Foreign matter invasion monitoring system

Abstract

The utility model provides a foreign matter invasion monitoring system. The foreign matter invasion monitoring system comprises a battery module, a voltage division module, an optical camera, an edge calculation module, a laser radar and a laser radar junction box, the battery module is electrically connected with the voltage dividing module, and the battery module supplies power to the whole system; the voltage division module is electrically connected with the edge calculation module and the laser radar junction box, and outputs rated voltages required by the edge calculation module and the laser radar junction box; the edge calculation module is connected with the optical camera to realize power supply to the optical camera and data transmission between the optical camera and the edge calculation module; the laser radar is connected with the laser radar junction box, so that the battery module supplies power to the laser radar; and the laser radar junction box is connected with the edge calculation module to realize data transmission between the laser radar and the edge calculation module. According to the utility model, by using a laser radar and visual fusion mode, intrusion foreign matters on an engineering construction site and a railway perimeter can be automatically detected, a real-time point cloud data stream and a monitoring video stream in a target monitoring area are formed, and dynamic targets and static targets in the area are segmented and identified in real time by using the edge calculation module, so that the detection accuracy is improved. According to the application scene, early warning information is formed, and the monitoring video stream can be pushed to the server for remote viewing and archiving.

Description

Technical Field

[0001] The utility model relates to the technical field of safety monitoring, in particular to a foreign body intrusion monitoring system, and in particular to a foreign body intrusion monitoring system for engineering construction and road perimeters. Background Art

[0002] During railway construction, the construction site often has a spatial intersection with existing bridges and tunnels. Large machinery (excavators, cranes, etc.) in construction can easily collide and damage existing bridges, tunnels or other facilities. Even if the operators are experienced, such collision damage is difficult to avoid due to factors such as ambient lighting and their own fatigue.

[0003] Although my country's high-speed railway lines are basically in a closed operation state, in some bridge and tunnel sections, it is very easy for people to intrude or other means of intrusion to occur, such as falling rocks at tunnel entrances near mountains and landslides in dangerous sections, which seriously endanger the safety of railway operations.

[0004] Accidents are frequent in my country's highway traffic, often causing great losses to people's lives and property. In some accident-prone sections, such as urban road intersections, mountain road turning sections, rural road village intersections, etc., traffic accidents are very likely to occur due to the driver's visual blind spots. Utility Model Content

[0005] In order to solve the problems in the background technology, the purpose of the utility model is to provide a foreign body intrusion monitoring system to realize all-weather foreign body intrusion monitoring and to realize accurate identification, tracking and early warning of the types of intruding foreign bodies.

[0006] The utility model provides a foreign body intrusion monitoring system, including a battery module, a voltage divider module, an optical camera, an edge computing module, a laser radar and a laser radar junction box;

[0007] The battery module is electrically connected to the voltage divider module, and the battery module supplies power to the entire system;

[0008] The voltage divider module is electrically connected to the edge computing module and the lidar junction box, and the voltage divider module outputs the rated voltage required by each.

[0009] The edge computing module is connected to the optical camera to realize power supply to the optical camera and data transmission between the two;

[0010] The laser radar is connected to the laser radar junction box to realize the power supply of the laser radar by the battery module; the laser radar junction box is connected to the edge computing module to realize data transmission between the laser radar and the edge computing module.

[0011] In a specific implementation, the number of the optical cameras is several.

[0012] In a specific implementation, the foreign body intrusion monitoring system further includes a fill light module, which is electrically connected to the voltage divider module to ensure the video image quality and coverage of the optical camera, thereby enhancing the reliability of the system.

[0013] In a specific implementation, the battery module is connected to the voltage dividing module via a cable.

[0014] In a specific implementation, the edge computing module is connected to the optical camera via a USB data cable.

[0015] In a specific embodiment, the laser radar is connected to one side of the laser radar junction box, and the other side of the laser radar junction box separates a power cable and a network cable. The power cable is connected to a voltage divider module to realize the power supply of the laser radar by the battery module, and the network cable is connected to the network port of the edge computing module to realize data transmission between the laser radar and the edge computing module.

[0016] In a specific implementation, the optical camera is used to receive video image information of the target area and output video image data. The use of the optical camera can intuitively indicate the type of monitored, identified and early-warning targets, thereby facilitating on-site use.

[0017] In a specific implementation, the laser radar generates a nearly circular illumination surface with a wavelength of 950nm, which is used to obtain three-dimensional distance information of the target area and output three-dimensional point cloud data. The use of laser radar can obtain accurate distance information of the monitoring target area in real time to ensure the accuracy of monitoring, identification and early warning results. At the same time, the laser radar can work all day long, which improves the reliability and practicality of the system.

