Methods, devices, systems, equipment, and media for optimizing the target perception capabilities of standard-issue mobile aircraft.

Abstract

This application discloses a method, apparatus, system, device, and medium for optimizing the target perception capability of a roadside warning system (LDS-based system). The method includes receiving target information transmitted by a roadside unit, matching the target information with the target perception information of the LDS-based system, determining a corresponding correction rule based on the matching result, correcting the LDS-based system's prediction information using the correction rule, and providing road warnings based on the corrected prediction information. The system includes a roadside unit, a vehicle-mounted unit, a LDS-based system, and an image acquisition unit. The roadside unit includes a roadside perception device, a roadside calculation unit, and a roadside communication unit. This application utilizes the target perception information provided by the roadside unit to match the target perception information in the LDS-based system, and by calculating and correcting the LDS-based system's prediction information, thereby enhancing the LDS-based system's road perception capability and improving the timeliness and accuracy of the warning function.

Description

Technical Field

[0001] This application relates to the field of vehicle-mounted intelligent device application technology, and in particular to a method, device, system, equipment and medium for optimizing the target perception capability of a vehicle. Background Technology

[0002] The Ministry of Transport's integrated recorder, or simply recorder, is a digital electronic recording device that records and stores vehicle speed, time, mileage, and other relevant vehicle status information, and can output data through an interface. It is widely used in transport vehicles and is an essential piece of equipment. Through its Advanced Driver Assistance System (ADAS) and Driver Status Monitor (DSM), it can perform functions such as forward collision warning, lane departure warning, pedestrian collision avoidance, and driver fatigue warning.

[0003] Currently, ADAS (Advanced Driver Assistance Systems) functions primarily rely on ADAS cameras to capture road images. Then, using image detection and segmentation algorithms, they detect, locate, and track vehicles and lane markings on the road. Combined with the vehicle's speed and location information, warnings are issued for forward collisions and lane departures to ensure the safety of road transport vehicles and drivers. For example, the forward collision warning function monitors the dynamics of vehicles ahead using ADAS cameras. When the calculated size, position, and speed of the vehicle ahead are below a trigger threshold, a collision risk is identified, and a warning is immediately issued to the driver. However, this existing method is limited by hardware constraints. For instance, camera resolution and environmental interference significantly affect the quality of the captured images, hindering high-quality image acquisition and image analysis capabilities. The limited computing power of onboard computers also restricts model size and accuracy, ultimately affecting the accuracy and stability of the algorithm model. Therefore, the current perception capabilities of ADAS cameras deviate from real-world scenarios, leading to untimely warnings or false alarms, posing significant safety hazards to road transport vehicles and drivers. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, system, equipment and medium for optimizing the target perception capability of roadside marker trolleys, thereby enhancing the target perception capability of roadside marker trolleys by utilizing roadside data, thus solving the problems of susceptibility to equipment limitations, low accuracy and poor stability in the application of existing roadside marker trolleys.

[0005] To achieve the above objectives, this application provides a method for optimizing the target perception capability of a target-oriented machine, comprising:

[0006] Receive target information transmitted by the road test unit and match the target information with the target perception information of the target detection machine;

[0007] Based on the matching results, the corresponding correction rules are determined, and the prediction information of the vehicle is corrected using the correction rules. Road warnings are then issued based on the corrected prediction information.

[0008] Furthermore, preferably, the target information transmitted by the road testing unit includes target ID information, target appearance time, target location, target speed, target heading angle, target size, and target-related confidence information; the target includes road vehicles.

[0009] Furthermore, preferably, matching the target information with the target perception information of the target-marking machine includes:

[0010] Determine whether the target information transmitted by the road test unit exists in the target historical trajectory of the target machine;

[0011] When the target information transmitted by the road test unit exists in the target historical trajectory of the target machine, and the target ID information exists in the target ID correspondence list of the target machine, the target historical trajectory of the target machine is corrected according to the target trajectory of the road test unit.

[0012] Furthermore, preferably, the step of correcting the target historical trajectory corresponding to the target machine based on the target trajectory of the road test unit includes:

[0013] If the time difference between the target appearance time in the road test unit and a certain time point in the target indicator is less than a first threshold, the target location at the time of the target appearance is obtained.

