Intrusion monitoring method and device based on laser radar and electronic equipment

Abstract

The invention discloses an intrusion monitoring method and device based on a laser radar, and electronic equipment, and the method comprises the steps: collecting the initial specified number of frames of laser radar data in real time, and building a scene background; calculating a calculation background converted into the laser radar; fusing a scene background with the calculation background to generate an intrusion detection boundary background; calculating an intrusion saliency coefficient of an intrusion detection boundary background; performing preprocessing, angle alignment and differential processing on the real-time collected laser radar data to obtain differentiated data; performing binarization processing on the projection value to obtain a set of all possible intrusion points; performing connected domain analysis, and counting possible candidate intrusion point sets to obtain a connected domain set; and obtaining the largest connected domain in the connected domain set, counting the number of effective points in the connected domain, and judging whether intrusion occurs or not according to the number of effective points. Intrusion events caused by timeliness and blind areas due to the fact that positions with high safety risks depend on manual inspection or visual inspection are solved.

Description

Technical Field

[0001] The present application relates to the field of intrusion monitoring technology, and in particular to an intrusion monitoring method, device and electronic equipment based on laser radar. Background Art

[0002] Intrusion detection is the process of detecting and identifying unauthorized entry into a specific area through technical means, and taking appropriate measures when an intrusion is detected. This monitoring technology is widely used in the security field to protect critical areas from unauthorized access.

[0003] Traditional water conservancy intrusion monitoring relies on manual inspections or visual methods at high-risk locations such as sluice pump stations, reservoir entrances, discharge points, and dangerous waters. This has blind spots in complex terrain, at night, or in bad weather, making it easy for incidents to be missed and unable to be monitored in real time 24 hours a day. This can lead to unknowing intrusions, serious consequences, and even life-threatening situations. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide an intrusion monitoring method, device and electronic equipment based on lidar to solve the technical problems existing in the related technology such as the timeliness and blind spots caused by manual inspection or visual inspection at locations with high security risks, which in turn affect the life safety of people.

[0005] According to a first aspect of an embodiment of the present application, a laser radar-based intrusion monitoring method is provided, comprising: Collect the initial specified number of frames of lidar data in real time to establish the scene background; Set the intrusion monitoring angle range, intrusion boundary distance and boundary limit distance, and convert them into the calculation background of the laser radar through mathematical calculation; Fusing the scene background with the calculation background to generate an intrusion detection boundary background; Calculating the projection of the normal vectors of all points of the intrusion detection boundary background as the coefficient of the intrusion significance; Preprocessing the real-time collected laser radar data, aligning the preprocessed data with the intrusion detection boundary background, and then performing differential processing on the preprocessed data with the intrusion detection boundary background to obtain differential data; Calculating the projection value of the differential data on the normal vector using the coefficient, and binarizing the projection value to obtain a set of all possible intrusion points; performing noise removal on the set of all possible intrusion points; Perform connected domain analysis on the possible intrusion points after noise removal, count the possible candidate intrusion point sets, and obtain the connected domain set; The largest connected domain in the connected domain set is obtained, and the number of valid points in the connected domain is counted. If the number of valid points is greater than the intrusion point threshold, it indicates intrusion; otherwise, it indicates no intrusion.

[0006] According to a second aspect of an embodiment of the present application, there is provided a laser radar-based intrusion monitoring device, comprising: The scene background establishment module is used to collect the initial specified number of frames of lidar data in real time to establish the scene background; The calculation background establishment module is used to set the angle range of intrusion monitoring, the boundary distance of intrusion and the limit distance of the boundary, and convert it into the calculation background of the laser radar through mathematical calculation; A detection boundary generation module, configured to fuse the scene background with the calculation background to generate an intrusion detection boundary background; A first calculation module is used to calculate the projection of the normal vectors of all points of the intrusion detection boundary background as the coefficient of the intrusion significance; A second calculation module is used to preprocess the real-time collected laser radar data, align the angle of the preprocessed data with the intrusion detection boundary background, and then perform differential processing on the preprocessed data with the intrusion detection boundary background to obtain differential data; a third calculation module, configured to calculate a projection value of the differential data on a normal vector using the coefficient, and perform binarization processing on the projection value to obtain a set of all possible intrusion points; A noise removal module, configured to remove noise from the set of all possible intrusion points; The connected domain analysis module is used to perform connected domain analysis on the possible intrusion points after noise removal, count the possible candidate intrusion point sets, and obtain the connected domain set; The intrusion judgment module is used to obtain the largest connected domain in the connected domain set and count the valid points in the connected domain. If the valid points are greater than the intrusion point threshold, it indicates intrusion; otherwise, it indicates no intrusion.

