Target reporting method and device and storage medium

Abstract

The invention discloses a target reporting method and device and a storage medium, which can perform accurate and non-redundant target reporting so as to comprehensively improve the perception ability of a ship to a shore-based environment and the information collaboration efficiency. The target reporting method comprises the following steps: acquiring current frame data containing a plurality of targets; wherein the current frame data comprises a target category, an identification number and distance information; sorting the targets according to the categories of the targets, preset category priorities, the identification numbers and the distance information to obtain a target list; selecting the first target in the target list as a current tracking target; and when the current tracking target is a first type of target, adding corresponding priorities to other types of targets except the current tracking target according to a preset weight, and reporting and storing the identification number of the current tracking target in an identified target list.

Description

Technical Field

[0001] This application relates to the field of target processing technology, specifically to a target reporting method, apparatus, and storage medium. Background Technology

[0002] In applications such as marine transportation and near-shore operations, vessels navigating on the water or sea need to continuously and effectively monitor, identify, and report information on land and near-shore targets along their coastline. Timely and accurate reporting of this target information to shore-based command centers or nearby friendly vessels is crucial for ensuring navigational safety, executing monitoring tasks, and achieving situational coordination. However, existing technologies, especially in scenarios where mobile vessel platforms are probing complex shore-based environments, have significant shortcomings in target identification and reporting schemes. Traditional reporting schemes suffer from incomplete target type identification and excessive target duplication, leading to information redundancy and channel congestion. Summary of the Invention

[0003] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide a target reporting method, apparatus, and storage medium, which can perform accurate and non-redundant target reporting, thereby comprehensively improving the ship's perception capability of the shore-based environment and information collaboration efficiency.

[0004] According to a first aspect of this application, a target reporting method is provided, comprising: acquiring current frame data containing multiple targets; wherein the current frame data includes the target's category, identification number, and distance information; sorting the targets according to the target's category, a preset category priority, the identification number, and the distance information to obtain a target list; selecting the first target in the target list as the current tracking target; when the current tracking target is a first category target, increasing the priority of other categories of targets besides the current tracking target according to a preset weight, and reporting and storing the identification number of the current tracking target in the identified target list.

[0005] As one possible implementation, the targets are sorted according to their category, preset category priority, identification number, and distance information to obtain a target list, including: performing a filtering operation on the multiple targets sequentially to obtain candidate targets; and sorting the candidate targets according to their category, preset category priority, and distance information to obtain a target list.

[0006] As one possible implementation, the filtering operation includes: filtering targets that are not in a specified category based on a preset list of specified target categories; filtering targets identified in the list of identified targets based on the list of identified targets; and filtering targets whose volume is smaller than the preset volume and whose distance is greater than the effective distance range based on a preset effective distance range and a preset volume.

[0007] As one possible implementation, the targets are sorted according to their category, preset category priority, identification number, and distance information to obtain a target list. This includes: when the number of target categories is not less than the preset number of target categories, the targets are sorted according to the preset category priority to obtain a first target list; when the number of target categories is less than the preset number of target categories, or when the first target list has been obtained, targets of the same category are sorted in ascending order of image center offset to obtain a second target list; wherein, selecting the first target in the target list as the current tracking target includes: selecting the first target in the second target list as the current tracking target.

[0008] As one possible implementation, after selecting the first target in the target list as the current tracking target, the target reporting method further includes: when the current tracking target is within the recognition box, measuring the distance of the current tracking target according to a preset frequency and a preset period to obtain multiple ranging results; and calculating the real-time distance of the current tracking target based on the multiple ranging results.

[0009] As one possible implementation, the target reporting method further includes: when measuring the distance of the currently tracked target within the preset period, if the currently tracked target is not located within the identification box and the duration of the period when it is not located within the identification box is greater than a preset duration, the category priority of the currently tracked target is set to 0, and the priority of other categories of targets is increased by a preset value.

[0010] As one possible implementation, the current tracking target includes people, vehicles, and ships. When the current tracking target is a first category target, corresponding priorities are added to other categories of targets besides the current tracking target according to preset weights. This includes: when the current tracking target is a person, setting the priority of the person to 0, adding a first value to the priority of the vehicle and a second value to the priority of the ship according to preset weights; wherein the first value is greater than the second value; when the current tracking target is a vehicle, setting the priority of the vehicle to 0, adding a third value to the priority of the person and a second value to the priority of the ship according to preset weights; wherein the third value is greater than the second value; when the current tracking target is a ship, setting the priority of the ship to 0, adding a third value to the priority of the person and a first value to the priority of the vehicle according to preset weights; wherein the third value is greater than the first value.