[0014] The target location is subjected to a confidence-based weighted average to correct the target's historical trajectory corresponding to the target aircraft.

[0015] Furthermore, as a preferred embodiment, the step of correcting the target historical trajectory corresponding to the target machine based on the target trajectory of the road test unit further includes:

[0016] If the time of the target appearance in the road test unit is between the earliest and latest time of the target appearance in the standard machine, obtain the time point closest to the time of the target appearance in the road test unit;

[0017] Based on the target information in the road test unit, the location information of the most recent time point is calculated, and the location of the most recent time point is taken as the target location.

[0018] The target location is subjected to a confidence-based weighted average to correct the target's historical trajectory corresponding to the target aircraft.

[0019] Furthermore, as a preferred embodiment, the step of correcting the target historical trajectory corresponding to the target machine based on the target trajectory of the road test unit further includes:

[0020] If the target in the road test unit appears later than the latest target in the target history of the target system, the target trajectory in the road test unit will be added to the target history trajectory of the target system.

[0021] Use advanced driver assistance systems to extract new target information and confirm the new target location;

[0022] The new target location is processed by a confidence-weighted average to correct the target's historical trajectory corresponding to the target aircraft.

[0023] Furthermore, preferably, after the target historical trajectory corresponding to the corrected target machine, the following is also included:

[0024] The current corrected target historical trajectory is used as a constraint to correct the next target historical trajectory, thereby correcting the next target historical trajectory of the target machine, including:

[0025] Obtain the corrected target ID at the same time point as the current target, determine the corresponding target location information in the road test unit based on the target ID, and calculate the relative distance of the target in the road test unit;

[0026] Based on the relative distance of the target in the road test unit and the current position information of other target IDs in the target machine, calculate the current position information of the target at the same time point in the trajectory of other targets, and use it as the relative position information;

[0027] The target perception information, relative position information and target information predicted by the target information machine in the road test unit are weighted and processed to modify the historical trajectory of the next target.

[0028] Furthermore, as a preferred embodiment, the method for optimizing the target perception capability of the target-aware machine further includes:

[0029] When the target information transmitted by the road test unit exists in the target historical trajectory of the Ministry of Public Security's target identification machine, and the ID information of the target vehicle is not in the target ID correspondence list of the Ministry of Public Security's target identification machine, similar targets are searched in the target historical trajectory of the Ministry of Public Security's target identification machine according to preset conditions based on the target historical trajectory in the road test unit.

[0030] Establish the ID correspondence between historical targets and similar targets in the road test unit.

[0031] Furthermore, preferably, the step of searching for similar targets in the target historical trajectory of the target machine according to preset conditions includes:

[0032] Based on the historical trajectory of the target in the road test unit, extract the historical target speed information, and calculate the corresponding target position based on the target speed information;

[0033] Align the target time in the road test unit with the target time of the Ministry of Public Security's target machine, compare the target historical trajectory in the road test unit with the target position on the target historical trajectory of the Ministry of Public Security's target machine one by one, and when the Euclidean distance between the two target positions is less than the second threshold, the corresponding target in the Ministry of Public Security's target machine is regarded as a similar target.

[0034] Furthermore, as a preferred embodiment, the method for optimizing the target perception capability of the target-aware machine further includes:

[0035] When the target information transmitted by the road test unit does not exist in the target history trajectory of the target machine, the target information transmitted by the road test unit is used as the new target.

[0036] Search for targets in the target history trajectory of the target machine whose time or location deviates from the time or location of the new target by less than the third threshold, and locate them as approximate targets;

[0037] Establish an ID correspondence between the new target and its approximate targets.

[0038] This application also provides a device for optimizing the target perception capability of a standard-issue machine, comprising:

[0039] The matching module is used to receive target information transmitted by the road test unit and match the target information with the target perception information of the target detection machine.

[0040] The correction module is used to determine the corresponding correction rules based on the matching results, correct the prediction information of the vehicle using the correction rules, and provide road warnings based on the corrected prediction information.