[0007] According to a third aspect of the embodiments of the present application, there is provided an electronic device, including: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect.

[0008] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0009] The technical solutions provided by the embodiments of the present application may have the following beneficial effects: It can be seen from the above embodiments that the present application establishes a scene background, and derives a calculation background based on the angle range of intrusion monitoring, the boundary distance of the intrusion and the limit distance of the boundary, and fuses the scene background and the calculation background to generate an intrusion detection background. By performing a series of processing such as preprocessing, differential processing, binarization processing and connected domain analysis on the real-time collected lidar data, the status of whether an intrusion has occurred is finally obtained, which overcomes the technical problems of timeliness and intrusion incidents caused by blind spots brought about by traditional monitoring relying on manual inspections or visual inspections, thereby achieving the effect of real-time detection and a large detection range.

[0010] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0012] Figure 1 The figure is a flowchart of a laser radar-based intrusion monitoring method according to an exemplary embodiment.

[0013] Figure 2 The figure is a schematic diagram showing a calculation process for an intrusion detection angle in the horizontal direction greater than or equal to 180° according to an exemplary embodiment.

[0014] Figure 3 The figure is a schematic diagram showing a calculation process for an intrusion detection angle less than 180° in the horizontal direction according to an exemplary embodiment.

[0015] Figure 4 The figure is a schematic diagram of a radial distance calculation process of a laser radar according to an exemplary embodiment.

[0016] Figure 5 The figure is a schematic structural diagram of an intrusion monitoring device based on a laser radar according to an exemplary embodiment.

[0017] Figure 6 The figure is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0018] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different figures represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of the present application.

[0019] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a," "the," and "the" used in this application are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0020] It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0021] Figure 1 FIG. 1 is a flow chart of an intrusion monitoring method based on a laser radar according to an exemplary embodiment. Figure 1 As shown, the method may include the following steps: S1: Collect the initial specified number of frames of lidar data in real time to establish the scene background; Specifically, the specified frame lidar data is continuously collected, and the points at each angle in the horizontal direction of the lidar beam with different vertical angles are processed in turn. If the distance of the point at the angle is greater than the distance threshold, the distance of the point at the angle is accumulated, and the number of valid points of the point at the angle is added by 1; otherwise, the point is discarded, and the distance and valid point number of the point at the angle are not accumulated; after the specified frame lidar data processing is completed, the total distance of the points at each angle is divided by the valid point number of the points at each angle to obtain the average distance of the points at each angle, thereby establishing the scene background.

[0022] The main purpose of this step is to establish the background of the scene scanned by the LiDAR. Multiple frames of data are continuously collected, processed, and averaged to eliminate errors, making the established scene background more accurate. Generally, the refresh rate of a LiDAR is 10 Hz, meaning it scans 10 times per second. The number of frames continuously collected here can be consistent with the LiDAR refresh rate; 10 frames is sufficient. During scanning, the LiDAR may not see any objects, meaning they are infinitely far away, resulting in no distance measurement. In this case, the distance value is 0. Furthermore, the LiDAR may be damaged or obstructed, such as by a cover, causing the measured distance to be infinitely close. Therefore, a distance threshold is set. This threshold can be determined based on the actual site conditions. Considering the possibility of intrusion from the side, the distance threshold is preferably 0.1-0.5 meters.

