Moving target detection method and device based on laser radar

Abstract

The embodiment of the invention provides a moving target detection method and device based on a laser radar, and the method comprises the steps: obtaining historical point cloud data, and determining an initial background grid based on the historical point cloud data; obtaining point cloud data of a current frame, performing weight calculation based on the initial background grid and the point cloud data of the current frame, and determining a weight result; determining a grid type based on a weight result; wherein the grid type comprises a blind area grid, a foreground grid and a background grid; and performing moving target detection based on the grid type. Whether the object belongs to the background or not is judged by counting the retention time of the object in the area, so that the foreground and the background are separated, meanwhile, a blind area concept is introduced to avoid misjudgment caused by point cloud ghosting caused by foreground object movement, and therefore the accuracy of moving target detection is improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of radar detection technology, and in particular to a moving target detection method based on laser radar. Background Art

[0002] Lidar is a radar system that emits laser beams to detect the position, speed and other characteristic quantities of a target. Its working principle is to emit a detection signal (laser beam) to the target, and then compare the received signal reflected from the target (target echo) with the transmitted signal. After appropriate processing, relevant information about the target can be obtained, such as target distance, direction, height, speed, attitude, and even shape parameters, so as to detect, track and identify targets such as aircraft and missiles.

[0003] In the existing technology, laser radar is used for scanning, and after generating a three-dimensional grid map, each point cloud scanned by the multi-line laser radar is judged to be a ground point by calculating the attributes of the point cloud and the propagation of the attributes of the adjacent points, thereby separating the foreground and the background. There is also a solution that uses the real-time point cloud of the laser radar to subtract the environmental background model to obtain the foreground point cloud. However, the accuracy of separating the foreground and background is insufficient, so a better solution is urgently needed. Summary of the invention

[0004] In view of this, the embodiments of this specification provide a moving target detection method based on laser radar. One or more embodiments of this specification also relate to a moving target detection device based on laser radar, a computing device, a computer-readable storage medium and a computer program to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a method for detecting moving targets based on a laser radar is provided, comprising: Acquire historical point cloud data, and determine an initial background grid based on the historical point cloud data; Obtain the current frame point cloud data, perform weight calculation based on the initial background grid and the current frame point cloud data, and determine the weight result; Determine the grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; Active object detection based on raster type.

[0006] In a possible implementation, obtaining historical point cloud data and determining an initial background grid based on the historical point cloud data include: Obtain historical point cloud data within the target time, perform weight accumulation based on the historical point cloud data, and determine the initial background grid.

[0007] In a possible implementation, the current frame point cloud data is obtained, and weight calculation is performed based on the initial background grid and the current frame point cloud data to determine the weight result, including: Obtain the current frame point cloud data, and determine the target point cloud data from the current frame point cloud data; Perform point cloud mapping based on target point cloud data to determine the target grid; The weight calculation is performed based on the target grid and the initial background grid to determine the weight result.

[0008] In a possible implementation, point cloud mapping is performed based on target point cloud data to determine a target grid, including: If there is no corresponding grid for the target point cloud data, create the target grid; Bind the target grid to the target point cloud data.

[0009] In a possible implementation, weight calculation is performed based on the target grid and the initial background grid to determine the weight result, including: Determine the weight change value of each grid based on the target grid and the background grid; The weight results are determined based on the weight change values ​​of each grid.

[0010] In a possible implementation, determining the grid type based on the weight result includes: When the weight result is greater than the weight threshold, the grid type is determined to be a background grid; When the grid corresponding to the weight result is a newly added grid, it is determined whether the newly added grid is a blind area grid; When the newly added grid is not a blind area grid, the grid type is determined to be a foreground grid.

[0011] In a possible implementation, active target detection is performed based on the grid type, including: When the grid type is a foreground grid, obtain the foreground point cloud data corresponding to the foreground grid; Active target detection based on foreground point cloud data.

[0012] According to a second aspect of an embodiment of this specification, a moving target detection device based on a laser radar is provided, comprising: A background determination module is configured to obtain historical point cloud data and determine an initial background grid based on the historical point cloud data; A weight determination module is configured to obtain the current frame point cloud data, perform weight calculation based on the initial background grid and the current frame point cloud data, and determine the weight result; A type determination module is configured to determine a grid type based on a weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; The target detection module is configured to perform active target detection based on the grid type.