[0018] In a specific embodiment, the edge computing module includes a data preprocessing unit, a target recognition and tracking unit, a coordinate system alignment unit, a fusion determination unit, a remote communication unit, and a display unit;

[0019] The data preprocessing unit is used to receive three-dimensional point cloud data and video image data;

[0020] The target recognition and tracking unit uses point cloud segmentation, point cloud target recognition and tracking algorithms to output point cloud target recognition and tracking results; the target recognition and tracking unit uses an intelligent recognition algorithm to output video image target recognition and tracking results;

[0021] The coordinate system alignment unit uses the space conversion relationship matrix between the camera coordinate system and the laser radar coordinate system that has been calibrated in advance to convert the point cloud target recognition and tracking results and the video image target recognition and tracking results into the same coordinate system for representation; the point cloud target recognition and tracking results use the laser radar as the reference coordinate system; the video image target recognition and tracking results use the camera as the reference coordinate system;

[0022] The fusion determination unit receives the point cloud target recognition and tracking results and the image video target recognition and tracking results, determines whether the target area is in a state of foreign body invasion, and uploads the determination result to the remote server through the remote communication unit;

[0023] The display unit is used to fuse the real-time discrimination results of the discrimination unit.

[0024] Beneficial effects of this application:

[0025] The utility model uses laser radar and vision fusion to automatically detect intruding foreign objects at construction sites and railway perimeters, form real-time point cloud data and monitoring video streams in the target monitoring area, and use the edge computing module to segment and identify dynamic and static targets in the area in real time. According to the application scenario, early warning information is generated, and the monitoring video stream can be pushed to the server for remote viewing and archiving.

[0026] The utility model provides a foreign body intrusion monitoring system, which is based on an edge computing module and includes a data preprocessing unit, a target recognition and tracking unit, a coordinate system alignment unit, a fusion judgment unit, a remote communication unit and a display unit, and finally gives corresponding early warning information. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the utility model, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the utility model and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A schematic structural diagram of a foreign body intrusion monitoring system of the utility model is shown;

[0029] Figure 2 The working principle diagram of a foreign body intrusion monitoring system of the utility model is shown;

[0030] Figure 3 A schematic diagram of the railway perimeter deployment of a foreign object intrusion monitoring system is shown;

[0031] Figure 4The target recognition and tracking result diagram is shown;

[0032] Figure 5 The target recognition and tracking result diagram after the coordinate system is aligned is shown;

[0033] Description of main component symbols:

[0034] 1. Battery module; 2. Voltage divider module; 3. Optical camera; 4. Edge computing module; 401. Display unit; 5. LiDAR; 6. LiDAR junction box; 7. Fill light module. DETAILED DESCRIPTION

[0035] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0036] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0037] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present utility model, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0038] In the present invention, unless otherwise clearly specified and limited, the terms "install", "connect", "connect", "fix" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0039] In the present utility model, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0040] Embodiment 1

[0041] See also Figure 1 to Figure 2 A foreign object intrusion monitoring system includes a battery module 1, a voltage divider module 2, an optical camera 3, an edge computing module 4, a laser radar 5, a laser radar junction box 6 and a fill light module 7.

[0042] The battery module 1 is arranged at the bottom of the entire system, and the laser radar junction box 6 is arranged above the battery module 1; the optical camera 3 and the laser radar 5 are located above the laser radar junction box 6, wherein the laser radar 5 is arranged on the right side of the optical camera 3; the fill light module 7 is arranged on the left side of the battery module 1, and its height is consistent with that of the battery module 1; the voltage divider module 2 is arranged behind the fill light module 7, and its height is consistent with that of the fill light module 7; the edge computing module 4 is located behind the four components of the battery module 1, the laser radar junction box 6, the optical camera 3 and the laser radar 5, and the edge computing module 4 is arranged above the voltage divider module 2 and the fill light module 7.

[0043] The battery module 1 is connected to the voltage divider module 2 via a cable, and the battery module provides power for the entire system.

[0044] The voltage divider module 2 is electrically connected to the edge computing module 4 and the lidar junction box 6, and the voltage divider module 2 outputs the rated voltage required by each.

[0045] The edge computing module 4 is connected to the optical camera 3 via a USB data cable to realize power supply to the optical camera and data transmission between the two.

[0046] The laser radar 5 is connected to one side of the laser radar junction box 6, and the other side of the laser radar junction box separates the power line and the network cable. The power line is connected to the voltage divider module 2 to realize the power supply of the laser radar by the battery module. The network cable is connected to the network port of the edge computing module to realize data transmission between the laser radar and the edge computing module.

[0047] Specifically, the number of optical cameras 3 is several, and the foreign body intrusion monitoring system further includes a fill light module 7, which is electrically connected to the voltage divider module 2 to ensure the video image quality and coverage of the optical camera, thereby enhancing the reliability of the system.

