge distance data of the foreign object invading the tunnel entrance is obtained, including: Acquire real-time distance information and static distance information of adjacent detection points of the abnormal detection point; Based on the real-time distance information and static distance information of the abnormal detection point and the adjacent detection point, a spatial analysis algorithm is used to obtain edge distance data of the foreign object invading the tunnel entrance, and the edge distance data represents the distance from the edge of the foreign object to the lidar device.

3. The method according to claim 1, characterized in that Based on the edge distance data of the foreign object, the foreign object type and the dangerousness of the foreign object are obtained, including: Based on the edge distance data of the foreign object, calculating the plane two-dimensional positioning information and body shape parameters of the foreign object, wherein the body shape parameters are used to characterize the length and height of the foreign object; Based on the two-dimensional positioning information and shape parameters of the foreign object, image data of the foreign object is acquired; Based on the image data of the foreign object, using a convolutional neural network algorithm, obtaining the foreign object type to which the foreign object belongs; Based on the body shape parameters and the foreign body type to which the foreign body belongs, the danger of the foreign body is calculated.

4. The method according to claim 3, characterized in that Based on the edge distance data, calculating the two-dimensional positioning information and shape parameters of the foreign object, including: Based on the difference between the real-time distance information and the static distance information of the abnormal detection point, the dimension information of the foreign object is obtained, and the dimension information is used to indicate whether the foreign object is in the same dimension as the track at the tunnel entrance; Based on the edge distance data and the dimensional information, the foreign object is mapped into a preset two-dimensional orbital plane map, and the two-dimensional plane positioning information and body parameters of the foreign object are calculated. The static distance information of each detection point is mapped onto the two-dimensional orbital plane map.

5. The method according to claim 3, characterized in that: Calculating the danger of the foreign object based on the body shape parameter and the foreign object type to which the foreign object belongs, including: Based on the foreign object type to which the foreign object belongs, obtaining the hazard weight corresponding to the foreign object; and based on the body shape parameters, obtaining the maximum value of the length interval and the maximum value of the height interval of the foreign object; The hazard weight, the maximum value of the length interval and the maximum value of the height interval are weighted and combined to calculate the hazard of the foreign object.

6. The method according to claim 1, characterized in that Based on the type of foreign matter to which the foreign matter belongs and the dangerousness of the foreign matter, a corresponding treatment strategy for the foreign matter is determined, including: In the case that the foreign object belongs to a non-living object type and the danger is less than a preset threshold, based on the foreign object, updating the pre-stored static distance information of each of the detection points; When the foreign object type to which the foreign object belongs is non-biological and the danger level is greater than or equal to a preset threshold, a foreign object handling reminder is issued to remind manual handling.

7. A foreign body intrusion monitoring device, characterized in that: include: A radar scanning module is used to scan the tunnel entrance using a laser radar device to obtain real-time distance information of each detection point at the tunnel entrance; An abnormality detection module, used for acquiring abnormal detection points where the real-time distance information and the static distance information are different based on the real-time distance information of each detection point and the pre-stored static distance information of each detection point; A first calculation module is used to obtain edge distance data of a foreign object invading the tunnel entrance based on the real-time distance information and static distance information of the abnormal detection point; A second calculation module is used to obtain the foreign object type and the danger of the foreign object based on the edge distance data of the foreign object; The strategy confirmation module is used to confirm the processing strategy corresponding to the foreign object based on the foreign object type to which the foreign object belongs and the dangerousness of the foreign object.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images