[0013] According to a third aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned laser radar-based active target detection method are implemented.

[0014] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned laser radar-based active target detection method are implemented.

[0015] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned laser radar-based active target detection method.

[0016] The embodiments of this specification provide a method and device for detecting active targets based on laser radar, wherein the method for detecting active targets based on laser radar includes: obtaining historical point cloud data, determining the initial background grid based on the historical point cloud data; obtaining current frame point cloud data, performing weight calculation based on the initial background grid and the current frame point cloud data, and determining the weight result; determining the grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; and detecting active targets based on the grid type. Whether an object belongs to the background is determined by counting the length of time the object stays in the area, thereby separating the foreground from the background, and introducing the concept of blind areas to avoid misjudgment caused by point cloud afterimages caused by the movement of foreground objects, thereby improving the accuracy of active target detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of a scene of a method for detecting moving targets based on laser radar provided by an embodiment of this specification; Figure 2 is a flow chart of a method for detecting moving targets based on laser radar provided by an embodiment of this specification; Figure 3a is a grid schematic diagram of a laser radar-based moving target detection method provided by an embodiment of this specification; Figure 3b is a schematic diagram of a moving target detection method based on laser radar provided in one embodiment of this specification; Figure 4This is a schematic diagram of a first scenario of a method for detecting moving targets based on laser radar provided by an embodiment of this specification; Figure 5 is a schematic diagram of a second scenario of a method for detecting moving targets based on laser radar provided by an embodiment of this specification; Figure 6 is a schematic diagram of a third scenario of a method for detecting moving targets based on a laser radar provided by an embodiment of this specification; Figure 7 It is a structural schematic diagram of a moving target detection device based on laser radar provided by an embodiment of this specification; Figure 8 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0018] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

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

[0020] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. 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] In this specification, a moving target detection method based on laser radar is provided. This specification also involves a moving target detection device based on laser radar, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0022] See also Figure 1 , Figure 1 A schematic diagram of a scenario of a laser radar-based active target detection method provided according to an embodiment of the present specification is shown.

[0023] exist Figure 1 In the application scenario, the computing device 101 can obtain historical point cloud data and determine the initial background grid 102 based on the historical point cloud data. Then, the computing device 101 can obtain the current frame point cloud data, perform weight calculation based on the initial background grid 102 and the current frame point cloud data, and determine the weight result 103. After that, the computing device 101 can determine the grid type 104 based on the weight result 103. Finally, the computing device 101 can perform active target detection based on the grid type 104, as shown in the reference numeral 105.

[0024] It should be noted that the computing device 101 can be hardware or software. When the computing device 101 is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device 101 is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.

[0025] See also Figure 2 , Figure 2 A flowchart of a laser radar-based moving target detection method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0026] Step 201: Acquire historical point cloud data, and determine an initial background grid based on the historical point cloud data.

[0027] In a possible implementation, historical point cloud data is obtained, and an initial background grid is determined based on the historical point cloud data, including: obtaining historical point cloud data within a target time, accumulating weights based on the historical point cloud data, and determining the initial background grid.

[0028] In practical applications, the solution of this embodiment can be applied to multi-line radars and single-line radars. Taking a single-line radar as an example, the detection coverage area of ​​the laser radar is rasterized as A×D×1. If it is a multi-line radar, then A×D×Z, where A is the dimension of the radar servo azimuth, D is the radar distance dimension, and Z is the number of radar lines. Figure 3a, the grids are defined into four types: foreground, background, blind spot, and unobstructed. Among them, background grid: there are persistent point clouds in it, that is, point clouds formed by fixed objects or environments, such as walls, pillars, and the ground. Foreground grid: there are non-persistent point clouds in it, that is, point clouds formed by moving objects or people. Unobstructed grid: in the same dimension A, there is no background grid, nor foreground grid area. Blind spot grid: in the same dimension A, all grids with D values ​​greater than "detection" and "background", that is, the blocked area. There may be moving people or objects in this area, or it may be a fixed background.

[0029] Furthermore, each grid is defined with the following properties: background weight , where ∅_b is the background weight threshold.