[0023] S2: Set the intrusion monitoring angle range, intrusion boundary distance, and boundary limit distance, and convert them into the calculation background of the laser radar through mathematical calculation; this step includes the following sub-steps: S21: Set the angle range of intrusion monitoring, the boundary distance of intrusion and the limit distance of the boundary; The main purpose of this step is to provide data basis for the subsequent calculation of the horizontal distance by the lidar.

[0024] S22: Starting from the starting angle of intrusion monitoring, scan progressively according to the horizontal angle resolution. Combining the limit distance of the laser radar boundary and the intrusion boundary distance of the laser radar, the horizontal projection distance of the laser radar radial distance is obtained according to the trigonometric function theorem; Specifically, Figure 2 The figure shows the calculation process for intrusion detection angles greater than or equal to 180° in the horizontal direction. Figure 3 The figure shows the calculation process of the intrusion detection angle in the horizontal direction less than 180°, where Figure 2 、 Figure 3 1 represents the boundary distance limit, and data outside the boundary is not processed; 2 represents the intrusion boundary distance, within the boundary indicates intrusion, and outside the boundary indicates no intrusion; 3 represents the starting and ending angle ranges of intrusion monitoring; 4 is used to split the calculation range, forming two areas based on the angle with the boundary. The small angle area is constrained by the boundary limit distance, and the large angle area is constrained by the intrusion boundary distance; Figure 2 5, 6, 10 and Figure 35 and 6 represent the horizontal projection of the radial distance of the laser radar during the laser radar scanning process. The calculation is performed in units of resolution, with each process being illustrated in the example. 7 represents the angle relative to the starting angle of intrusion detection during the scanning process; 8 represents the angle relative to the ending angle of intrusion detection during the scanning process; and 9 represents the angular range of intrusion monitoring. Starting from the starting angle of intrusion monitoring, the distances 5, 6, and 10 are calculated in sequence according to the horizontal angle resolution. If the angular range of intrusion monitoring is greater than 180°, the calculation is performed in three steps; if the angular range is less than 180°, the calculation is performed in two steps. The horizontal angle is calculated by gradually increasing the resolution based on the angular range of intrusion monitoring. Combining the distance from the laser radar to the boundary limit line and the distance from the laser radar to the intrusion boundary line, the lengths 5, 6, or 10, i.e., the horizontal projection of the radial distance of the laser radar, can be calculated using trigonometric functions.

[0025] S23: The vertical angle of each beam is obtained by gradually increasing the vertical beam resolution according to the angle of the starting beam. The radial distance of the laser radar, i.e., the distance between the laser radar and the target object, is calculated based on trigonometric functions in combination with the horizontal projection distance of the radial distance of the laser radar. Specifically, if Figure 4 The figure shows a schematic diagram of the radial distance calculation process of the laser radar, where 1 represents the horizontal projection distance of the laser radar's radial distance, 2 represents the angle between the current beam and the horizontal direction, and 3 represents the radial distance of the laser radar. The vertical angle is obtained by gradually increasing the vertical beam resolution according to the angle of the starting beam. Combined with the horizontal projection distance of the laser radar's radial distance, the radial distance of the laser radar can be calculated according to trigonometric functions.

[0026] S24: Starting from the first line beam, repeat S22-S23 to obtain the radial distance of the line beams in different vertical directions of the laser radar at each angle in the horizontal direction from the laser radar; The main purpose of this step is to calculate the radial distance of the laser radar at each angle in the horizontal direction of the laser radar's beam in different vertical directions.

[0027] S25: Calculate the angle corresponding to the laser radar data based on the vertical beam resolution and the horizontal angle resolution. The position of each angle can be mapped to a two-dimensional array. The horizontal coordinate of the two-dimensional array is the index of the vertical beam resolution, and the vertical coordinate is the index of the horizontal angle resolution. Assign the radial distance of the laser radar to the position of the two-dimensional array corresponding to the laser radar angle, so as to obtain the calculation background of the laser radar.