[0011] As one possible implementation, the step of reporting and storing the identification number of the currently tracked target in the list of identified targets includes: when the number of times the identification number of the currently tracked target is reported is greater than a preset number, storing the identification number of the currently tracked target in the list of identified targets.

[0012] According to a second aspect of this application, a target reporting device is provided, comprising: an acquisition module for acquiring current frame data containing multiple targets; wherein the current frame data includes the target's category, identification number, and distance information; a sorting module for sorting the targets according to the target's category, a preset category priority, the identification number, and the distance information to obtain a target list; a selection module for selecting the first target in the target list as the current tracking target; and a reporting module for, when the current tracking target is a first category target, adding corresponding priorities to targets of other categories other than the current tracking target according to a preset weight, and reporting and storing the identification number of the current tracking target in an identified target list.

[0013] According to a third aspect of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the method as described in the first aspect or any implementation thereof.

[0014] The target reporting method, apparatus, and storage medium provided in this application identify targets from the current frame data and sort them according to their type, identification number, and distance information. The first target in the target list is tracked first, and after identification, it is recorded in the identified target list. The priority of other unidentified targets is increased to avoid duplicate identification of the same type of target. Based on this, multiple types of targets can be classified and identified, comprehensively acquiring target information along the coastline, avoiding repetitive identification and reporting, and saving communication and data processing resources. Attached Figure Description

[0015] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 This is a flowchart illustrating a target reporting method provided in an exemplary embodiment of this application.

[0017] Figure 2 This is a schematic diagram of the target reporting device provided in an exemplary embodiment of this application.

[0018] Figure 3 This is a structural diagram of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0019] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0020] Application Overview In today's world of increasingly developed water transportation and more frequent maritime operations, the timely and accurate reporting of target information such as people, vehicles, and ships along the coastline is of paramount importance. For civilian shipping, accurate target reporting allows other vessels to understand their surroundings, plan their routes accordingly, avoid collisions, and ensure the safety of personnel and the smooth transport of goods. In the military field, timely target reporting helps military command grasp the maritime situation, make sound strategic decisions, and improve combat effectiveness. In scenarios such as maritime rescue and marine resource development, accurate target reporting provides crucial information support for rescue operations and resource development work, improving efficiency and success rates. Therefore, developing efficient and accurate maritime target reporting technology has become a key requirement in the current maritime domain.

[0021] Traditional target reporting schemes lack effective target uniqueness identification and association mechanisms in the target identification and reporting process. In actual coastal environments, targets may be dynamically changing, and sensors may be affected by environmental factors (such as waves and weather), leading to repeated identification of the same target. For example, a fishing boat navigating in coastal waters may have slightly different target characteristics captured by the sensor at different times due to wave fluctuations. Traditional target identification algorithms may mistakenly identify it as multiple different targets and report each suspected target. Alternatively, when a target briefly disappears from the sensor's monitoring range and then reappears, traditional schemes may fail to accurately determine that it is the same target, resulting in repeated identification and reporting of target information.

[0022] Even though traditional methods can identify some duplicate targets to a certain extent, the lack of a robust duplicate reporting filtering mechanism still cannot prevent the transmission of duplicate information. During target reporting, a large amount of duplicate information consumes valuable communication resources and increases communication costs. For example, in situations where communication bandwidth is limited at sea, excessive duplicate target reports may prevent the timely transmission of critical information, affecting its timeliness and accuracy. Simultaneously, duplicate information also puts enormous pressure on the receiving end's information processing system, reducing processing efficiency, increasing the workload of operators, and making it difficult for them to quickly and accurately obtain valuable target information.

[0023] In summary, traditional target reporting schemes have serious problems in terms of repeated target identification and reporting, and existing technologies have many shortcomings in dealing with this problem, failing to meet the accuracy and efficiency requirements of modern water transportation and maritime operations for target information reporting.

[0024] Therefore, this application proposes a target reporting method, apparatus, and storage medium, which can effectively solve the problems of repeated target identification and reporting. It is understood that this target reporting method, apparatus, and storage medium can be applied not only to reporting human, vehicle, and ship targets on water or at sea from a ship to the coastline, but also to the identification of other scenarios or objects.