[0030] It should be noted that when implementing this scheme, a certain cumulative time needs to be given to the grid background weight after the scheme is started, that is, the initial background grid is determined. Therefore, the point cloud in the "foreground grid" for a period of time after the scheme is started is not processed. The specific value of a period of time is determined according to the scanning frequency of the radar, which is generally a few seconds.

[0031] For example, see Figure 3a ,Within 10 seconds after the scheme is started, the background weight of the grid area corresponding to the cylinder is continuously accumulated, that is, the cylinder is determined as the initial background grid.

[0032] Step 202: Obtain the current frame point cloud data, perform weight calculation based on the initial background grid and the current frame point cloud data, and determine the weight result.

[0033] In one possible implementation, the current frame point cloud data is obtained, and weight calculation is performed based on the initial background grid and the current frame point cloud data to determine the weight result, including: obtaining the current frame point cloud data, and determining the target point cloud data from the current frame point cloud data; performing point cloud mapping based on the target point cloud data to determine the target grid; and performing weight calculation based on the target grid and the initial background grid to determine the weight result.

[0034] In practical applications, see Figure 3b , in the currently acquired point cloud data, a frame of point cloud data is accessed, that is, the target point cloud data is determined from the current frame of point cloud data, the target point cloud data is traversed, and the target point cloud data is mapped to the corresponding grid, that is, the target grid is determined. After the target grid is determined, the weight calculation can be performed according to the target grid and the initial background grid to determine the weight result.

[0035] In a possible implementation, point cloud mapping is performed based on the target point cloud data to determine the target grid, including: creating a target grid when no corresponding grid exists for the target point cloud data; and binding the target grid to the target point cloud data.

[0036] In practical applications, in order to reduce computing resources, each grid is created dynamically, that is, only the background grid and the detection grid are maintained, and the grid object is released when the grid b value is 0. Then, when new point cloud data appears in a certain area, the grid of the area is created in real time.

[0037] It should be noted that the mapping count n can be maintained in the grid object. After the traversal is completed, if the grid n value is too small, the corresponding point cloud can be discarded, thereby achieving a denoising effect and improving the accuracy of subsequent detection.

[0038] In a possible implementation, weight calculation is performed based on the target grid and the initial background grid to determine the weight result, including: determining the weight change value of each grid based on the target grid and the background grid; and determining the weight result based on the weight change value of each grid.

[0039] In practical applications, see Figure 3b After the target grid is determined, the weight calculation can be performed based on the target grid and the initial background grid, that is, the grid with point cloud mapping is executed b = b+ Operation. Among them, is the background weight gain, and correspondingly, is the periodic attenuation of the background weight, , , To improve the detection sensitivity, The final value of b is the weight result.

[0040] Step 203: Determine the grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid.

[0041] In a possible implementation, the grid type is determined based on the weight result, including: when the weight result is greater than the weight threshold, determining the grid type as a background grid; when the grid corresponding to the weight result is a newly added grid, judging whether the newly added grid is a blind spot grid; when the newly added grid is not a blind spot grid, determining the grid type as a foreground grid.

[0042] In practical applications, whether a grid is a background grid can be determined based on a set weight threshold. Figure 3b For the newly added grid, first determine whether it is a blind grid. The judgment method is that if there is a background grid or a foreground grid in the same A dimension, if the D value of the current grid is greater than the background grid or the foreground grid, it is determined to be a blind area. If the newly added grid is not a blind grid, the grid type is determined to be a foreground grid.

[0043] It should be noted that since the point cloud data is constantly updated, it is also necessary to set the grid background weight periodic decay. After that, traverse all grids and delete the grids with b value of 0.

[0044] Step 204: Perform active target detection based on the grid type.

[0045] In a possible implementation, active target detection is performed based on the grid type, including: when the grid type is a foreground grid, obtaining foreground point cloud data corresponding to the foreground grid; and active target detection is performed based on the foreground point cloud data.

[0046] In practical applications, the point cloud data in all foreground grids are taken out for subsequent processing such as point cloud segmentation, point cloud recognition, and tracking.

[0047] For example, the point cloud data in all foreground grids are retrieved, shape determination is performed based on the point cloud data, and the category of the object is determined based on the result of the shape determination.