[0041] This application also provides a target perception capability optimization system for a standard-issue machine, comprising:

[0042] Road test unit, vehicle-mounted unit, standard marking unit and image acquisition unit;

[0043] The drive test unit includes a drive test sensing device, a drive test computing unit, and a drive test communication unit;

[0044] The road test sensing device is used to sense target information and send it to the road test calculation unit; the road test calculation unit is used to calculate the received target information, generate target sensing information, and transmit the target sensing information to the Ministry of Industry and Information Technology (MIIT) standard machine through the road test communication unit and the vehicle-mounted unit.

[0045] The target acquisition unit receives image information collected by the image acquisition unit, analyzes the image information through the advanced driver assistance system to obtain predictive perception information, and uses the target perception information to correct the target trajectory to determine the overall road situation.

[0046] The image acquisition unit includes an ADAS camera and an AVM camera.

[0047] This application also provides a computer device, including:

[0048] One or more processors;

[0049] A memory, coupled to the processor, for storing one or more programs;

[0050] When the one or more programs are executed by the one or more processors, the one or more processors implement the target perception capability optimization method of the Ministry of Industry and Information Technology as described in any of the preceding claims.

[0051] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the target perception capability optimization method for the target machine as described in any of the preceding claims.

[0052] Compared to existing technologies, the advantages of this application are as follows:

[0053] 1) The self-positioning accuracy of the vehicle positioning system is between 10-15m, and the ranging accuracy of ADAS is ±15%. Therefore, the accuracy of a distance of 50m is about 7.5m. The perception and positioning accuracy of the roadside unit (RSU) is 1.5m. Therefore, in this application, the target information provided by the RSU is used to correct the target historical trajectory in the vehicle positioning system, which can improve the fusion accuracy, reduce the error, and obtain more accurate target information. Therefore, the accuracy of the warning function will be improved when the corrected target information is calculated compared with the original information. At the same time, when uploading the vehicle positioning information, the perception and positioning of the RSU can be used instead of the positioning of the vehicle positioning system itself to improve the positioning accuracy.

[0054] 2) The RSU uses local sensors such as cameras, radar, and communication equipment to detect current road information. Compared with the Ministry of Public Security's target information system, which only uses cameras to judge road information, the target information provided by the RSU is undoubtedly more accurate. Moreover, it is less affected by factors such as camera blur and weather than the target information system that relies solely on cameras. Therefore, correcting the target information predicted by the target information system by using the target information provided by the RSU will improve the target information system's anti-interference ability for target perception. Attached Figure Description

[0055] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0056] Figure 1This is a flowchart illustrating a method for optimizing the target perception capability of a target-aware machine according to a certain embodiment of this application;

[0057] Figure 2 This is a flowchart illustrating a method for optimizing the target perception capability of a target-aware machine according to another embodiment of this application;

[0058] Figure 3 This is a schematic diagram illustrating the principle of comparing the target location points one by one with the target historical trajectory of the Ministry of Public Security's target and the target historical trajectory of the RSU, according to a certain embodiment of this application.

[0059] Figure 4 This is a schematic diagram of a process provided in a certain embodiment of the present application, which uses the previously corrected target historical trajectory of the target aircraft as the constraint for correcting the target historical trajectory of the next target aircraft.

[0060] Figure 5 This is a schematic diagram of the structure of a target perception capability optimization device for a target-setting machine provided in a certain embodiment of this application;

[0061] Figure 6 This is a schematic diagram of the structure of a target perception capability optimization system for a target-setting machine provided in a certain embodiment of this application;

[0062] Figure 7 This is a schematic diagram of the structure of a computer device provided in a certain embodiment of this application. Detailed Implementation

[0063] 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, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0064] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0065] It should be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0066] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0067] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0068] Please see Figure 1 This application provides a method for optimizing the target perception capability of a target-sensing machine in one embodiment. For example... Figure 1 As shown, the target perception capability optimization method for this target-sensing aircraft includes steps S10 to S20. The specific steps are as follows:

[0069] S10. Receive target information transmitted by the road test unit and match the target information with the target perception information of the target detection machine;

[0070] S20. Determine the corresponding correction rule based on the matching result, use the correction rule to correct the prediction information of the vehicle, and conduct road warning based on the corrected prediction information.

