Foreign matter detection method and system based on three-dimensional laser radar

Abstract

This application provides a foreign object detection method and system based on three-dimensional lidar, relating to the field of computer technology. The method includes: acquiring data to be detected, the data including signal data and audio / video data of a region to be detected; detecting the data to be detected to obtain an initial detection result; determining an adjustable error based on the initial detection result; and performing error compensation processing on the initial detection result based on a target foreign object detection model and the adjustable error to obtain a target detection result, wherein the target detection result includes first information about the target foreign object. This application can improve the efficiency and effectiveness of foreign object detection.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method and system for foreign object detection based on three-dimensional lidar. Background Technology

[0002] With the rapid development of technology, high-speed rail stations and railway stations are usually equipped with a variety of devices to detect foreign objects, passenger flow and other relevant information in order to ensure the orderly flow of people.

[0003] However, the equipment used to detect the above information usually only acquires some pictures and videos of the area around the station building, and then the staff checks the pictures and videos to determine whether there are foreign objects. This has the drawbacks of large detection errors and low efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide a foreign object detection method and system based on three-dimensional lidar. This application embodiment can significantly improve the accuracy and efficiency of foreign object detection. The specific technical solution is as follows:

[0005] In a first aspect of the present invention, a foreign object detection method based on three-dimensional lidar is provided, the method comprising:

[0006] Acquire the data to be detected, which includes signal data and audio / video data of the area to be detected;

[0007] The data to be detected is then tested to obtain initial detection results;

[0008] Based on the initial detection results, determine the adjustable error;

[0009] Based on the target foreign object detection model, the initial detection result is processed by error compensation combined with the adjustable error to obtain the target detection result, which includes the first information of the target foreign object.

[0010] Optionally, acquiring the data to be detected includes: acquiring the region to be detected and the fused detection signal of the candidate targets in the region to be detected.

[0011] Optionally, acquiring the region to be detected and the fused detection signal of candidate targets in the region to be detected includes:

[0012] Signals are transmitted to the region to be detected and the candidate target;

[0013] The reflected signal from the region to be detected and the reflected signal from the candidate target are received as input signals.

[0014] The input signal and the transmitted signal are fused to obtain the fused detection signal.

[0015] Optionally, the step of detecting the data to be detected to obtain an initial detection result includes:

[0016] Obtain the first confidence level of detecting the candidate target in the data to be detected;

[0017] If the first confidence level is greater than a preset threshold, then the second information of the candidate target is further obtained as the initial detection result.

[0018] Optionally, determining the adjustable error includes:

[0019] Obtain the danger level of the candidate target;

[0020] The adjustable error is determined based on the hazard level of the candidate target.

[0021] Optionally, the adjustable error includes the theoretical error movement distance of the candidate target, and determining the adjustable error based on the hazard level of the candidate target includes:

[0022] Based on the confidence level, determine the error weight;

[0023] The adjustable error is determined based on the error weight and the movement time of the candidate target.

[0024] In another aspect of the present invention, a foreign object detection system based on three-dimensional lidar is provided, the system comprising:

[0025] The data acquisition module is used to acquire the data to be detected, which includes signal data and audio / video data of the area to be detected.

[0026] The initial detection result acquisition module is used to detect the data to be detected and obtain the initial detection result;

[0027] An adjustable error determination module is used to determine an adjustable error based on the initial detection result;

[0028] The target foreign object detection module is used to perform error compensation processing on the initial detection result based on the target foreign object detection model and the adjustable error to obtain the target detection result, wherein the target detection result includes the first information of the target foreign object.

[0029] Optionally, the data acquisition module is further configured to: acquire the region to be detected, and the fused detection signal of the candidate target in the region to be detected.

[0030] In another aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed, implements the steps of the method described above.

[0031] In another aspect of the present invention, a computer device is provided, including a processor, a memory, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described above.

[0032] As can be seen from the above, the embodiments of this application can use a three-dimensional lidar in conjunction with audio and video data acquisition equipment to detect foreign objects in the area to be detected. During the detection process, theoretical errors can be fully considered, and after error compensation is performed on the preliminary detection results, the various information of the foreign object can be accurately detected by combining a neural network model, thereby improving the efficiency and accuracy of foreign object detection. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a schematic diagram illustrating an application scenario of the foreign object detection system based on three-dimensional LiDAR provided in the embodiments of this application;

[0035] Figure 2 This is a flowchart illustrating the foreign object detection method based on three-dimensional lidar provided in the embodiments of this application;

[0036] Figure 3 This is a schematic diagram of the foreign object detection system based on three-dimensional lidar provided in the embodiments of this application;

[0037] Figure 4 This is an internal structural diagram of the computer device provided in the embodiments of this application. Detailed Implementation

[0038] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0039] It should be understood that the terms "system," "unit," and / or "module" used herein are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0040] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0041] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0042] Figure 1 This is a schematic diagram of a foreign object detection system 100 based on a three-dimensional LiDAR, according to some embodiments of the present invention. For example, the foreign object detection system 100 based on a three-dimensional LiDAR can be a platform providing services for image / video detection. The foreign object detection system 100 based on a three-dimensional LiDAR may include a server 110, a storage device 120, a network 150, and one or more terminals 140. The server 110 may include a processing engine 112.