[0028] Specifically, for the convenience of calculation, the angle corresponding to the lidar data can be calculated based on the vertical beam resolution and the horizontal angle resolution. The position of each angle can be mapped to a two-dimensional array. The horizontal coordinate of the two-dimensional array is the index of the vertical beam resolution, and the vertical coordinate is the index of the horizontal angle resolution. The radial distance of the lidar is assigned to the position of the two-dimensional array corresponding to the lidar angle, thereby obtaining the calculation background of the lidar.

[0029] The main purpose of this step is to obtain the calculation background and provide a data basis for the subsequent generation of intrusion detection boundary background.

[0030] S3: Fusing the scene background with the calculation background to generate an intrusion detection boundary background; Specifically, the distance between each corresponding point of the scene background and the calculated background is compared. If the distance of the scene background is greater than the distance of the calculated background, the distance of the corresponding point of the intrusion detection boundary background is set to the distance of the corresponding point of the calculated background; otherwise, if the distance of the scene background is 0, the distance of the corresponding point of the intrusion detection boundary background is set to the distance of the corresponding point of the calculated background; otherwise, if the distance of the scene background is not greater than the distance of the calculated background, the distance of the corresponding point of the intrusion detection boundary background is set to the distance of the corresponding point of the scene background, and the generation of the intrusion detection boundary background is completed.

[0031] The main purpose of this step is to generate an intrusion detection boundary background. The scene background is the actual background, and the calculated background is calculated based on the angle range of the intrusion monitoring, the boundary distance of the intrusion, and the limit distance of the boundary, which is equivalent to a virtual background. Since there may be other objects in the background of the lidar scan, such as stone piers, doors, trees, etc., if the calculated background is used directly, the existing objects will be regarded as intruders, resulting in misjudgment. If the scene background is used directly to detect intruders, any changes in the intruders need to be detected, and there is no intrusion boundary for comparison. The data of each point needs to be judged one by one, which increases the detection burden. By fusing the scene background and the calculated background, they can complement each other. We only need to pay attention to whether the intruder exceeds the intrusion detection boundary. Events outside the intrusion detection boundary do not need to be detected.

[0032] S4: Calculate the projection of the normal vectors of all points of the intrusion detection boundary background as the coefficient of the intrusion significance; this step includes the following sub-steps: S41: Calculating the vector coordinates of each point of the intrusion detection boundary background according to a trigonometric function and combining the distance of each point of the intrusion detection boundary background; Specifically, the vertical angle and horizontal angle of each point of the laser radar are known, and according to trigonometric functions and in combination with the distance of each point of the intrusion detection boundary background, the vector coordinates of each point of the intrusion detection boundary background can be calculated.

[0033] The main purpose of this step is to calculate the vector coordinates of each point of the intrusion detection boundary background to provide data support for subsequent calculations.

[0034] S42: For each laser radar data point, search for valid points around each point according to a predetermined grid. If the distance between the point and the surrounding valid points is less than a mutation threshold, the position of the valid point is recorded and the number of valid points is increased by 1. Otherwise, the position of the point is not recorded. After each grid search is completed, the number of all valid points in the same row or column is counted. If the number of valid points in the same row and column is greater than 0, the number of valid points is the number of valid points found. Otherwise, the number of valid points is 0. Specifically, for each point of the laser radar, the valid points around each point are searched according to the predetermined grid. If the distance between the point and the surrounding valid points is less than the mutation threshold, the position of the valid point is recorded and the number of valid points is increased by 1. Otherwise, the position of the point is not recorded. After each grid search is completed, the number of all valid points in the same row or column is counted. If the number of valid points in the same row and column is greater than 0, the number of valid points is the number of valid points searched, otherwise the number of valid points is 0.

