Target detection method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application relate to a target detection method and device, electronic equipment and storage medium. The method comprises: obtaining first position information of a target, wherein the first position information comprises information obtained by an electromagnetic wave device detecting a target in a first detection area corresponding to the electromagnetic wave device; determining an image acquisition device corresponding to the target according to the first position information; determining a second detection area corresponding to the image acquisition device and determining the target in the second detection area; obtaining second position information of the target, determining a detection strategy corresponding to the target according to the second position information, and detecting the target based on the detection strategy. Thus, after the target is detected by the electromagnetic wave device, the image acquisition device corresponding to the target can be determined, the target can be determined by the image acquisition device, and the target can be tracked and detected, which is more intelligent, saves manpower, and improves real-time performance.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a target detection method, apparatus, electronic device, and storage medium. Background Technology

[0002] In areas requiring security checks, many are geographically open and remote, such as border regions. These areas are prone to danger if unauthorized vehicles or personnel are lurking nearby. Using personnel patrols presents challenges: patrol personnel face inherent risks, patrol efficiency is low, and checks may be missed.

[0003] Therefore, in existing technologies, video surveillance is commonly used for detection. However, video surveillance suffers from problems such as difficulty in determining the target location, small monitoring range, numerous blind spots, and difficulty in target detection. When using radar alone for detection, after a target is detected, it needs to be manually designated before further tracking and detection can be performed, which is labor-intensive, has low intelligence, and poor real-time performance. Summary of the Invention

[0004] In view of this, to address the problems of video surveillance detection, which suffers from difficulties in determining location, limited monitoring range, numerous blind spots, and difficulty in target detection, and radar detection, which requires manual designation of the target after detection for further tracking and detection, resulting in high labor costs, low intelligence, and poor real-time performance, this application provides a target detection method, device, electronic device, and storage medium.

[0005] In a first aspect, embodiments of this application provide a target detection method applied to an edge computing server, the method comprising:

[0006] Acquire first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device detecting the target within a first detection area corresponding to the electromagnetic wave device;

[0007] The image acquisition device corresponding to the target is determined based on the first location information;

[0008] Determine the second detection area corresponding to the image acquisition device, and determine the target in the second detection area;

[0009] Obtain the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy.

[0010] In an optional implementation, the electromagnetic wave device corresponds to at least one image acquisition device, and determining the image acquisition device corresponding to the target based on the first location information includes:

[0011] For any image acquisition device corresponding to the electromagnetic wave device, determine the device location information of the image acquisition device in the first detection area;

[0012] The distance between the target and the image acquisition device is determined based on the first location information and the device location information;

[0013] The image acquisition device with the smallest distance from the target is determined as the image acquisition device corresponding to the target.

[0014] In an optional implementation, the first position information is the position information of the target in a first coordinate system corresponding to the electromagnetic wave device, and before determining the second detection area corresponding to the image acquisition device, the method further includes:

[0015] Obtain the position transformation matrix between the electromagnetic wave device and the image acquisition device;

[0016] According to the position transformation matrix, the first position information is converted into the third position information of the target in the second coordinate system corresponding to the image acquisition device;

[0017] The shooting angle corresponding to the image acquisition device is determined based on the third location information;

[0018] Determine the distance between the target and the image acquisition device, and determine the shooting focal length corresponding to the image acquisition device based on the distance;

[0019] The image acquisition device is adjusted according to the shooting angle and the shooting focal length.

[0020] In an optional implementation, the method further includes, after which:

[0021] If the electromagnetic wave device detects the fourth location information of N new targets other than the target within a preset time period, then for any new target, the dispersion between the new target and the target is determined, where N is an integer;

[0022] Obtain the discreteness threshold corresponding to the image acquisition device;

[0023] If the dispersion is less than or equal to the dispersion threshold, then the second detection area corresponding to the image acquisition device is determined, and the new target in the second detection area is determined;

[0024] Obtain the fifth location information of the new target, determine the first detection strategy corresponding to the new target based on the fifth location information, and detect the new target based on the first detection strategy.

[0025] In an optional implementation, the method further includes:

[0026] If the dispersion is greater than the dispersion threshold, then based on the fourth location information of the new target, the image acquisition device closest to the new target is determined as the first image acquisition device corresponding to the new target;

[0027] Determine the third detection area corresponding to the first image acquisition device, and determine the new target in the third detection area;

[0028] Obtain the sixth position information of the new target, determine the second detection strategy corresponding to the new target based on the sixth position information, and detect the new target based on the second detection strategy.

[0029] In an optional implementation, the method further includes:

[0030] If the dispersion is greater than the dispersion threshold, then the target image acquisition device that is closest to the image acquisition device is determined;

[0031] The target image acquisition device is determined to be the second image acquisition device corresponding to the new target;

[0032] Determine the fourth detection area corresponding to the second image acquisition device, and determine the new target in the fourth detection area;

[0033] Obtain the seventh position information of the new target, determine the third detection strategy corresponding to the new target based on the seventh position information, and detect the new target based on the third detection strategy.