[0043] In some embodiments, server 110 may be a single server or a group of servers. The server group may be centralized or distributed (e.g., server 110 may be a distributed system). In some embodiments, server 110 may be local or remote. For example, server 110 may access information and / or data stored in storage device 120 and / or terminal 140 via network 130. As another example, server 110 may directly connect to storage device 130 and / or terminal 140 to access stored information and / or data. In some embodiments, server 110 may be implemented on a cloud platform. As merely an example, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, etc., or any combination of the above examples. In some embodiments, server 110 may be integrated with this application. Figure 2 or Figure 3 This is implemented on the computing device shown. For example, server 110 can be implemented on a computing device such as... Figure 2The example shown is implemented on a computing device 200, including one or more components within the computing device 200. For example, server 110 can be implemented as follows: Figure 3 Implemented on a mobile device 300, as shown, it includes one or more components in the computing device 300.

[0044] In some embodiments, server 110 may include a processing engine 112. Processing engine 112 may process information and / or data related to service requests to perform one or more functions described herein. For example, processing engine 112 may detect a target from an image and / or video. In some embodiments, processing engine 112 may include one or more processors (e.g., a single-core processor or a multi-core processor). As merely an example, processing engine 112 may include one or more hardware processors, such as a central processing unit (CPU), application-specific integrated circuit (ASIC), application-specific instruction set processor (ASIP), graphics processing unit (GPU), physical processing unit (PPU), digital signal processor (DSP), field-programmable gate array (FPGA), programmable logic device (PLD), controller, microcontroller unit, reduced instruction set computer (RISC), microprocessor, etc., or any combination of the examples above.

[0045] Storage device 120 can store data and / or instructions. In some embodiments, storage device 130 can store data obtained from terminal 140. In some embodiments, storage device 120 can store data and / or instructions for execution or use by server 110, which can implement the exemplary methods described herein by executing or using the data and / or instructions. In some embodiments, storage device 120 may include mass storage, removable storage, volatile read-write storage, read-only storage (ROM), or any combination of the examples above. Exemplary mass storage may include disks, optical disks, solid-state drives, etc. Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, compressed hard drives, magnetic tapes, etc. Exemplary volatile read-only storage may include random access memory (RAM). Exemplary random access memory may include dynamic random access memory (DRAM), dual data rate synchronous dynamic random access memory (DDRSDRAM), static random access memory (SRAM), silicon controlled retrieval memory (T-RAM), and zero-capacitance memory (Z-RAM), etc. Exemplary read-only memories may include masked read-only memories (MROMs), programmable read-only memories (PROMs), erasable programmable read-only memories (EPROMs), electrically erasable programmable read-only memories (EEPROMs), compressed hard disk read-only memories (CD-ROMs), and digital multifunction hard disk read-only memories, etc. In some embodiments, storage device 120 may be implemented on a cloud platform. To give merely one example, the cloud platform may include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, inter-cloud, multi-cloud, etc., or any combination of the examples above.

[0046] In some embodiments, storage device 120 may be connected to network 130 to enable communication with one or more components (e.g., server 110, terminal 140, etc.) of the 3D LiDAR-based foreign object detection system 100. One or more components of the 3D LiDAR-based foreign object detection system 100 may access data or instructions stored in storage device 120 via network 130. In some embodiments, storage device 120 may be directly connected to or communicate with one or more components (e.g., terminal 140, etc.) of the 3D LiDAR-based foreign object detection system 100. In some embodiments, storage device 120 may be part of server 110.