[0035] The main purpose of this step is to calculate the number of valid points in the surface formed by each data point and its neighboring points, providing a data foundation for the subsequent calculation of the surface normal. By finding the normal vector of the surface formed by each data point and its neighboring points, the vertical resolution is high and the horizontal resolution is low. For consistency, the number of neighboring points is determined based on the vertical resolution: 2 points in the vertical direction, and the horizontal resolution is the maximum vertical resolution / the horizontal resolution. Taking a 16-line lidar as an example, the vertical resolution is 2° and the horizontal resolution is 0.18, resulting in a grid size of 2*10. Theoretically, the distance between adjacent points should not vary significantly. Excessive variation indicates anomalies or discontinuities. The length per degree is calculated using the formula 2πr / 360, where r is the boundary distance of the intrusion. The distance between two adjacent points is obtained based on the vertical resolution, which is the mutation threshold.

[0036] S43: If the number of valid points is greater than the number threshold, and all valid points are neither in the same row nor in the same column, the vector coordinates of the valid points are sequentially saved, a vector set is established, a covariance matrix of the vector set is calculated, and the covariance matrix is subjected to eigenvalue decomposition to obtain eigenvectors and eigenvalues, a vector value corresponding to the minimum eigenvalue is obtained, and a dot product operation is performed on the vector value and the vector value of the corresponding point to obtain a projection of the direction line of the corresponding point of the intrusion detection boundary background on the normal vector, that is, a coefficient of the intrusion significance is obtained; The main purpose of this step is to calculate the projection of the direction line of the intrusion detection boundary background corresponding point on the normal vector to remove the influence of small ground objects such as ground protrusions, mice, cats, etc.

[0037] S5: Preprocessing the real-time collected laser radar data, aligning the preprocessed data with the intrusion detection boundary background, and then performing differential processing on the preprocessed data with the intrusion detection boundary background to obtain differential data; Specifically, real-time laser radar data is collected. After a complete scanning cycle, each beam completes a full horizontal scan. Different radars have different specifications and may have different angles, some of which are 360°, others 120°, or other angles. The index of each point is calculated based on the vertical scanning angle resolution and the horizontal scanning angle resolution. The data is arranged in sequence in a two-dimensional array, and only the data within the scanning angle range of each laser radar beam is retained, thereby achieving angular alignment of the data with the intrusion detection boundary background. The pre-processed data is then differentially processed with the intrusion detection boundary background to obtain the differential data. In the differential process, the pre-processed data is subtracted from the intrusion detection boundary background. Points greater than 0 indicate intrusion, and points less than 0 indicate no intrusion.

[0038] The main purpose of this step is to obtain data that is differentiated from the intrusion detection boundary background, so as to provide a data basis for the subsequent judgment of whether there is an intrusion.

[0039] S6: Calculating the projection value of the differential data on the normal vector using the coefficient, and performing binarization processing on the projection value to obtain a set of all possible intrusion points; Specifically, the differenced data is multiplied by the coefficients at corresponding positions to obtain a projected value. This projected value is then binarized. If the projected value is greater than or equal to the intrusion point threshold, it is set to 255; otherwise, it is set to 0, resulting in a set of all possible intrusion points. Due to inherent LiDAR measurement errors and the potential for wind-induced leaf movement during measurement, an intrusion point threshold is introduced to eliminate both external and inherent measurement errors. Therefore, the intrusion point threshold can be determined based on the LiDAR's inherent ranging resolution.

[0040] The main purpose of this step is to obtain possible invasion points and provide a data basis for the subsequent calculation of intruders.

[0041] S7: performing noise removal on the set of all possible intrusion points; Specifically, the morphological noise removal algorithm is used to remove noise by opening operation. The main purpose of this step is to remove isolated and discontinuous points and eliminate abnormal data for the subsequent connected domain analysis.

[0042] S8: Perform connected domain analysis on the possible intrusion points after noise removal, count the possible candidate intrusion point sets, and obtain the connected domain set; Specifically, after noise removal, the possible intrusion points are analyzed for connected domains, and the set of possible candidate intrusion points is counted to obtain the connected domain set. The main purpose of this step is to obtain the connected domain set to provide a data basis for the subsequent calculation of whether there is an intrusion.

[0043] S9: Obtain the largest connected domain in the connected domain set, and count the valid points in the connected domain. If the valid points are greater than the intrusion point threshold, it indicates intrusion; otherwise, it indicates no intrusion.