[0025] Exemplary methods To address the problems of traditional target reporting, this application proposes an exemplary target reporting method. Figure 1 This is a flowchart illustrating a target reporting method provided in an exemplary embodiment of this application. Figure 1 For example, first, obtain the current frame data containing multiple targets (see...). Figure 1 (S110). The current frame data includes the target's category, identification number, and distance information. Next, the targets are sorted according to their category, preset category priority, identification number, and distance information to obtain a target list (see S110). Figure 1 (S120). Then, select the first target in the target list as the current tracking target (see S120). Figure 1 (S130). Finally, when the currently tracked target is a first-category target, the corresponding priority is increased for other categories of targets besides the currently tracked target according to the preset weight, and the identification number of the currently tracked target is reported and stored in the list of identified targets (see S130). Figure 1 (S140).

[0026] The target reporting method provided in this application acquires real-time images of the coastline, identifies targets from the current frame data of the coastline, and sorts the targets according to their type, identification number, and distance information. It prioritizes tracking the first target in the target list, records it in the identified target list after identification, and increases the priority of other unidentified targets to avoid duplicate identification of the same type of target. Based on this, it can classify and identify multiple types of targets over a wide area, comprehensively acquire target information along the coastline, avoid duplicate identification and reporting of single targets, and save communication and data processing resources.

[0027] The following text combines Figure 1 The target reporting method provided in the embodiments of this application will be described in more detail.

[0028] In S110, the current frame data containing multiple targets is acquired.

[0029] In some embodiments, before identifying and reporting targets, a category priority initialization can be performed to reset the priorities of targets in different categories. The category priority of targets can be set autonomously. For example, targets that are small and difficult to identify can be given a higher priority to prevent missed identification and reporting, while targets that are larger and easier to identify can be given a lower priority to reduce the risk of false alarms and duplicate identification.

[0030] In some embodiments, after initialization, the image-capturing device is aimed at the reconnaissance direction to acquire images and form the current frame data. The image-capturing device can be a camera, or a camera combined with a lidar system. The lidar system can be used to acquire the distance between the target and the hull carrying the image-capturing device.

[0031] In some embodiments, the current frame data includes the target's category, identification number, and distance information.

[0032] The target categories can include people, vehicles, ships, etc. For target identification on a coastline, in addition to people, vehicles, and ships, there may also be objects such as buoys. These objects are not considered as identification targets, therefore there is no target category classification.

[0033] For the identification number, the target identification number is a unique ID for each object. For example, each car, boat, and person in the current frame data is assigned an identification number for statistical analysis during subsequent target identification. This identification number is bound to each target and remains unchanged when the target moves out of the current frame and re-enters, unless the number is modified or reset.

[0034] Distance information, including the distance of a target in an image from the center of the image, or the offset of the target relative to the center of the image, can be used to sort and identify targets. Targets closer to the center of the image are sorted higher, meaning targets in the center of the image are identified first.

[0035] In some embodiments, to obtain the current frame data for image recognition, a deep learning model can be used to infer the input image. The model outputs the type and bounding box of each detected target. Based on the detection, a multi-target tracking algorithm, such as ByteTrack or DeepSORT, is integrated. The algorithm assigns and maintains a unique ID number for the same physical target detected in each frame, achieving stable identity recognition across frames. Next, the distance and orientation between the target and the image center are calculated to obtain distance information.

[0036] Continue to refer to Figure 1 In S120, the targets are sorted according to their category, preset category priority, identification number, and distance information to obtain a target list.

[0037] In some embodiments, filtering operations are performed sequentially on multiple targets. First, invalid targets are filtered out to obtain candidate targets. Then, the candidate targets are sorted according to their category, preset category priority, and distance information to obtain a target list.

[0038] As one possible implementation, the filtering operation can include: filtering targets not belonging to a specified target category based on a pre-defined list of target categories. For example, the list of specified target categories includes vehicles, ships, and people; objects such as buoys and marine debris in the image can be filtered to eliminate interference from irrelevant objects. Filtering targets already identified in a list of identified targets. Identified targets are stored in the identified target list, and because each target has a unique identification number, duplicate identification and reporting of targets can be prevented. Filtering targets smaller than a preset effective distance range and a preset volume based on a pre-defined effective distance range and a preset volume. For example, people and vehicles more than two kilometers away from a specified area will be filtered out. Because the distance is too far and the size of people and vehicles is too small, long-distance identification requires a long time and consumes a lot of resources; therefore, filtering small targets at long distances can improve identification efficiency.