[0034] In an optional implementation, determining the detection strategy corresponding to the target based on the second location information, and detecting the target based on the detection strategy, includes:

[0035] If the second location information is within the detection line of the second detection area, then the image data or video of the target will be sent to the monitoring platform;

[0036] If the monitoring platform responds to the image data or video of the target by sending a mobile detection device invocation command, it invokes the mobile detection device to detect the target.

[0037] Secondly, embodiments of this application provide a target detection device applied to an edge computing server, the device comprising:

[0038] The first location information acquisition module is used to acquire the first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device detecting the target within the first detection area corresponding to the electromagnetic wave device;

[0039] An image acquisition device determination module is used to determine the image acquisition device corresponding to the target based on the first location information;

[0040] The target determination module is used to determine the second detection area corresponding to the image acquisition device and to determine the target in the second detection area;

[0041] The target detection module is used to acquire the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy.

[0042] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory, wherein the processor is configured to execute a target detection program stored in the memory to implement the target detection method described in any one of the first aspects.

[0043] Fourthly, embodiments of this application provide a storage medium storing one or more programs, which can be executed by one or more processors to implement the target detection method described in any one aspect.

[0044] The technical solution provided in this application provides the following steps: First, obtain the first location information of a target, which includes information obtained by an electromagnetic wave device detecting a target within a first detection area corresponding to the electromagnetic wave device; determine an image acquisition device corresponding to the target based on the first location information; determine a second detection area corresponding to the image acquisition device; determine the target within the second detection area; obtain second location information of the target; determine a detection strategy corresponding to the target based on the second location information; and detect the target based on the detection strategy. This allows for the detection of a target by an electromagnetic wave device, the determination of the corresponding image acquisition device, and the tracking and detection of the target using the image acquisition device, making the process more intelligent and saving manpower. Attached Figure Description

[0045] Figure 1 A schematic diagram illustrating the implementation process of a target detection method provided in this application embodiment;

[0046] Figure 2 A schematic diagram illustrating the implementation process of another target detection method provided in this application embodiment;

[0047] Figure 3A schematic diagram illustrating the implementation process of another target detection method provided in this application embodiment;

[0048] Figure 4 A schematic diagram illustrating the implementation process of a novel target detection method provided in this application embodiment;

[0049] Figure 5 A schematic diagram illustrating the implementation process of another novel target detection method provided in this application embodiment;

[0050] Figure 6 A schematic diagram illustrating the implementation process of another target detection method provided in this application embodiment;

[0051] Figure 7 A schematic diagram of a detection area provided in an embodiment of this application;

[0052] Figure 8 This is a schematic diagram of the structure of a target detection device provided in an embodiment of this application;

[0053] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] In some open and remote scenarios, it is necessary to detect incoming vehicles and personnel. When using image acquisition equipment for detection, it is difficult for the equipment to locate the target. Furthermore, when vehicles and personnel are disguised or located in the blind spot of the image acquisition equipment, the equipment cannot detect the target, thus posing a certain danger. Using electromagnetic wave equipment to detect targets and then calling the image acquisition equipment to track them requires manual designation of the detected target before the image acquisition equipment can capture an image. The operator then determines whether to take further defensive measures based on the captured image, which is not intelligent enough.

[0056] This application provides a system comprising a front-end device, a control subsystem, and a display subsystem. The front-end device consists of one or more electromagnetic wave devices and an image acquisition device. The control subsystem includes an edge computing server, and the display subsystem includes a monitoring platform. In this system, after acquiring a target detected by the electromagnetic wave device, the corresponding image acquisition device is automatically determined, and the image acquisition device is invoked to track and detect the target.

[0057] First, electromagnetic wave devices and image acquisition devices are deployed in the scene requiring security detection. Since the detection range of the electromagnetic wave devices is larger than the image acquisition range of the image acquisition devices, one electromagnetic wave device corresponds to at least one image acquisition device, ensuring that after the electromagnetic wave devices detect a target, a suitable image acquisition device can track and detect the target. In this system, the electromagnetic wave devices guide the image acquisition devices to conduct comprehensive monitoring of the scene requiring security detection, without being limited by the visible area of ​​the image acquisition devices. The following embodiments provide a detailed description of the solution of this application.

[0058] Figure 1 This is a schematic diagram illustrating the implementation process of a target detection method provided in this application embodiment, applied to an edge computing server. The method may include the following steps:

[0059] S101: Obtain the first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device from detecting the target within the first detection area corresponding to the electromagnetic wave device.

[0060] In this embodiment, the edge computing server reads parameters corresponding to the electromagnetic wave device. The electromagnetic wave device includes, but is not limited to, radar. When the electromagnetic wave device is radar, the edge computing server obtains parameters such as the radar's monitoring range and radiation angle range. For example, the edge computing server obtains a radar monitoring range of 6km and a radiation angle range of 72.5°, which is not limited in this application. After reading the parameters corresponding to the electromagnetic wave device, the edge computing server can determine the first detection area corresponding to the electromagnetic wave device based on these parameters, control the electromagnetic wave device to detect the first detection area, and when the electromagnetic wave device detects a target, obtain the first location information of the target detected by the electromagnetic wave device.