[0048] Specifically, the optical camera 3 is used to receive video image information of the target area and output video image data. The use of an optical camera can intuitively indicate the type of monitoring, identification and early warning targets, thereby facilitating on-site use.

[0049] Specifically, the laser radar 5 generates a nearly circular illumination surface with a wavelength of 950nm, which is used to obtain three-dimensional distance information of the target area and output three-dimensional point cloud data. The use of laser radar can obtain accurate distance information of the monitoring target area in real time to ensure the accuracy of monitoring, identification and early warning results. At the same time, the laser radar can work all day long, which improves the reliability and practicality of the system.

[0050] Specifically, the edge computing module 4 includes a data preprocessing unit, a target recognition and tracking unit, a coordinate system alignment unit, a fusion determination unit, a remote communication unit and a display unit 401;

[0051] The data preprocessing unit is used to receive three-dimensional point cloud data and video image data;

[0052] The target recognition and tracking unit uses point cloud segmentation, point cloud target recognition and tracking algorithms to output point cloud target recognition and tracking results; the target recognition and tracking unit uses intelligent recognition algorithms to output video image target recognition and tracking results;

[0053] The coordinate system alignment unit uses the space conversion relationship matrix between the camera coordinate system and the laser radar coordinate system that has been calibrated in advance to convert the point cloud target recognition and tracking results and the video image target recognition and tracking results into the same coordinate system for representation; the point cloud target recognition and tracking results use the laser radar as the reference coordinate system; the video image target recognition and tracking results use the camera as the reference coordinate system;

[0054] The fusion discrimination unit receives the point cloud target recognition and tracking results, the image video target recognition and tracking results, determines whether the target area is in a state of foreign body invasion, and uploads the discrimination results to the remote server through the remote communication unit;

[0055] The display unit 401 is used to fuse the real-time discrimination results of the discrimination unit.

[0056] The schematic diagram of the whole system at work is as follows: Figure 2 shown. Figure 2 In the diagram, the arrows with numbers indicate the direction of data or current transmission. First, their meanings are explained:

[0057] 1 indicates that the power module supplies power to the laser radar and optical camera respectively;

[0058] 2 indicates that the battery module supplies power to the edge computing module;

[0059] 3 and 4 represent the point cloud data output by the laser radar and the video image data output by the optical camera, respectively;

[0060] 5 and 6 respectively represent the laser radar data and video image data output by the data preprocessing unit;

[0061] 7 and 8 represent the recognition and tracking results output by the target recognition and tracking units, respectively, including the number, location and category of targets;

[0062] 9 and 10 respectively represent the point cloud data and video image data corresponding to each target output by the coordinate system alignment unit after the coordinate system alignment is performed;

[0063] 11 represents the discrimination result output by the fusion discrimination unit, which is transmitted to the display unit and the remote communication unit respectively;

[0064] 12 represents the coded information output by the remote display unit: including the discrimination result and the target recognition and tracking result.

[0065] The working process of the utility model is:

[0066] (1) The laser radar and optical camera detect the target area and output the above 3 and 4;

[0067] (2) The data preprocessing unit processes 3 and 4 respectively. For 3, the data preprocessing unit mainly uses point cloud denoising technology to remove discrete point noise of the point cloud, uses point cloud segmentation technology to remove static background, uses point cloud clustering technology to obtain clustering results, and outputs 5. For 4, the data preprocessing unit mainly uses image denoising and defogging technology to remove image noise, uses image dedistortion and image stitching technology to obtain a distortion-free image within the coverage area, and outputs 6;

[0068] (3) The coordinate system alignment unit uses the previously obtained coordinate system transformation relationship matrix between the laser radar and the camera to perform spatial transformation on 5 and 6, and obtains the transformed laser radar point cloud 7 and image 8 respectively;

[0069] (4) The target recognition and tracking unit processes 7 and 8 respectively. For 7, the point cloud target recognition technology is used to compare the clustering results with the database, identify the target type corresponding to each category in the cluster, and use the target tracking technology to track each type of target, output 9; for 8, the image target recognition and tracking technology is used to classify, identify and track the target, output 10;

[0070] (5) The fusion discrimination unit uses a scene-based fusion discrimination algorithm to perform a comprehensive discrimination on 9 and 10, and outputs a discrimination result 11;

[0071] (6) The display unit can display the discrimination result;

[0072] (7) The remote communication unit encodes 9, 10, and 11, transmits the encoded information to the remote server via a wireless network, and outputs 12;

[0073] (8) The remote server decodes 12 and displays the identification results, real-time target recognition and tracking, and warning results for reference by the staff.