[0048] The embodiments of this specification provide a method and device for detecting active targets based on laser radar, wherein the method for detecting active targets based on laser radar includes: obtaining historical point cloud data, determining the initial background grid based on the historical point cloud data; obtaining current frame point cloud data, performing weight calculation based on the initial background grid and the current frame point cloud data, and determining the weight result; determining the grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; and detecting active targets based on the grid type. Whether an object belongs to the background is determined by counting the length of time the object stays in the area, thereby separating the foreground from the background, and introducing the concept of blind areas to avoid misjudgment caused by point cloud afterimages caused by the movement of foreground objects, thereby improving the accuracy of active target detection.

[0049] In one embodiment, if Figure 4 As shown in the figure, a car is parked between the laser radar and the wall. After the laser radar is turned on, some point clouds fall on the vehicle, and some point clouds may fall on the wall through the glass or wheel gap of the vehicle. According to the algorithm of this scheme, the grid S where the vehicle is located 车 The background weight of the car and the wall grid S 墙 The background weights of are rapidly accumulated, and after reaching the weight, due to S 车 The D value is less than S 墙 The D value is thus determined. 车 is the background grid, S 墙 Blind area grid.

[0050] like Figure 5As shown, when a pedestrian passes in front of a vehicle, the grid where the person is located will be immediately determined as a foreground grid, thereby detecting the point cloud falling on the pedestrian.

[0051] like Figure 6 As shown, the vehicle moves from a stationary state to S 车 When the grid is 车 The background weight of the grid decays until the judgment of "background grid" is cancelled, and S 墙 The background weight of S is accumulated quickly and is judged as a new background. 墙 It was previously determined to be a blind spot, so when the point cloud that was previously blocked by the vehicle falls on the wall, it will not be determined as a "foreground point cloud", thus avoiding misjudgment.

[0052] The embodiments of this specification do not require maintenance of a background model. If the environment in the detection area changes, it can adapt quickly. The algorithm is simple and efficient, occupies few computing resources, and the algorithm time complexity is only O(N). It has good detection performance for fast-moving objects, adjustable detection sensitivity, and built-in point cloud denoising capabilities.

[0053] Corresponding to the above method embodiment, this specification also provides an embodiment of a moving target detection device based on laser radar, Figure 7 FIG. 1 is a schematic diagram showing a structure of a moving target detection device based on a laser radar provided by an embodiment of the present specification. Figure 7 As shown, the device comprises: The background determination module 701 is configured to obtain historical point cloud data and determine an initial background grid based on the historical point cloud data; The weight determination module 702 is configured to obtain the current frame point cloud data, perform weight calculation based on the initial background grid and the current frame point cloud data, and determine the weight result; The type determination module 703 is configured to determine the grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; The target detection module 704 is configured to perform active target detection based on the grid type.

[0054] In a possible implementation, the background determination module 701 is further configured to: Obtain historical point cloud data within the target time, perform weight accumulation based on the historical point cloud data, and determine the initial background grid.

[0055] In a possible implementation, the weight determination module 702 is further configured to: Obtain the current frame point cloud data, and determine the target point cloud data from the current frame point cloud data; Perform point cloud mapping based on target point cloud data to determine the target grid; The weight calculation is performed based on the target grid and the initial background grid to determine the weight result.

[0056] In a possible implementation, the weight determination module 702 is further configured to: If there is no corresponding grid for the target point cloud data, create the target grid; Bind the target grid to the target point cloud data.

[0057] In a possible implementation, the weight determination module 702 is further configured to: Determine the weight change value of each grid based on the target grid and the background grid; The weight results are determined based on the weight change values ​​of each grid.

[0058] In a possible implementation, the type determination module 703 is further configured to: When the weight result is greater than the weight threshold, the grid type is determined to be a background grid; When the grid corresponding to the weight result is a newly added grid, it is determined whether the newly added grid is a blind area grid; When the newly added grid is not a blind area grid, the grid type is determined to be a foreground grid.

[0059] In a possible implementation, the target detection module 704 is further configured to: When the grid type is a foreground grid, obtain the foreground point cloud data corresponding to the foreground grid; Active target detection based on foreground point cloud data.