[0061] In the embodiments of this application, the target varies depending on the scenario requiring security detection. Common targets include, but are not limited to, personnel and vehicles, and this application does not limit them. The first location information includes all information corresponding to the target detected by the electromagnetic wave device, including but not limited to the distance between the target and the electromagnetic wave device, the direction of the target relative to the electromagnetic wave device, and the target's moving speed, and this application does not limit it.

[0062] S102: Determine the image acquisition device corresponding to the target based on the first location information.

[0063] In this embodiment of the application, an electromagnetic wave device corresponds to at least one image acquisition device. The edge computing server can obtain the positional relationship between the electromagnetic wave device and its corresponding image acquisition device. Based on the first position information of the target detected by the electromagnetic wave device and the positional relationship between the electromagnetic wave device and its corresponding image acquisition device, the image acquisition device corresponding to the target can be determined.

[0064] S103: Determine the second detection area corresponding to the image acquisition device, and determine the target in the second detection area.

[0065] In this embodiment, the edge computing server reads the parameters corresponding to the electromagnetic wave device and simultaneously reads the parameters corresponding to all image acquisition devices. These image acquisition devices include, but are not limited to, PTZ cameras. When the image acquisition device is a PTZ camera, the edge computing server acquires parameters such as the horizontal and vertical rotation angle ranges and focal length variation ranges of the PTZ camera. For example, the edge computing server acquires parameters for the PTZ camera such as a horizontal rotation angle range of 0° to 360°, a vertical rotation angle range of -15° to 90°, and a focal length variation range of 6-192mm. This application does not limit these parameters. After reading the parameters corresponding to the image acquisition devices, the edge computing server can determine the second detection area corresponding to each image acquisition device based on these parameters.

[0066] The above process identifies the target in the second detection area, that is, the target detected by the electromagnetic wave device, and locks onto and tracks the target. Specifically, an image acquisition device can be used to acquire images of the target in the second detection area. The acquired images are then input into a preset target recognition model, which identifies the target, thereby determining the target in the second detection area.

[0067] In this embodiment of the application, the target recognition model is obtained in the following ways:

[0068] 1. Obtain sample image data in a preset scene, wherein the sample image data includes sample targets, and the sample targets have been labeled.

[0069] In this application embodiment, the preset scenarios include general scenarios and scenarios requiring security detection. General scenarios include, but are not limited to, highways, shopping malls, and parks. Scenarios requiring security detection include scenarios requiring security detection as well as scenarios similar to those requiring security detection. For example, if the scenario requiring security detection is a school, sample images from that school and several other school scenarios can be collected. It should be noted that the acquired sample image data for the preset scenarios can include sample image data from preset scenarios under different time periods, different weather conditions, different seasons, and other environments.

[0070] In this embodiment, the acquired sample image data is manually annotated to mark the target objects in the sample image data. For example, when the target objects are people and vehicles, all target objects in the sample image data are marked. It can be understood that people and vehicles in a concealed or semi-concealed state should also be marked.

[0071] It should be noted that when the sample target is a person and a vehicle, the sample image data may contain only sample image data containing people, or only sample image data containing vehicles, or sample image data containing both people and vehicles. This application does not limit this.

[0072] In this embodiment of the application, the sample image data can also be obtained by first obtaining sample video data, and then performing frame extraction processing on the sample video data to obtain sample image data.

[0073] 2. Process the sample image data to obtain target sample image data; wherein, the processing methods for the sample image data include at least one or more of the following: appearance enhancement processing, geometric enhancement processing, and virtual sample enhancement processing.

[0074] In this embodiment, the acquired sample image data is enhanced to obtain target sample image data, thereby expanding the sample image dataset. This includes performing appearance enhancement processing on the sample image data to obtain target sample image data, performing geometric enhancement processing on the sample image data to obtain target sample image data, and further performing virtual sample enhancement on the sample image data to obtain target sample image data.

[0075] Appearance enhancement and / or geometric enhancement increase the diversity of sample image data through data augmentation, including but not limited to: JPEG (Joint Photographic Experts Group) compression, brightness and contrast enhancement, Gamma brightness enhancement, Gaussian blur, motion blur, Gaussian noise, and rotation at random angles (blank areas are filled with the average pixels of the entire image). Virtual sample enhancement increases the diversity of sample image data through image synthesis, including but not limited to: synthesizing sample image data and constructing various types of targets to add to sample image data.

[0076] 3. Prune and / or reduce channels in the initial detection model to determine the hyperparameters in the processed initial detection model. Train the processed initial detection model based on the target sample image data to adjust the hyperparameters and obtain the target detection model.

[0077] In this embodiment, a YOLO V3 neural network is used to train the detection model. First, the YOLO V3 neural network is pruned and / or its channels are reduced; specifically, the number of channels in each convolutional layer is halved to obtain an initial detection model. Then, the hyperparameters in the initial detection model are determined through optimal selection. Optimal selection of hyperparameters includes obtaining an optimal solution based on existing training samples using clustering algorithms or prior experience. The target sample image data is then input into the processed initial detection model for training to adjust the hyperparameters, thereby obtaining the target detection model.