[0047] Network 130 can facilitate the exchange of information and / or data. In some embodiments, one or more components in the 3D LiDAR-based foreign object detection system 100 (e.g., server 110, storage device 120, and terminal 140, etc.) can send information and / or data to other components in the on-demand service 100 via network 130. For example, server 110 can obtain / receive requests from terminal 140 via network 130. In some embodiments, network 130 can be any of a wired network or a wireless network, or a combination thereof. For example, network 130 can include a cable network, wired network, fiber optic network, telecom network, intranet, Internet, local area network (LAN), wide area network (WAN), wireless local area network (WLAN), metropolitan area network (MAN), public switch telephone network (PSTN), Bluetooth network, ZigBee network, near field communication (NFC) network, etc., or any combination of the examples above. In some embodiments, network 130 can include one or more network access points. For example, network 130 may include wired or wireless network access points, such as base stations and / or Internet switching points 130-1, 130-2, etc. Through an access point, one or more components of the 3D LiDAR-based foreign object detection system 100 may be connected to the network 130 to exchange data and / or information.

[0048] Terminal 140 may include one or more devices with photo and / or video recording capabilities. For example, a desktop computer 140-1, a laptop computer 140-2, a 3D LiDAR 140-3, a smart mobile device 140-4, etc. In some embodiments, the 3D LiDAR 140-3 may include, but is not limited to, a camera, a security detection device, etc., or any combination thereof. In some embodiments, the mobile device 140-4 may include, but is not limited to, a smartphone, a personal digital assistant (PDA), a tablet computer, a handheld game console, smart glasses, a smartwatch, a wearable device, a virtual display device, a display enhancement device, etc., or any combination thereof. In some embodiments, terminal 140 may send images / videos to one or more devices in the 3D LiDAR-based foreign object detection system 100. For example, terminal 140 may send images / videos to server 110 for processing.

[0049] Figure 2 This application provides a schematic flowchart of a foreign object detection method and system based on a three-dimensional lidar, as illustrated in an embodiment of this application. Figure 2 As shown, a foreign object detection method and system based on three-dimensional lidar includes the following steps:

[0050] Step 201: Obtain the data to be detected.

[0051] The data to be detected may include signal data and audio / video data of the area to be detected. It can be understood that in a foreign object detection scenario at a high-speed railway station, a 3D LiDAR can acquire the radar signal of an object in the area to be detected. Furthermore, to improve detection accuracy, the foreign object detection method of this application can also be combined with audio / video data acquired by an audio / video acquisition device to complement the signal data of the 3D LiDAR for foreign object detection.

[0052] Step 201 may further include: acquiring the region to be detected and the fused detection signal of the candidate target in the region to be detected.

[0053] Candidate targets refer to targets that are detected as potentially foreign objects. For example, birds, animals, unidentified objects on high-speed rail station buildings, vehicles or machines moving at excessive speeds or under excessive loads, and other suspicious persons or objects that pose a threat to the high-speed rail transportation and maintenance environment can all be considered foreign objects.

[0054] Optionally, the step "acquiring the region to be detected and the fused detection signal of the candidate target in the region to be detected" includes:

[0055] Signals are transmitted to the region to be detected and the candidate target;

[0056] The reflected signal from the region to be detected and the reflected signal from the candidate target are received as input signals.

[0057] The input signal and the transmitted signal are fused to obtain the fused detection signal.

[0058] Specifically, the transmitted signal can be represented as:

[0059] *

[0060] in, The signal amplitude, Let t be the carrier frequency, t be the time, and u be the frequency modulation slope. These are preset parameters.

[0061] Alternatively, the frequency modulation slope can be expressed as:

[0062] u=B×T

[0063] Where B is the transmission signal bandwidth and T is the transmission signal duration.

[0064] After acquiring the transmitted signal, the features of the transmitted and input signals can be convolved using a signal fusion neural network model, followed by vector fusion. The output is a fused detection signal, which integrates the signal features of the region to be detected and the candidate target. The signal fusion neural network model can be a deep belief network (DBN), a deep learning neural network (DNN), etc., and this embodiment does not impose any restrictions on it.

[0065] Step 202: Detect the data to be detected to obtain the initial detection result.

[0066] Optionally, step 202 may also include:

[0067] Obtain the first confidence level of detecting the candidate target in the data to be detected;

[0068] If the first confidence level is greater than a preset threshold, then the second information of the candidate target is further obtained as the initial detection result. The second information is of the same type as the first information, and may include information such as the type, location coordinates, moving speed, volume, and danger level of the target object.

[0069] Optionally, the audio and video data of the fused detection signal and the candidate target can be input into the target foreign object detection model. The target foreign object detection model can be a classic learning model, such as DMP, OverFeat, R-CNN, SPP-Net, FastR-CNN, Faster R-CNN, R-FCN, DSOD, etc.

[0070] Specifically, the target foreign object detection model can calculate information such as the moving speed, moving distance, and position coordinates of a candidate target during the detection period based on the fused detection signal, combined with data such as the speed of light, the duration of the fused detection signal, and its frequency. For example, the moving speed and moving distance of a candidate target during the detection period can be calculated using the speed of light and the feedback duration of the fused detection signal. Then, by combining the moving distance data with the initial position coordinates of the candidate target, its real-time position coordinates can be calculated.