[0074] The circuit diagrams and algorithms involved in the utility model are all conventional technologies in the field. The protection object of the utility model is limited to hardware and does not involve related circuit diagrams and algorithms.

[0075] Embodiment 2

[0076] See also Figures 3 to 5 Taking the railway perimeter foreign object intrusion monitoring as an example, the specific deployment scenario of the system, the conditions required for the normal operation of the system, and the specific operation steps are explained.

[0077] The system is deployed at a certain section of the railway perimeter that needs to be monitored. The specific deployment diagram is as follows: Figure 3 The upper left corner of the picture shows the deployed monitoring system. The camera and lidar illumination area is the oval gray area. The main monitoring intrusion target is the person who enters the railway perimeter without permission.

[0078] For the normal operation of the system, it is first necessary to collect the background data of the system within the railway perimeter monitoring range, that is, the image video data and point cloud data without the intrusion of irrelevant personnel, so as to pre-process the data by the data pre-processing unit of the system.

[0079] Then, the target tracking and recognition unit obtains the result of human target recognition and tracking. Figure 4 shown.

[0080] For image data, the results of single human target recognition and tracking are expressed as a two-dimensional bounding box and a two-dimensional tracking path in the image, and its position in the image can be expressed in the form of two-dimensional coordinates u, v. For point cloud data, the results of single human target recognition and tracking are expressed as a three-dimensional bounding box and a three-dimensional tracking path in the point cloud, and its position in the point cloud can be expressed in the form of three-dimensional coordinates x, y, z. Among them, the bounding box reflects the position of the target in the image or point cloud, and the tracking path reflects the movement of the target.

[0081] Next, the coordinate system alignment unit aligns the bounding box and path of the point cloud recognition and tracking results with the image tracking results, and outputs the three-dimensional bounding box and three-dimensional tracking path marked in the image data, which are represented by the aligned three-dimensional coordinate points X, Y, and Z, as shown in Figure 5 shown.

[0082] Afterwards, the fusion judgment unit judges the tracking result based on the database, determines whether the current human target has entered the monitoring area in the railway perimeter after permission, and gives whether it is necessary to output warning information at present.

[0083] The display unit can display Figure 5 The remote communication unit will also transmit the display content of the display unit to the remote server in real time for the staff to view.

[0084] Although the target recognition and tracking method in this example is mainly for human targets, the system can be easily extended to the recognition and tracking of other dynamic targets. In addition, this project solution combines video target recognition, which should be able to further improve the target recognition accuracy and effectively avoid the misrecognition phenomenon of pure point cloud data.

[0085] The utility model installs an intrusion monitoring system on existing facilities or large-scale machinery, utilizes the detection information output by vision, radar and other equipment, effectively identifies obstacles through edge computing, and establishes a collision warning prompt system, which can effectively avoid collision accidents during construction; through vision (visible light, infrared), radar (lidar, millimeter wave radar) and other technologies, an intrusion monitoring system for key areas is established, which can detect the type of intrusion target in time when there is foreign body intrusion, and can take corresponding measures to ensure the safe and orderly operation of the railway system, which is very necessary.

[0086] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the utility model. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0087] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A foreign body intrusion monitoring system, characterized in that: Includes battery module, voltage divider module, optical camera, edge computing module, LiDAR and LiDAR junction box; The battery module is electrically connected to the voltage divider module, and the battery module supplies power to the entire system; The voltage divider module is electrically connected to the edge computing module and the lidar junction box, and the voltage divider module outputs the rated voltage required by each. The edge computing module is connected to the optical camera to realize power supply to the optical camera and data transmission between the two; The laser radar is connected to the laser radar junction box to realize the power supply of the laser radar by the battery module; the laser radar junction box is connected to the edge computing module to realize data transmission between the laser radar and the edge computing module.

2. A foreign body intrusion monitoring system according to claim 1, characterized in that: The optical cameras are arranged in a plurality of numbers.

3. A foreign body intrusion monitoring system according to claim 2, characterized in that: The foreign body intrusion monitoring system further includes a fill light module, which is electrically connected to the voltage divider module.

4. A foreign body intrusion monitoring system according to claim 1, characterized in that: The battery module is connected to the voltage dividing module via a cable.

5. The foreign body intrusion monitoring system according to claim 1, characterized in that: The edge computing module is connected to the optical camera via a USB data cable.

6. A foreign body intrusion monitoring system according to claim 1, characterized in that: The laser radar is connected to one side of the laser radar junction box, and the other side of the laser radar junction box separates a power cable and a network cable. The power cable is connected to the voltage divider module to realize the battery module to power the laser radar. The network cable is connected to the network port of the edge computing module to realize data transmission between the laser radar and the edge computing module.

Images