[0078] S104: Obtain the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy.

[0079] In this embodiment of the application, after determining the target in the second detection area, the target is tracked by an image acquisition device to obtain the second position information of the target. The detection strategy corresponding to the target is determined based on the second position information of the target, and the target is detected according to the detection strategy.

[0080] In this embodiment, based on the scenario requiring security detection, two detection lines are pre-marked in the second detection area corresponding to the image acquisition device, such as... Figure 7 As shown, the area outside the first detection line is a no-concern area, and the area inside the second detection line is a prohibited area for the target. Different detection strategies apply to targets located inside the first detection line, between the first and second detection lines, and inside the second detection line.

[0081] 1. If the target's location information is inside the first detection line of the detection area, the first warning information is triggered, and the target is tracked.

[0082] 2. If the target's location information is located between the first and second detection lines of the detection area, the target's location and shape information are acquired using an image acquisition device. It is then determined whether the target's location and shape information have changed within a preset time. If the target changes within the preset time, the tracking of the target continues; if the target does not change within the preset time, the tracking of the target ends.

[0083] 3. If the target's location information is located between the first and second detection lines in the detection area, and the distance between the target's location information and the second detection line is less than a preset distance, such as 200 meters, then the target is identified to determine whether it is a legitimate target in the target database. Specifically, when the target is a person, facial recognition technology can be used to determine whether the target is a legitimate person; when the target is a vehicle, license plate recognition technology can be used to determine whether the license plate number is legitimate. If the target is not a legitimate target, a second warning message is triggered; if the target is a legitimate target, the tracking of the target ends.

[0084] 4. If the target's location information is inside the second detection line of the detection area, the target's image data or video will be sent to the monitoring platform. The specific procedures thereafter can be found in S604 and S605, and will not be repeated here.

[0085] It should be noted that the level of the second warning information is higher than that of the first warning information, and it can be expressed through different forms of warning information. For example, when the warning information is an alarm sound, the sound of the second warning information can be set to be higher than that of the first warning information. This application does not limit this.

[0086] Based on the above description of the technical solutions provided in the embodiments of this application, this application uses electromagnetic wave devices and image acquisition devices to collaboratively track and detect targets. After obtaining the first position information of the target detected by the electromagnetic wave devices, the image acquisition device corresponding to the target is determined based on the first position information. The image acquisition device is then invoked to identify and track the target. No operator intervention is required, making the target detection process more intelligent and saving manpower. Furthermore, there is no need to wait for the operator to issue the next detection instruction. The corresponding detection strategy is automatically adopted to detect the target based on the second position information of the target, improving real-time performance.

[0087] The following is based on Figure 2 The steps shown detail how to determine the corresponding image acquisition device after the electromagnetic wave device detects a target. Figure 2This is a schematic diagram illustrating the implementation process of another target detection method provided in this application embodiment. The method may include the following steps:

[0088] S201: Obtain the first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device from detecting the target within the first detection area corresponding to the electromagnetic wave device.

[0089] In the embodiments of this application, S201 has been described in detail in S101, and will not be repeated here.

[0090] S202: For any image acquisition device corresponding to the electromagnetic wave device, determine the device location information of the image acquisition device in the first detection area.

[0091] In this embodiment, the electromagnetic wave device corresponds to at least one image acquisition device. For any image acquisition device corresponding to the electromagnetic wave device, the device position information of the image acquisition device in the first detection area is determined. Specifically, the device position information includes, but is not limited to, the distance between the image acquisition device and the electromagnetic wave device, and its direction relative to the electromagnetic wave device, etc., which are not limited in this application.

[0092] S203: Determine the distance between the target and the image acquisition device based on the first location information and the device location information.

[0093] In the embodiments of this application, by Figure 1 It is known that the device location information includes the distance between the image acquisition device and the electromagnetic wave device, and the direction relative to the electromagnetic wave device, etc. The first location information includes the distance between the target and the electromagnetic wave device, and the direction relative to the electromagnetic wave device, etc. Therefore, the distance between the target and the image acquisition device can be determined based on the first location information and the device location information.

[0094] S204: Determine the image acquisition device with the smallest distance from the target as the image acquisition device corresponding to the target.

[0095] In this embodiment of the application, the distance between the target and all image acquisition devices corresponding to the electromagnetic wave device is determined, and the image acquisition device with the smallest distance from the target is determined as the image acquisition device corresponding to the target.

[0096] S205: Determine the second detection area corresponding to the image acquisition device, and determine the target in the second detection area.

[0097] S206: Obtain the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy.

[0098] In the embodiments of this application, S205 and S206 have been described in detail in S103 and S104, and will not be repeated here.

[0099] Based on the above description of the technical solutions provided in the embodiments of this application, this application uses an electromagnetic wave device as a reference point. The distance between the target and the image acquisition device is determined by the first position information of the target relative to the electromagnetic wave device and the device position information of the image acquisition device relative to the electromagnetic wave device. This determines the image acquisition device closest to the target, and the image acquisition device closest to the target is called to identify and track the target. The acquired image is clearer, and the tracking results are more accurate and reliable.