[0071] In this embodiment, without changing the existing conditions, the target perception information provided by the Road Side Unit (RSU) is matched with the target perception information in the target warning machine. The prediction information of the target warning machine is then calculated and corrected, thereby enhancing the road perception capability of the target warning machine and improving the timeliness and accuracy of the warning function.

[0072] Specifically, according to the "Application Layer and Application Data Interaction Standard for Vehicle Communication System of Cooperative Intelligent Transportation System (Phase II)" requirements for sharing and interacting perception data among traffic participants, the target information transmitted by the Roadside Unit (RSU) includes the following: target ID information, target appearance time, target location, target speed, target heading angle, target size, and target-related confidence information; the target includes road vehicles.

[0073] See Figure 2 , Figure 2 A flowchart for correcting the historical trajectory of a target aircraft is provided. The following will be based on... Figure 2 This application provides a detailed explanation of the method for optimizing the target perception capability of the standard-compliant machine:

[0074] In one specific embodiment, matching the target information with the target perception information of the target identification machine includes:

[0075] 1) Determine whether the target information transmitted by the road test unit exists in the target historical trajectory of the target testing machine;

[0076] 2) When the target information transmitted by the road test unit exists in the target historical trajectory of the target machine, and the target ID information exists in the target ID correspondence list of the target machine, the target historical trajectory of the target machine is corrected according to the target trajectory of the road test unit.

[0077] In this embodiment, it is first determined whether the target information transmitted by the road test unit exists in the target historical trajectory of the target machine; if it exists, the corresponding target ID of the target machine is searched for in the correspondence list between RSU target ID and target ID of the target machine; if it exists, the corresponding target historical trajectory of the target machine needs to be corrected by the received RSU target, and the different RSU target trajectories need to be divided into the following three cases:

[0078] Situation A:

[0079] If the time difference between the target appearance time in the road test unit and a certain time point in the target indicator is less than a first threshold, the target location at the time of the target appearance is obtained.

[0080] The target location is subjected to a confidence-based weighted average to correct the target's historical trajectory corresponding to the target aircraft.

[0081] In this embodiment, if the time of the RSU target information and the time value of a certain point in the historical trajectory of the target are less than a first threshold, it can be considered that the two times are basically overlapping. Then, a confidence-weighted average is performed on the target's location to correct the historical trajectory position of the target. After correction, if necessary, alarm logic is executed, such as... Figure 2 As shown.

[0082] Situation B:

[0083] If the time of the target appearance in the road test unit is between the earliest and latest time of the target appearance in the standard machine, obtain the time point closest to the time of the target appearance in the road test unit;

[0084] Based on the target information in the road test unit, the location information of the most recent time point is calculated, and the location of the most recent time point is taken as the target location; specifically, the principle of comparing the location of the historical trajectory of the target (e.g., the Ministry of Public Security target) and the historical trajectory of the RSU target is as follows: Figure 3 As shown.

[0085] The target location is processed using a confidence-based weighted average to correct the target's historical trajectory corresponding to the target aircraft. After correction, if necessary, alarm logic is executed, such as... Figure 2 As shown.

[0086] Case C:

[0087] If the target in the road test unit appears later than the latest target in the target history of the target system, the target trajectory in the road test unit will be added to the target history trajectory of the target system.

[0088] Use advanced driver assistance systems to extract new target information and confirm the new target location;

[0089] The new target location is processed by a confidence-weighted average to correct the target's historical trajectory corresponding to the target aircraft.

[0090] In this embodiment, if the time of the RSU target is later than the latest point in the target's historical trajectory on the target acquisition system, the RSU target information is added to the target's historical trajectory, but the alarm logic is not executed immediately. After the target acquisition system obtains new target data from the ADAS, a confidence-based weighting is applied to the position. If necessary, the alarm logic is executed, such as... Figure 2 As shown.