[0044] Specifically, the connected domain set is sorted, the largest point in the connected domain set is obtained, and the number of valid points in the connected domain is counted.

[0045] Formula (1): c = 2πr / 360; According to formula (1), the length c per degree of distance from the laser radar to the intrusion boundary is calculated, where r is the distance from the laser radar to the intrusion boundary. Assuming that the height of a normal person is 1.7 meters (ignoring the influence of the head) and the width is 0.4 meters, it is equivalent to a rectangle. The number of points in the vertical direction is calculated as nc1=1.7 / c. The number of points after conversion according to the vertical resolution of the laser radar is nc=nc1 / vertical resolution. Similarly, the number of points in the horizontal direction is calculated as nr1=0.4 / c. The number of points after conversion according to the horizontal resolution of the laser radar is nr=nr1 / horizontal resolution. The number of points at the distance of the intrusion boundary for an adult is ny=nr*nc. Considering that the body shape of children is different from that of adults and the error caused by the head, the coefficient a can be appropriately reduced. a can be 0.5 or even lower to obtain the effective point threshold ny*a. The above calculation is based on land. The calculation method for the number of intrusion points in water is similar. Considering that the exposed area of intrusions in water is smaller than that on land, the coefficient can be appropriately reduced.

[0046] If the valid object points are greater than the invasion point threshold, it indicates invasion; otherwise, it indicates no invasion.

[0047] It can be seen from the above embodiments that the present application establishes a scene background, and derives a calculation background based on the angle range of intrusion monitoring, the boundary distance of the intrusion and the limit distance of the boundary, and fuses the scene background and the calculation background to generate an intrusion detection background. By performing a series of processing such as preprocessing, differential processing, binarization processing and connected domain analysis on the real-time collected lidar data, the status of whether an intrusion has occurred is finally obtained, which overcomes the technical problems of timeliness and intrusion incidents caused by blind spots brought about by traditional monitoring relying on manual inspections or visual inspections, thereby achieving the effect of real-time detection and a large detection range.

[0048] Corresponding to the aforementioned embodiment of the intrusion monitoring method based on laser radar, the present application also provides an embodiment of an intrusion monitoring device based on laser radar.

[0049] Figure 5 FIG. 1 is a block diagram of an intrusion monitoring device based on a laser radar according to an exemplary embodiment. Figure 5 , the device comprises: Scene background establishment module 1 is used to collect an initial specified number of frames of lidar data in real time to establish the scene background; The calculation background establishment module 2 is used to set the angle range of intrusion monitoring, the boundary distance of intrusion and the limit distance of the boundary, and convert it into the calculation background of the laser radar through mathematical calculation; A detection boundary generation module 3 is used to fuse the scene background with the calculation background to generate an intrusion detection boundary background; A first calculation module 4 is used to calculate the projection of the normal vectors of all points of the intrusion detection boundary background as the coefficient of the intrusion significance; The second calculation module 5 is used to pre-process the real-time collected laser radar data, align the pre-processed data with the intrusion detection boundary background, and then perform differential processing on the pre-processed data with the intrusion detection boundary background to obtain differential data; a third calculation module 6, configured to calculate the projection value of the differential data on the normal vector using the coefficient, and perform binarization processing on the projection value to obtain a set of all possible intrusion points; A noise removal module 7, configured to remove noise from the set of all possible intrusion points; Connected domain analysis module 8, used to perform connected domain analysis on the possible intrusion points after noise removal, count possible candidate intrusion point sets, and obtain a connected domain set; The intrusion judgment module 9 is used to obtain the largest connected domain in the connected domain set and count the valid points in the connected domain. If the valid points are greater than the intrusion point threshold, it indicates intrusion; otherwise, it indicates no intrusion.

[0050] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0051] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0052] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned laser radar-based intrusion monitoring method. Figure 6 As shown in the figure, a hardware structure diagram of an intrusion monitoring device based on laser radar provided by an embodiment of the present invention is provided in any device with data processing capability, except Figure 6 In addition to the processor, memory, DMA controller, disk, and non-volatile memory shown, any device with data processing capabilities in which the apparatus in the embodiment is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.