[0100] Figure 3 This is a schematic diagram illustrating the implementation process of another target detection method provided in this application. The method may include the following steps:

[0101] S301: Obtain the first position information of the target, wherein the first position information includes information obtained by the electromagnetic wave device from detecting the target within the first detection area corresponding to the electromagnetic wave device, and the first position information is the position information of the target in the first coordinate system corresponding to the electromagnetic wave device.

[0102] In this embodiment of the application, the first position information is obtained by the electromagnetic wave device detecting the target within the first detection area corresponding to the electromagnetic wave device. In the edge computing server, a first coordinate system corresponding to the electromagnetic wave device is established based on the first detection area corresponding to the electromagnetic wave device. The first position information is the position information of the target in the first coordinate system corresponding to the electromagnetic wave device. At this time, the first position information includes the first coordinate of the target in the first coordinate system.

[0103] S302: Determine the image acquisition device corresponding to the target based on the first location information.

[0104] In the embodiments of this application, S301 and S302 have been described in detail in S101 and S102, and will not be repeated here.

[0105] S303: Obtain the position transformation matrix between the electromagnetic wave device and the image acquisition device.

[0106] S304: Based on the position transformation matrix, convert the first position information into the third position information of the target in the second coordinate system corresponding to the image acquisition device.

[0107] S305: Determine the shooting angle corresponding to the image acquisition device based on the third position information.

[0108] S306: Determine the distance between the target and the image acquisition device, and determine the corresponding shooting focal length of the image acquisition device based on the distance.

[0109] S307: Image acquisition device that adjusts according to shooting angle and focal length.

[0110] The following provides a unified explanation of S303 to S307:

[0111] In this embodiment, since the detection range and deployment location of the electromagnetic wave device and the image acquisition device are different, the first position information of the target in the first coordinate system corresponding to the electromagnetic wave device and the second position coordinate in the second coordinate system corresponding to the image acquisition device are different. After reading the parameters of the electromagnetic wave device and the image acquisition device, the edge computing server calculates the position transformation matrix between the electromagnetic wave device and the image acquisition device based on their relative positions.

[0112] Based on the position transformation matrix, the first position information is converted into the third position information of the target in the second coordinate system corresponding to the image acquisition device. The shooting angle corresponding to the image acquisition device is determined based on the third position information; specifically, the shooting center of the image acquisition device is determined, and the shooting angle corresponding to the image acquisition device when the target is located at the shooting center is determined based on the third position information. The distance between the target and the image acquisition device is determined based on the third position information, and the shooting focal length corresponding to the image acquisition device is determined based on the distance. The image acquisition device is adjusted according to the determined shooting angle and focal length.

[0113] S308: Determine the second detection area corresponding to the image acquisition device, and determine the target in the second detection area.

[0114] S309: Obtain the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy.

[0115] In the embodiments of this application, S308 and S309 have been described in detail in S103 and S104, and will not be repeated here.

[0116] Based on the above description of the technical solutions provided in the embodiments of this application, before determining the second detection area corresponding to the image acquisition device, the shooting angle of the image acquisition device is adjusted so that the target is located at the shooting center of the image acquisition device. The shooting focal length corresponding to the image acquisition device is determined according to the distance between the target and the image acquisition device, and the shooting focal length of the image acquisition device is adjusted so that the image acquisition device can identify and track the target in the best shooting state.

[0117] The above describes the situation where an electromagnetic wave device detects one target. In practical applications, an electromagnetic wave device may detect multiple targets within a certain period of time. When an electromagnetic wave device detects multiple targets within a preset time period, the first target detected by the electromagnetic wave device is processed as described above, and the image acquisition device corresponding to the first target is determined. After the first target is tracked by the image acquisition device, the new targets detected after the electromagnetic wave device detects the first target are processed as follows.

[0118] Figure 4 This is a schematic diagram illustrating the implementation process of a novel target detection method provided in this application embodiment. The method may include the following steps:

[0119] S401: If the electromagnetic wave device detects the fourth position information of N new targets other than the above-mentioned targets within a preset time period, then for any new target, determine the dispersion between the new target and the above-mentioned targets, where N is an integer.

[0120] In this embodiment, a preset time period is used, for example, 1 hour. Within 1 hour, the electromagnetic wave device detects N new targets besides the first target mentioned above. For each new target detected, the edge computing server acquires the fourth location information of the new target in real time. This fourth location information includes targets detected by the electromagnetic wave device within the first detection area corresponding to the electromagnetic wave device. For any new target, the dispersion between the new target and previously detected targets is calculated, i.e., the degree to which the new target deviates from previously detected targets. Specifically, the sum of the squared differences of the distances between the new target and each previously detected target can be calculated; this application does not limit this calculation. It should be noted that the targets previously detected include targets tracked and detected using the image acquisition device corresponding to the first target.

[0121] S402: Obtain the discreteness threshold corresponding to the above image acquisition device.