[0039] In some embodiments, the filtered targets are sorted. First, if there is only one target in the current frame, priority is not considered; if there is only one category of target in the current frame, category priority is not considered.

[0040] As one possible implementation, when the number of target categories in the current frame is not less than the preset number of target categories, the targets are sorted according to the preset category priority to obtain a first target list. For example, if there are two target categories, people and cars, in the current frame, people have a higher priority than cars in the initial category priority, so all identified people are ranked before cars in the first target list.

[0041] As another possible implementation, when the number of target categories is less than the preset number of target categories, or when a first target list has already been obtained. For example, after sorting the targets according to preset category priorities, or when there is only one category, targets of the same category are sorted in ascending order of their offset from the image center to obtain a second target list. For example, at this point, the targets have already been initially sorted according to the preset category priorities of people and vehicles. Then, the offset of all people in the image from the image center is calculated, and the person with the smallest offset, i.e., the person closest to the image center, is placed at the beginning of the second target list.

[0042] Continue to refer to Figure 1 In S130, the first target in the target list is selected as the current tracking target.

[0043] In some embodiments, if there is only one type of target in the current frame, the target closest to the image center is directly selected as the current tracking target. If there are multiple types of targets in the current frame, the first target in the second target list is selected as the current tracking target based on the final results of the two sorting processes.

[0044] In some embodiments, after selecting the first target and determining the current tracking target, distance measurement can be performed on the current tracking target. For example, when the current tracking target is within the recognition frame, distance measurement is performed on the current tracking target according to a preset frequency and a preset period to obtain multiple distance measurement results. Based on the multiple distance measurement results, the real-time distance of the current tracking target is calculated. The recognition frame refers to the central recognition frame of the device used to capture the current frame data. After determining the current tracking target, the current tracking target is locked and tracked through the central recognition frame. When performing laser ranging, the target within the central recognition frame is illuminated by a laser and the distance is measured. However, due to the delay in shooting and the movement of the ship with the waves, if the current tracking target is small, the laser may easily deviate and illuminate other objects during ranging. Performing only one ranging measurement can easily lead to a large error in the calculated target position. Therefore, to reduce the ranging error, multiple ranging measurements can be performed, and data processing and averaging can be performed to obtain a more accurate real-time distance of the current tracking target. This provides accurate distance information for target recognition and target reporting, and can also provide basic data for obstacle avoidance and route planning.

[0045] In other embodiments, when ranging the current tracked target within a preset period, if the current tracked target is not within the identification frame and the duration of its absence exceeds a preset duration, the category priority of the current tracked target is set to 0, and the priorities of other target categories are increased by a preset value. That is, if the current tracked target leaves the identification frame within the preset measurement period, and the time spent outside the frame exceeds a preset duration, ranging of the current tracked target is stopped, and the category priority of the first target is initially set to 0 to reduce its identification priority and avoid repeated identification of this target. Then, the priorities of other categories are increased by a preset value (e.g., by 1 or another value) to prioritize the identification of other stable targets. After the priority adjustment is completed, the target is aligned with the detection direction again to re-determine the next tracked target.

[0046] Continue to refer to Figure 1 In S140, when the current tracking target is a first-category target, the corresponding priority is added to other categories of targets other than the current tracking target according to the preset weight, and the identification number of the current tracking target is reported and stored in the list of identified targets.

[0047] In some embodiments, the first category of target can be any category of target, such as any one of people, vehicles, and ships. When the currently tracked target is determined to be a certain category of target, the category priority of this category is set to 0, and the corresponding priorities of other categories of targets other than the currently tracked target are increased according to preset weights, so as to avoid repeatedly identifying the same type of target in the same frame.

[0048] In some embodiments, taking people, vehicles, and boats as examples, since people are smaller than vehicles, and vehicles are smaller than boats, increasing the weight of smaller targets helps in identifying them. When the currently tracked target is a person, the priority of people is set to 0, and the priority of vehicles is increased by a first value and the priority of boats is increased by a second value according to the preset weights; wherein the first value is greater than the second value. When the currently tracked target is a vehicle, the priority of vehicles is set to 0, and the priority of people is increased by a third value and the priority of boats is increased by a second value according to the preset weights; wherein the third value is greater than the second value. When the currently tracked target is a boat, the priority of boats is set to 0, and the priority of people is increased by a third value and the priority of vehicles is increased by a first value according to the preset weights; wherein the third value is greater than the first value.