[0053] Accordingly, the present application also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-described laser radar-based intrusion monitoring method. The computer-readable storage medium may be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or memory. The computer-readable storage medium may also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. equipped on the device. Furthermore, the computer-readable storage medium may include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and may also be used to temporarily store data that has been output or is to be output.

[0054] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the contents disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only.

[0055] It will be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A laser radar-based intrusion monitoring method, characterized in that: include: Collect the initial specified number of frames of lidar data in real time to establish the scene background; Set the intrusion monitoring angle range, intrusion boundary distance and boundary limit distance, and convert them into the calculation background of the laser radar through mathematical calculation; Fusing the scene background with the calculation background to generate an intrusion detection boundary background; Calculating the projection of the normal vectors of all points of the intrusion detection boundary background as the coefficient of the intrusion significance; Preprocessing the real-time collected laser radar data, aligning the preprocessed data with the intrusion detection boundary background, and then performing differential processing on the preprocessed data with the intrusion detection boundary background to obtain differential data; Calculating the projection value of the differential data on the normal vector using the coefficient, and binarizing the projection value to obtain a set of all possible intrusion points; performing noise removal on the set of all possible intrusion points; Perform connected domain analysis on the possible intrusion points after noise removal, count the possible candidate intrusion point sets, and obtain the connected domain set; The largest connected domain in the connected domain set is obtained, and the number of valid points in the connected domain is counted. If the number of valid points is greater than the intrusion point threshold, it indicates intrusion; otherwise, it indicates no intrusion.

2. The method according to claim 1, characterized in that Collect the initial specified number of frames of lidar data in real time to establish the scene background, including: Continuously collect specified frame lidar data, and process the points at each angle in the horizontal direction of the lidar beam with different vertical angles in turn. If the distance of the point at the angle is greater than the distance threshold, the distance of the point at the angle is accumulated, and the number of valid points of the point at the angle is added by 1; otherwise, the point is discarded, and the distance and valid point number of the point at the angle are not accumulated; after the specified frame lidar data processing is completed, the total distance of the points at each angle is divided by the valid point number of the points at each angle to obtain the average distance of the points at each angle, thereby establishing the scene background.

3. The method according to claim 1, characterized in that Set the intrusion monitoring angle range, intrusion boundary distance and boundary limit distance, and convert them into the calculation background of the laser radar through mathematical calculation, including: S21: Set the angle range of intrusion monitoring, the boundary distance of intrusion and the limit distance of the boundary; S22: Starting from the starting angle of intrusion monitoring, scan progressively according to the horizontal angle resolution. Combining the limit distance of the laser radar boundary and the intrusion boundary distance of the laser radar, the horizontal projection distance of the laser radar radial distance is obtained according to the trigonometric function theorem; S23: The vertical angle is obtained by gradually increasing the vertical angle of each beam according to the resolution based on the angle of the starting beam. Combined with the horizontal projection distance of the radial distance of the laser radar, the radial distance of the horizontal projection distance on the laser radar can be calculated according to trigonometric functions, that is, the distance between the laser radar and the target object. S24: Starting from the first line beam, repeat S22-S23 to obtain the radial distance of the line beams in different vertical directions of the laser radar at each angle in the horizontal direction from the laser radar; S25: Calculate the angle corresponding to the laser radar data based on the vertical beam resolution and the horizontal angle resolution. The position of each angle can be mapped to a two-dimensional array. The horizontal coordinate of the two-dimensional array is the index of the vertical beam resolution, and the vertical coordinate is the index of the horizontal angle resolution. Assign the radial distance of the laser radar to the position of the two-dimensional array corresponding to the laser radar angle, so as to obtain the calculation background of the laser radar.