[0122] In this embodiment of the application, the image acquisition device is the image acquisition device corresponding to the first target, and different discrete thresholds are set according to different parameters of the image acquisition device.

[0123] S403: If the dispersion is less than or equal to the dispersion threshold, then determine the second detection area corresponding to the above image acquisition device, and determine the new target in the second detection area.

[0124] S404: Obtain the fifth position information of the new target, determine the first detection strategy corresponding to the new target based on the fifth position information, and detect the new target based on the first detection strategy.

[0125] The following provides a unified explanation of S403 and S404:

[0126] In this embodiment of the application, if the dispersion is less than or equal to the dispersion threshold, the new target is relatively close to the previously detected target. The image acquisition device corresponding to the first target can simultaneously track and detect the new target and the previously detected target.

[0127] In this embodiment of the application, before determining the second detection area corresponding to the above-mentioned image acquisition device, it is necessary to adjust the image acquisition device so that the central axis of the image acquisition device is located on the angle bisector of the maximum angle formed by the lines connecting each target and the image acquisition device.

[0128] In this embodiment of the application, "determining the second detection area corresponding to the above-mentioned image acquisition device, determining the new target in the second detection area, obtaining the fifth position information of the new target, determining the first detection strategy corresponding to the new target based on the fifth position information, and detecting the new target based on the first detection strategy" is similar to the description of S103 and S104 above, and will not be repeated here.

[0129] S405: If the dispersion is greater than the dispersion threshold, then based on the fourth position information of the new target, determine the image acquisition device closest to the new target as the first image acquisition device corresponding to the new target.

[0130] In this embodiment, if the dispersion is greater than the dispersion threshold, the new target is relatively dispersed from the previously detected targets and cannot be tracked and detected by the image acquisition device corresponding to the first target. Therefore, the image acquisition device closest to the new target is determined as the first image acquisition device corresponding to the new target based on the fourth position information of the new target.

[0131] S406: Determine the third detection area corresponding to the first image acquisition device, and determine the new target in the third detection area.

[0132] S407: Obtain the sixth position information of the new target, determine the second detection strategy corresponding to the new target based on the sixth position information, and detect the new target based on the second detection strategy.

[0133] The following provides a unified explanation of S406 and S407:

[0134] In this embodiment, the first image acquisition device needs to be adjusted before steps S406 and S407. The specific adjustment method is the same as... Figure 3 The explanations for S406, S407, S103, and S104 are similar and will not be repeated here.

[0135] Figure 5This is a schematic diagram illustrating the implementation process of another novel target detection method provided in this application embodiment. The method may include the following steps:

[0136] S501: If the electromagnetic wave device detects the fourth position information of N new targets other than the above targets within a preset time period, then for any new target, determine the dispersion between the new target and the above targets, where N is an integer.

[0137] S502: Obtain the discreteness threshold corresponding to the above image acquisition device.

[0138] S503: If the dispersion is less than or equal to the dispersion threshold, then determine the second detection area corresponding to the above image acquisition device, and determine the new target in the second detection area.

[0139] S504: Obtain the fifth position information of the new target, determine the first detection strategy corresponding to the new target based on the fifth position information, and detect the new target based on the first detection strategy.

[0140] In the embodiments of this application, S501 to S504 have been described in detail in S401 to S404, and will not be repeated here.

[0141] S505: If the dispersion is greater than the dispersion threshold, then determine the target image acquisition device that is closest to the image acquisition device.

[0142] In this embodiment, if the dispersion threshold is greater than the dispersion threshold, the new target is relatively dispersed from the previously detected targets and cannot be tracked and detected by the image acquisition device corresponding to the first target. Therefore, the target image acquisition device that is closest to the image acquisition device corresponding to the first target is determined. Specifically, this can be determined based on the distance between the various image acquisition devices when they are deployed; this application does not limit this.

[0143] S506: Determine the target image acquisition device as the second image acquisition device corresponding to the new target.

[0144] In this embodiment of the application, the target image acquisition device determined above is identified as the second image acquisition device corresponding to the new target, and the new target is tracked and detected by the second image acquisition device.

[0145] S507: Determine the fourth detection area corresponding to the second image acquisition device, and determine the new target in the fourth detection area.

[0146] S508: Obtain the seventh position information of the new target, determine the third detection strategy corresponding to the new target based on the seventh position information, and detect the new target based on the third detection strategy.

[0147] In the embodiments of this application, the descriptions of S507 and S508 and S406 and S407 are similar and will not be repeated here.

[0148] Based on the above description of the technical solutions provided in the embodiments of this application, this application calculates the discreteness of all targets other than the first target detected by the electromagnetic wave device within a preset time period to determine whether to call other image acquisition devices for tracking and detection, thereby achieving the highest tracking and detection effect. When the discreteness is greater than the discreteness threshold, Figure 4 The method shown uses the image acquisition device closest to the new target to track and detect the new target, achieving the best tracking and detection effect; Figure 5 The method shown uses the image acquisition device closest to the image acquisition device corresponding to the first target to track and detect the new target, eliminating the need to calculate the distance between the target and each image acquisition device, thus improving tracking and detection efficiency.