[0049] Understandably, the third value can be set to 3, the second value to 2, and the first value to 1. In addition, other values ​​can be used, which can be adjusted according to actual recognition needs and historical recognition data.

[0050] In some embodiments, after adjusting the priority, the number of times the current tracking target's identification number has been reported is checked. If the number of reports for the current tracking target's identification number exceeds a preset number, the identification number of the current tracking target is added to the list of identified targets. For example, when the number of reports reaches 3, the identification number is added to the list of identified targets. Setting the reporting count is to eliminate the possibility of false alarms and improve the accuracy and stability of identification.

[0051] In other embodiments, if the number of times the identification number is reported has not reached a preset number, the system checks whether the ship's navigation route has reached its destination. If the ship has reached its destination, the target reporting process ends. If the ship has not yet reached its destination, the target identification and reporting process is repeated, aligning with the reconnaissance direction.

[0052] Exemplary device Figure 2 This is a schematic diagram of the structure of a target reporting device provided in an exemplary embodiment of this application, as shown below. Figure 2As shown, the target reporting device 2 includes: an acquisition module 21, used to acquire current frame data containing multiple targets; wherein the current frame data includes the target's category, identification number, and distance information; a sorting module 22, used to sort the targets according to their category, preset category priority, identification number, and distance information to obtain a target list; a selection module 23, used to select the first target in the target list as the current tracking target; and a reporting module 24, used to, when the current tracking target is a first-category target, add corresponding priorities to other categories of targets other than the current tracking target according to preset weights, and report and store the identification number of the current tracking target in the identified target list.

[0053] As one possible implementation, the sorting module 22 can be configured to: perform filtering operations on multiple targets sequentially to obtain candidate targets; and sort the candidate targets according to the target category, preset category priority, and distance information to obtain a target list.

[0054] As one possible implementation, the sorting module 22 can be configured to include the following filtering operations: filtering targets that are not in a specified category based on a preset list of specified target categories; filtering targets identified in the list of identified targets based on a preset list of identified targets; and filtering targets whose volume is smaller than a preset volume and whose distance is greater than the effective distance range based on a preset effective distance range and a preset volume.

[0055] As one possible implementation, the sorting module 22 can be configured to: when the number of target categories is not less than the preset number of target categories, sort the targets according to the preset category priority to obtain a first target list; when the number of target categories is less than the preset number of target categories, or when the first target list has been obtained, sort the targets of the same category in ascending order of the offset of the image center to obtain a second target list; wherein, the selection module 23 can be configured to: select the first target in the second target list as the current tracking target.

[0056] As one possible implementation, the target reporting device 2 may further include: when the currently tracked target is within the identification frame, measuring the distance of the currently tracked target according to a preset frequency and a preset period to obtain multiple ranging results; and calculating the real-time distance of the currently tracked target based on the multiple ranging results.

[0057] As one possible implementation, the target reporting device 2 may further include: when measuring the distance of the currently tracked target within a preset period, if the currently tracked target is not located within the identification frame and the duration of the non-identification frame is longer than the preset duration, the priority of the current tracked target category is set to 0, and the priority of other target categories is increased by a preset value.

[0058] As one possible implementation, the reporting module 24 can be configured as follows: when the current tracking target is a person, set the person's priority to 0, and according to preset weights, increase the vehicle's priority by a first value and the ship's priority by a second value; wherein the first value is greater than the second value; when the current tracking target is a vehicle, set the vehicle's priority to 0, and according to preset weights, increase the person's priority by a third value and the ship's priority by a second value; wherein the third value is greater than the second value; when the current tracking target is a ship, set the ship's priority to 0, and according to preset weights, increase the person's priority by a third value and the vehicle's priority by a first value; wherein the third value is greater than the first value.

[0059] As one possible implementation, the reporting module 24 can be configured to store the identification number of the currently tracked target into the list of identified targets when the number of reports of the identification number of the currently tracked target exceeds a preset number.

[0060] Exemplary electronic devices An electronic device includes: a processor; a memory for storing processor-executable instructions; and a processor for executing the target reporting method of the embodiments provided in this application.

[0061] Below, for reference Figure 3 This application describes an electronic device according to embodiments thereof. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0062] Figure 3 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0063] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0064] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0065] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the target reporting methods of the various embodiments of this application described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0066] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0067] When the electronic device is a standalone device, the input device 13 can be a communication network connector for receiving the collected input signals from the first device and the second device.