[0071] Furthermore, it can detect the type and size of foreign objects by using a module with image recognition capabilities based on audio and video data and image recognition technology.

[0072] During the calculation process of the target foreign object detection model, the first confidence level of the candidate target can be calculated through its internal confidence calculation module. For example, the confidence level can be 0.8, 0.9, etc. Then, by comparing whether the confidence level is greater than a preset threshold, for example, the preset threshold is 0.8, if it is greater than the preset threshold, it means that the probability and credibility of the candidate target being the target foreign object exceeds 80%, and the candidate target can be identified as the target foreign object. Then, the first information of the target foreign object can be further obtained. For example, the first information may include the type, location coordinates, moving speed, volume, and danger level of the target foreign object.

[0073] Step 203: Determine the adjustable error based on the initial detection results.

[0074] Optionally, step 203 may also include:

[0075] Obtain the danger level of the candidate target;

[0076] The adjustable error is determined based on the hazard level of the candidate target.

[0077] Here, "danger level" refers to the degree of danger posed by the candidate target. Danger level can be evaluated from multiple aspects, such as the candidate target's size, movement speed, load weight, and suspiciousness. In this embodiment, the movement speed of the candidate target is used as the standard for judging the danger level.

[0078] It is understandable that if the candidate target is a bird, machine, or person inside the station building that moves too fast, its high speed may affect the current detection area of ​​the station building. Therefore, a 3D lidar system combined with sound data acquisition equipment can be used to detect the instantaneous and average speed of the candidate target at multiple moments. The recorded speed data can then be used to set a hazard coefficient and level. For example, the hazard coefficient can be set to 8, 9, or 10 out of 10, and the hazard level can be high, medium, or low. The hazard level is directly proportional to the speed of the candidate target.

[0079] Specifically, the adjustable error can be determined by combining the magnitude of the initial detection result with a preset value. The preset value of the adjustable error can include a theoretical error value and an error weight. Taking the movement distance of the candidate target in the initial detection result as an example, to achieve accurate error compensation for the initial detection result, the detection error needs to be fully considered.

[0080] As an example only, assuming the candidate target's movement distance in the initial detection results is 10 meters, a reasonable theoretical error value can be determined for this initial detection data based on a preset range. For example, a movement distance of 10 to 20 meters corresponds to a theoretical error value of 0.1 to 0.2 meters. Combined with the danger coefficient determined by the candidate target's average or instantaneous movement speed, a corresponding error weight is determined for this theoretical error value. For example, the error weight could be 1.2, 1, 0.8, etc. This embodiment does not impose any restrictions on the magnitude of the theoretical error value and the error weight.

[0081] Step 204: Based on the target foreign object detection model, the initial detection result is processed by error compensation in combination with the adjustable error to obtain the target detection result.

[0082] In some embodiments, the calculation module within the target foreign object detection model can calculate the error compensation for the initial detection result using the following formula, which can be specifically expressed as:

[0083]

[0084] in, For the target foreign object in Duration and The total distance traveled over the specified time period The velocity value is a result of combining the average velocity of candidate targets with the instantaneous velocity at multiple time points. The total distance value can be calculated based on the feedback time and velocity data of the fused detection signal from the target foreign object detection model, or it can be calculated by processing and analyzing audio and video data. and The change in coordinate position is obtained from the distance, and then the result is calculated. The comprehensive processing may include selecting the median of the speed data, calculating the overall average speed, or randomly selecting a speed value; this embodiment does not impose any restrictions on this. For error weights, The theoretical error shift distance. This is the value of the adjustable error. Wherein, The value is directly proportional to the degree of danger; the greater the degree of danger, the greater the need for error compensation.

[0085] It is understandable that, within the preset error weights By combining theoretical error movement distance, the actual movement distance of a candidate target over a period of time can be effectively calculated through error compensation operations. This helps to accurately detect the initial information of the target foreign object, such as its position coordinates and velocity based on the actual movement distance, and even to make auxiliary judgments about the type of the target foreign object based on its velocity. Furthermore, this application can also perform foreign object detection using both fused detection signals and audio / video data of the candidate target, achieving comprehensive detection. Compared with existing technologies that rely on manual judgment of target foreign objects, the method of this application can greatly improve the efficiency and effectiveness of target foreign object detection.