[0149] Figure 6 This is a schematic diagram illustrating the implementation process of another target detection method provided in this application embodiment. The method may include the following steps:

[0150] S601: Obtain the first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device from detecting the target within the first detection area corresponding to the electromagnetic wave device.

[0151] S602: Determine the image acquisition device corresponding to the target based on the first location information.

[0152] S603: Determine the second detection area corresponding to the image acquisition device, and determine the target in the second detection area.

[0153] In the embodiments of this application, S601 to S603 have been described in detail in S101 to S103, and will not be repeated here.

[0154] S604: Obtain the second location information of the target. If the second location information is within the detection line of the second detection area, send the image data or video of the target to the monitoring platform.

[0155] In this embodiment of the application, the second location information of the target is obtained. If the second location information is inside the detection line of the second detection area (see details...), then... Figure 7 If the detection lines can include a first detection line and a second detection line, the edge computing server will send the target's image data or video to the monitoring platform, and the monitoring platform will play the target's motion trajectory and motion video in real time.

[0156] S605: If the monitoring platform responds to the target's image data or video by sending a motion detection device call command, then the motion detection device will be called to detect the target.

[0157] In this embodiment, the inspector views the target through a monitoring platform and takes further action. Specifically, the monitoring platform can send a mobile detection device invocation command to the edge computing server. Upon receiving the command, the edge computing server invokes a mobile detection device, such as a drone, though this application does not limit this. The edge computing server can invoke the mobile detection device to track the target in real time and capture real-time image data or video of the target, then send the real-time image data or video of the target to the monitoring platform.

[0158] Based on the above description of the technical solutions provided in the embodiments of this application, when the target is inside the detection line, the target can be determined to be a suspicious target and further measures need to be taken. The target's image data or video is transmitted to the monitoring platform, and the mobile detection device call instruction sent by the monitoring platform is obtained. The mobile detection device is called to track and detect the target, avoiding the disadvantage that the image acquisition device cannot move and has blind spots.

[0159] Figure 8 This is a schematic diagram of the structure of a target detection device provided in an embodiment of this application. The device includes: a first location information acquisition module 801, an image acquisition device determination module 802, a target determination module 803, and a target detection module 804.

[0160] The first location information acquisition module 801 is used to acquire the first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device detecting the target within the first detection area corresponding to the electromagnetic wave device;

[0161] The image acquisition device determination module 802 is used to determine the image acquisition device corresponding to the target based on the first location information;

[0162] The target determination module 803 is used to determine the second detection area corresponding to the image acquisition device and to determine the target in the second detection area;

[0163] The target detection module 804 is used to acquire the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy.

[0164] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9The illustrated electronic device 900 includes at least one processor 901, a memory 902, at least one network interface 904, and a user interface 903. The various components in the electronic device 900 are coupled together via a bus system 905. It is understood that the bus system 905 is used to implement communication between these components. In addition to a data bus, the bus system 905 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 9 The general labeled all buses as Bus System 905.

[0165] The user interface 903 may include a display, keyboard or clicking device (e.g., mouse, trackball), touchpad or touch screen, etc.

[0166] It is understood that the memory 902 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 902 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0167] In some implementations, memory 902 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 9021 and application program 9022.

[0168] The operating system 9021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 9022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this application embodiment can be included in the application program 9022.

[0169] In this embodiment, by calling a program or instruction stored in memory 902, specifically a program or instruction stored in application program 9022, processor 901 executes the method steps provided in each method embodiment, including, for example:

[0170] The method involves: acquiring first location information of a target, wherein the first location information includes information obtained by an electromagnetic wave device detecting a target within a first detection area corresponding to the electromagnetic wave device; determining an image acquisition device corresponding to the target based on the first location information; determining a second detection area corresponding to the image acquisition device; determining the target within the second detection area; acquiring second location information of the target; determining a detection strategy corresponding to the target based on the second location information; and detecting the target based on the detection strategy.

[0171] The methods disclosed in the embodiments of this application can be applied to or implemented by processor 901. Processor 901 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware or by instructions in the form of software in processor 901. The processor 901 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or can be executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 902. Processor 901 reads the information in memory 902 and, in conjunction with its hardware, completes the steps of the above method.

[0172] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions of this application, or combinations thereof.

[0173] For software implementation, the techniques described herein can be implemented through units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented within the processor or external to the processor.

[0174] The electronic device provided in this embodiment may be as follows: Figure 9 The electronic device shown can perform the following: Figures 1-6 All steps of the target detection method are implemented to achieve... Figures 1-6 For details on the technical effectiveness of the target detection method, please refer to [link / reference]. Figures 1-6 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0175] This application also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; it may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and it may also include combinations of the above types of memory.

[0176] When one or more programs in the storage medium can be executed by one or more processors to implement the target detection method described above, executed on the electronic device side, the processor executes the target detection program stored in the memory to implement the following steps of the target detection method executed on the electronic device side:

[0177] The method involves: acquiring first location information of a target, wherein the first location information includes information obtained by an electromagnetic wave device detecting a target within a first detection area corresponding to the electromagnetic wave device; determining an image acquisition device corresponding to the target based on the first location information; determining a second detection area corresponding to the image acquisition device; determining the target within the second detection area; acquiring second location information of the target; determining a detection strategy corresponding to the target based on the second location information; and detecting the target based on the detection strategy.