[0068] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0069] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0070] Of course, for the sake of simplicity, Figure 3 Only some of the components of the electronic device 10 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0071] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0072] A computer-readable storage medium stores a computer program for executing the target reporting method of the embodiments provided in this application.

[0073] Computer-readable storage media may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0074] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A target reporting method, characterized in that, include: Acquire current frame data containing multiple targets; wherein the current frame data includes the target category, identification number, and distance information; The targets are sorted according to their category, preset category priority, identification number, and distance information to obtain a target list; Select the first target in the target list as the current tracking target; When the currently tracked target is a first-category target, the corresponding priority is increased for other categories of targets besides the currently tracked target according to the preset weight, and the identification number of the currently tracked target is reported and stored in the list of identified targets.

2. The target reporting method according to claim 1, characterized in that, Based on the target's category, preset category priority, identification number, and distance information, the targets are sorted to obtain a target list, including: Filtering operations are performed sequentially on the multiple targets to obtain candidate targets; The candidate targets are sorted according to their category, preset category priority, and distance information to obtain a target list.

3. The target reporting method according to claim 2, characterized in that, The filtering operation includes: Based on a pre-defined list of specified target categories, filters out targets that are not in the specified category; Based on the identified target list, filter the identified targets in the identified target list; Based on a preset effective distance range and a preset volume, targets with a volume smaller than the preset volume and a distance greater than the effective distance range are filtered.

4. The target reporting method according to claim 1, characterized in that, Based on the target's category, preset category priority, identification number, and distance information, the targets are sorted to obtain a target list, including: When the number of target categories is not less than the preset number of target categories, the targets are sorted according to the preset category priority to obtain a first target list; When the number of target categories is less than the preset number of target categories, or when the first target list has been obtained, targets of the same category are sorted in ascending order of image center offset to obtain a second target list; The step of selecting the first target in the target list as the current tracking target includes: Select the first target in the second target list as the current tracking target.

5. The target reporting method according to claim 1, characterized in that, After selecting the first target in the target list as the current tracking target, the target reporting method further includes: When the currently tracked target is within the recognition frame, the current tracked target is measured according to a preset frequency and a preset period to obtain multiple ranging results. Based on the multiple ranging results, the real-time distance of the currently tracked target is calculated.

6. The target reporting method according to claim 5, characterized in that, The target reporting method also includes: When ranging the current tracking target within the preset period, if the current tracking target is not located within the identification box and the duration of the non-location within the identification box is longer than the preset duration, the category priority of the current tracking target is set to 0, and the priority of other categories of targets is increased by a preset value.

7. The target reporting method according to claim 1, characterized in that, The currently tracked targets include people, vehicles, and ships. When the currently tracked target is a first-category target, other categories of targets besides the currently tracked target are given corresponding priority according to preset weights, including: When the current tracking target is a person, the priority of the person is set to 0, and the priority of the vehicle is increased by a first value and the priority of the ship is increased by a second value according to a preset weight; wherein the first value is greater than the second value. When the current tracking target is a vehicle, the vehicle's priority is set to 0. According to the preset weight, the priority of a person is increased by a third value, and the priority of a ship is increased by a second value; wherein the third value is greater than the second value. When the current tracking target is a ship, the ship's priority is set to 0. According to the preset weight, the priority of a person is increased by a third value, and the priority of a vehicle is increased by a first value; wherein the third value is greater than the first value.

8. The target reporting method according to claim 1, characterized in that, The step of reporting and storing the identification number of the currently tracked target in the list of identified targets includes: When the number of times the identification number of the currently tracked target is reported exceeds a preset number, the identification number of the currently tracked target is stored in the list of identified targets.

9. A target reporting device, characterized in that, include: The acquisition module is used to acquire current frame data containing multiple targets; wherein, the current frame data includes the target category, identification number, and distance information; The sorting module is used to sort the targets according to their category, preset category priority, identification number, and distance information to obtain a target list; The selection module is used to select the first target in the target list as the current tracking target; The reporting module is used to, when the current tracking target is a first-category target, add corresponding priorities to other categories of targets other than the current tracking target according to preset weights, and report and store the identification number of the current tracking target in the list of identified targets.

10. A computer-readable storage medium, characterized in that, It stores a computer program that performs the target reporting method according to any one of claims 1 to 8.

Images