[0060] The embodiments of this specification provide a method and device for detecting active targets based on laser radar, wherein the active target detection device based on laser radar includes: obtaining historical point cloud data, determining the initial background grid based on the historical point cloud data; obtaining current frame point cloud data, performing weight calculation based on the initial background grid and the current frame point cloud data, and determining the weight result; determining the grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; and detecting active targets based on the grid type. Whether an object belongs to the background is determined by counting the length of time the object stays in the area, thereby separating the foreground from the background, and at the same time introducing the concept of blind spots to avoid misjudgment caused by point cloud afterimages caused by the movement of foreground objects, thereby improving the accuracy of active target detection.

[0061] The above is a schematic scheme of a moving target detection device based on laser radar in this embodiment. It should be noted that the technical scheme of the moving target detection device based on laser radar and the technical scheme of the moving target detection method based on laser radar belong to the same concept, and the details not described in detail in the technical scheme of the moving target detection device based on laser radar can be referred to the description of the technical scheme of the moving target detection method based on laser radar.

[0062] Figure 8 The block diagram of a computing device 800 according to an embodiment of the present specification is shown. The components of the computing device 800 include but are not limited to a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0063] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0064] In one embodiment of the present specification, the above components of the computing device 800 and Figure 8 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 8 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0065] The computing device 800 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 800 may also be a mobile or stationary server.

[0066] Among them, the processor 820 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned active target detection method based on laser radar. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned active target detection method based on laser radar belong to the same concept. For details not described in detail in the technical scheme of the computing device, please refer to the description of the technical scheme of the above-mentioned active target detection method based on laser radar.

[0067] An embodiment of the present specification also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned laser radar-based active target detection method.

[0068] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned active target detection method based on laser radar belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned active target detection method based on laser radar.

[0069] An embodiment of the present specification also provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned laser radar-based active target detection method.

[0070] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned active target detection method based on laser radar belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above-mentioned active target detection method based on laser radar.

[0071] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0073] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0074] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0075] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A moving target detection method based on laser radar, characterized in that: include: Acquire historical point cloud data, and determine an initial background grid based on the historical point cloud data; Acquire the current frame point cloud data, perform weight calculation based on the initial background grid and the current frame point cloud data, and determine the weight result; Determining a grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; Active target detection is performed based on the grid type.

2. The method according to claim 1, characterized in that The acquiring of historical point cloud data and determining an initial background grid based on the historical point cloud data includes: Obtain historical point cloud data within the target time, perform weight accumulation based on the historical point cloud data, and determine the initial background grid.

3. The method according to claim 1, characterized in that Acquiring the current frame point cloud data, performing weight calculation based on the initial background grid and the current frame point cloud data, and determining the weight result, including: Acquire current frame point cloud data, and determine target point cloud data from the current frame point cloud data; Performing point cloud mapping based on the target point cloud data to determine a target grid; A weight calculation is performed based on the target grid and the initial background grid to determine a weight result.

4. The method according to claim 3, characterized in that The step of performing point cloud mapping based on the target point cloud data to determine the target grid includes: When there is no corresponding grid for the target point cloud data, creating a target grid; The target grid is bound to the target point cloud data.

5. The method according to claim 3, characterized in that: The step of performing weight calculation based on the target grid and the initial background grid to determine the weight result includes: Determine a weight change value of each grid based on the target grid and the background grid; A weight result is determined based on the weight change values ​​of each grid.

6. The method according to claim 1, characterized in that The determining of the grid type based on the weight result comprises: When the weight result is greater than the weight threshold, determining the grid type as a background grid; In the case where the grid corresponding to the weight result is a newly added grid, determining whether the newly added grid is a blind area grid; When the newly added grid is not a blind area grid, the grid type is determined to be a foreground grid.

7. The method according to claim 1, characterized in that The performing active target detection based on the grid type includes: When the grid type is a foreground grid, obtaining foreground point cloud data corresponding to the foreground grid; Active target detection is performed based on the foreground point cloud data.

8. A moving target detection device based on laser radar, characterized in that: include: A background determination module is configured to obtain historical point cloud data and determine an initial background grid based on the historical point cloud data; A weight determination module is configured to obtain the current frame point cloud data, perform weight calculation based on the initial background grid and the current frame point cloud data, and determine a weight result; A type determination module is configured to determine a grid type based on the weight result; wherein the grid type includes a blind area grid, a foreground grid, and a background grid; The target detection module is configured to perform active target detection based on the grid type.

9. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the active target detection method based on laser radar as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the laser radar-based active target detection method described in any one of claims 1 to 7.

Images