[0178] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0179] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0180] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above description is only a specific embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A target detection method, characterized in that, Applied to edge computing servers, the method includes: Acquire first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device detecting the target within a first detection area corresponding to the electromagnetic wave device; The image acquisition device corresponding to the target is determined based on the first location information; Determine the second detection area corresponding to the image acquisition device, and determine the target in the second detection area; Obtain the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy; If the electromagnetic wave device detects the fourth location information of N new targets other than the target within a preset time period, then for any new target, the dispersion between the new target and the target is determined, where N is an integer; Obtain the discreteness threshold corresponding to the image acquisition device; If the dispersion is greater than the dispersion threshold, then the target image acquisition device that is closest to the image acquisition device is determined; The target image acquisition device is determined to be the second image acquisition device corresponding to the new target; Determine the fourth detection area corresponding to the second image acquisition device, and determine the new target in the fourth detection area; Obtain the seventh position information of the new target, determine the third detection strategy corresponding to the new target based on the seventh position information, and detect the new target based on the third detection strategy.

2. The method according to claim 1, characterized in that, The electromagnetic wave device corresponds to at least one image acquisition device, and the step of determining the image acquisition device corresponding to the target based on the first location information includes: For any image acquisition device corresponding to the electromagnetic wave device, determine the device location information of the image acquisition device in the first detection area; The distance between the target and the image acquisition device is determined based on the first location information and the device location information; The image acquisition device with the smallest distance from the target is determined as the image acquisition device corresponding to the target.

3. The method according to claim 1, characterized in that, The first location information is the location information of the target in the first coordinate system corresponding to the electromagnetic wave device. Before determining the second detection area corresponding to the image acquisition device, the method further includes: Obtain the position transformation matrix between the electromagnetic wave device and the image acquisition device; According to the position transformation matrix, the first position information is converted into the third position information of the target in the second coordinate system corresponding to the image acquisition device; The shooting angle corresponding to the image acquisition device is determined based on the third location information; Determine the distance between the target and the image acquisition device, and determine the shooting focal length corresponding to the image acquisition device based on the distance; The image acquisition device is adjusted according to the shooting angle and the shooting focal length.

4. The method according to claim 1, characterized in that, The method further includes: If the dispersion is less than or equal to the dispersion threshold, then the second detection area corresponding to the image acquisition device is determined, and the new target in the second detection area is determined; Obtain the fifth location information of the new target, determine the first detection strategy corresponding to the new target based on the fifth location information, and detect the new target based on the first detection strategy.

5. The method according to claim 4, characterized in that, The method further includes: If the dispersion is greater than the dispersion threshold, then based on the fourth location information of the new target, the image acquisition device closest to the new target is determined as the first image acquisition device corresponding to the new target; Determine the third detection area corresponding to the first image acquisition device, and determine the new target in the third detection area; Obtain the sixth position information of the new target, determine the second detection strategy corresponding to the new target based on the sixth position information, and detect the new target based on the second detection strategy.

6. The method according to claim 1, characterized in that, The step of determining the detection strategy corresponding to the target based on the second location information, and detecting the target based on the detection strategy, includes: If the second location information is within the detection line of the second detection area, then the image data or video of the target will be sent to the monitoring platform; If the monitoring platform responds to the image data or video of the target by sending a mobile detection device invocation command, it invokes the mobile detection device to detect the target.

7. A target detection device, characterized in that, The device, applied to an edge computing server, includes: The first location information acquisition module is used to acquire the first location information of the target, wherein the first location information includes information obtained by the electromagnetic wave device detecting the target within the first detection area corresponding to the electromagnetic wave device; An image acquisition device determination module is used to determine the image acquisition device corresponding to the target based on the first location information; The target determination module is used to determine the second detection area corresponding to the image acquisition device and to determine the target in the second detection area; The target detection module is used to acquire the second location information of the target, determine the detection strategy corresponding to the target based on the second location information, and detect the target based on the detection strategy. If the electromagnetic wave device detects the fourth location information of N new targets other than the target within a preset time period, then for any new target, the dispersion between the new target and the target is determined, where N is an integer; Obtain the discreteness threshold corresponding to the image acquisition device; If the dispersion is greater than the dispersion threshold, then the target image acquisition device that is closest to the image acquisition device is determined; The target image acquisition device is determined to be the second image acquisition device corresponding to the new target; Determine the fourth detection area corresponding to the second image acquisition device, and determine the new target in the fourth detection area; Obtain the seventh position information of the new target, determine the third detection strategy corresponding to the new target based on the seventh position information, and detect the new target based on the third detection strategy.

8. An electronic device, characterized in that, include: A processor and a memory, the processor being configured to execute a target detection program stored in the memory to implement the target detection method according to any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the target detection method according to any one of claims 1 to 6.

Images