4. The method according to claim 1, wherein The scene background is integrated with the calculation background to generate an intrusion detection boundary background, including: Compare the distance between each corresponding point of the scene background and the calculated background. If the distance of the scene background is greater than the distance of the calculated background, set the distance of the corresponding point of the intrusion detection boundary background to the distance of the corresponding point of the calculated background; otherwise, if the distance of the scene background is 0, set the distance of the corresponding point of the intrusion detection boundary background to the distance of the corresponding point of the calculated background; otherwise, if the distance of the scene background is not greater than the distance of the calculated background, set the distance of the corresponding point of the intrusion detection boundary background to the distance of the corresponding point of the scene background, and the generation of the intrusion detection boundary background is completed.

5. The method according to claim 1, wherein Calculating the projection of the normal vectors of all points of the intrusion detection boundary background as the coefficient of the intrusion significance includes: Calculate the vector coordinates of each point of the intrusion detection boundary background according to trigonometric functions and in combination with the distance of each point of the intrusion detection boundary background; For each laser radar data, according to the predetermined grid, search for valid points around each point. If the distance between the point and the surrounding valid points is less than the threshold, the position of the valid point is recorded and the number of valid points is increased by 1. Otherwise, the position of the point is not recorded. After each grid search is completed, the number of all valid points in the same row or column is counted. If the number of valid points in the same row and column is greater than 0, the number of valid points is the number of valid points found. Otherwise, the number of valid points is 0. If the number of valid points is greater than the quantity threshold, and all valid points are neither in the same row nor in the same column, save the vector coordinates of the valid points in sequence, establish a vector set, calculate the covariance matrix of the vector set, and perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, obtain the vector value corresponding to the minimum eigenvalue, perform point multiplication on the vector value and the vector value of the corresponding point, and obtain the projection of the direction line of the corresponding point of the intrusion detection boundary background on the normal vector, that is, obtain the coefficient of the intrusion significance.

6. The method according to claim 1, characterized in that Preprocessing the real-time collected LiDAR data, aligning the preprocessed data with the intrusion detection boundary background, and then performing differential processing with the intrusion detection boundary background to obtain differential data, including: The laser radar data is collected in real time and arranged in sequence after completing a complete scanning cycle, retaining only the data of each laser radar line number within the scanning angle range, thereby achieving angular alignment of the data with the intrusion detection boundary background, and performing differential processing on the pre-processed data and the intrusion detection boundary background to obtain the differential data.

7. The method according to claim 1, characterized in that The projection value of the differential data on the normal vector is calculated using the coefficient, and the projection value is binarized to obtain a set of all possible intrusion points, including: The differential data is multiplied by the coefficient according to the corresponding position to obtain the projected value, and the projection value is binarized. That is, if the projection value is greater than or equal to the intrusion point threshold, it is set to 255, otherwise it is set to 0, and a set of all possible intrusion points is obtained.

8. An intrusion monitoring device based on laser radar, characterized in that: include: The scene background establishment module is used to collect the initial specified number of frames of lidar data in real time to establish the scene background; The calculation background establishment module is used to set the angle range of intrusion monitoring, the boundary distance of intrusion and the limit distance of the boundary, and convert it into the calculation background of the laser radar through mathematical calculation; A detection boundary generation module, configured to fuse the scene background with the calculation background to generate an intrusion detection boundary background; A first calculation module is used to calculate the projection of the normal vectors of all points of the intrusion detection boundary background as the coefficient of the intrusion significance; A second calculation module is used to preprocess the real-time collected laser radar data, align the angle of the preprocessed data with the intrusion detection boundary background, and then perform differential processing on the preprocessed data with the intrusion detection boundary background to obtain differential data; a third calculation module, configured to calculate a projection value of the differential data on a normal vector using the coefficient, and perform binarization processing on the projection value to obtain a set of all possible intrusion points; A noise removal module, configured to remove noise from the set of all possible intrusion points; The connected domain analysis module is used to perform connected domain analysis on the possible intrusion points after noise removal, count the possible candidate intrusion point sets, and obtain the connected domain set; The intrusion judgment module is used to obtain the largest connected domain in the connected domain set and count the valid points in the connected domain. If the valid points are greater than the intrusion point threshold, it indicates intrusion; otherwise, it indicates no intrusion.

9. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images