[0086] Therefore, the embodiments of this application can use a three-dimensional lidar in conjunction with audio and video data acquisition equipment to detect foreign objects in the area to be detected. During the detection process, theoretical errors can be fully considered, and after error compensation for the preliminary detection results, the various information of the foreign object can be accurately detected by combining a neural network model, thereby improving the efficiency and accuracy of foreign object detection.

[0087] To implement the above-described method embodiments, this application also provides a foreign object detection system based on three-dimensional LiDAR. Figure 3 This illustration shows a structural schematic diagram of a foreign object detection system based on a three-dimensional lidar according to an embodiment of this application. The system includes:

[0088] The detection data acquisition module 301 is used to acquire the detection data, which includes signal data and audio / video data of the detection area;

[0089] The initial detection result acquisition module 302 is used to detect the data to be detected and obtain the initial detection result;

[0090] The adjustable error determination module 303 is used to determine the adjustable error based on the initial detection result;

[0091] The target foreign object detection module 304 is used to perform error compensation processing on the initial detection result based on the target foreign object detection model and the adjustable error to obtain the target detection result, wherein the target detection result includes the first information of the target foreign object.

[0092] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the modules / units / subunits / components in the above-described system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0093] As can be seen from the above, the embodiments of this application can use a three-dimensional lidar in conjunction with audio and video data acquisition equipment to detect foreign objects in the area to be detected. During the detection process, theoretical errors can be fully considered, and after error compensation is performed on the preliminary detection results, the various information of the foreign object can be accurately detected by combining a neural network model, thereby improving the efficiency and accuracy of foreign object detection.

[0094] In some embodiments, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data from the image acquisition device. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a foreign object detection method and system based on three-dimensional LiDAR.

[0095] In some embodiments, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, communication interface, display screen, and input system connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a foreign object detection method and system based on three-dimensional LiDAR. The display screen can be an LCD screen or an e-ink screen. The input system can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0096] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0097] In some embodiments, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0098] In some embodiments, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0099] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0100] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

[0102] In summary, this application provides a foreign object detection method based on three-dimensional lidar, comprising:

[0103] Acquire the data to be detected, which includes signal data and audio / video data of the area to be detected;

[0104] The data to be detected is then tested to obtain initial detection results;

[0105] Based on the initial detection results, determine the adjustable error;

[0106] Based on the target foreign object detection model, the initial detection result is processed by error compensation combined with the adjustable error to obtain the target detection result, which includes the first information of the target foreign object.

[0107] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0108] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0109] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0110] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0111] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0112] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the technical scope disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A foreign matter detection method based on a three-dimensional laser radar, characterized by, The method includes: Acquire the data to be detected, which includes signal data and audio / video data of the area to be detected; The data to be detected is then tested to obtain initial detection results; Based on the initial detection results, determine the adjustable error; Based on the target foreign object detection model, the initial detection result is compensated for error by combining the adjustable error to obtain the target detection result, which includes the first information of the target foreign object. The acquisition of the data to be detected includes: acquiring the region to be detected, and the fused detection signal of the candidate targets in the region to be detected; The step of acquiring the region to be detected and the fused detection signal of the candidate targets in the region to be detected includes: Signals are transmitted to the region to be detected and the candidate target; The reflected signal from the region to be detected and the reflected signal from the candidate target are received as input signals. The input signal and the transmitted signal are fused to obtain the fused detection signal; The step of detecting the data to be detected to obtain an initial detection result includes: Obtain the first confidence level of detecting the candidate target in the data to be detected; If the first confidence level is greater than a preset threshold, then the second information of the candidate target is further obtained as the initial detection result; The determination of the adjustable error includes: Obtain the danger level of the candidate target; The adjustable error is determined based on the risk level of the candidate target; The adjustable error includes the theoretical error movement distance of the candidate target, and determining the adjustable error based on the hazard level of the candidate target includes: Based on the first confidence level, determine the error weight; The adjustable error is determined based on the error weight and the movement time of the candidate target.

2. A foreign object detection system based on a three-dimensional laser radar, characterized by, The system is used to perform the method of claim 1, including: The data acquisition module is used to acquire the data to be detected, which includes signal data and audio / video data of the area to be detected. The initial detection result acquisition module is used to detect the data to be detected and obtain the initial detection result; An adjustable error determination module is used to determine an adjustable error based on the initial detection result; The target foreign object detection module is used to perform error compensation processing on the initial detection result based on the target foreign object detection model and the adjustable error to obtain the target detection result, wherein the target detection result includes the first information of the target foreign object. The data acquisition module is further specifically used to: acquire the region to be detected, and the fused detection signal of the candidate targets in the region to be detected.

3. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the steps of the method as described in claim 1.

4. A computer device comprising a processor, a memory, and a computer program stored in the memory, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in claim 1.

Images