[0091] The above situation mainly addresses the correction process when the target information transmitted by the road test unit exists in the target historical trajectory of the target identification machine, and the target ID information exists in the target ID correspondence list of the target identification machine. In a specific embodiment, it also includes the case where the target ID information does not exist in the target ID correspondence list of the target identification machine, such as... Figure 2 As shown. Specifically, it includes the following:

[0092] 3) When the target information transmitted by the road test unit exists in the target historical trajectory of the Ministry of Public Security's target identification machine, and the ID information of the target vehicle is not in the target ID correspondence list of the Ministry of Public Security's target identification machine, similar targets are searched in the target historical trajectory of the Ministry of Public Security's target identification machine according to preset conditions based on the target historical trajectory in the road test unit; and the ID correspondence between the historical targets and similar targets in the road test unit is established.

[0093] In this embodiment, if the ID information of the target vehicle is not in the target ID correspondence list of the Ministry of Public Security's target identification machine, it means that the correspondence has not yet been established. At this time, it is necessary to use the RSU target historical trajectory to find similar targets in the target historical trajectory of the Ministry of Public Security's target identification machine.

[0094] In an exemplary embodiment, the step of searching for similar targets in the target history trajectory of the target machine according to preset conditions includes:

[0095] 3.1) Extract historical target speed information from the target historical trajectory in the road test unit, and deduce the corresponding target position based on the target speed information;

[0096] 3.2) Align the target time in the road test unit with the target time of the Ministry of Public Security's target machine, and compare the target historical trajectory in the road test unit with the target position on the target historical trajectory of the Ministry of Public Security's target machine one by one. When the Euclidean distance between the two target positions is less than the second threshold, the corresponding target in the Ministry of Public Security's target machine is regarded as a similar target.

[0097] In this embodiment, the position information is first calculated by the speed of the RSU target's historical trajectory, and the RSU target time is aligned with the target time of the Ministry of Defense. Then, the historical trajectory of the RSU target and the historical trajectory of the Ministry of Defense target are compared point by point. If the sum of the Euclidean distances is less than the threshold, they are determined to be the same target, and the two target IDs are linked together.

[0098] The above embodiments are all for the case where the target information transmitted by the road test unit exists in the target historical trajectory of the target camera. Please continue to refer to [the relevant documentation]. Figure 2 In one specific embodiment, the method for optimizing the target perception capability of the target-aware machine further includes:

[0099] When the target information transmitted by the road test unit does not exist in the target history trajectory of the target machine, the target information transmitted by the road test unit is used as the new target.

[0100] Search for targets in the target history trajectory of the target machine whose time or location deviates from the time or location of the new target by less than the third threshold, and locate them as approximate targets;

[0101] Establish an ID correspondence between the new target and its approximate targets.

[0102] In this embodiment, upon receiving an RSU target perception message, the system sequentially checks whether the target ID information exists in the target's historical trajectory. If it does not exist, it is determined to be a new target. For a new target, the new trajectory of the RSU needs to be maintained. At the same time, the system searches for targets in the target's historical trajectory whose time and location are less than a certain threshold compared to the target information (deviation) provided by the RSU. If a target exists, it is determined whether the target's size is within a third threshold. If it is, it is determined that the new target of the RSU and the target in the target's historical trajectory are the same target, and the target ID is then linked.

[0103] In a preferred embodiment, after the target historical trajectory corresponding to the corrected target machine, the method further includes:

[0104] The current corrected target historical trajectory is used as a constraint to correct the next target historical trajectory, thereby correcting the next target historical trajectory of the target machine, including:

[0105] Obtain the corrected target ID at the same time point as the current target, determine the corresponding target location information in the road test unit based on the target ID, and calculate the relative distance of the target in the road test unit;

[0106] Based on the relative distance of the target in the road test unit and the current position information of other target IDs in the target machine, calculate the current position information of the target at the same time point in the trajectory of other targets, and use it as the relative position information;

[0107] The target perception information, relative position information and target information predicted by the target information machine in the road test unit are weighted and processed to modify the historical trajectory of the next target.

[0108] See Figure 4 It should be noted that after the first target trajectory is corrected, when correcting the next target trajectory, the target information of the corrected trajectory can be used as a constraint. First, find the IDs of other corrected targets at the same time as the current target, obtain the corresponding target position information in the RSU, and calculate the relative distance with the current target's position information in the RSU. Then, calculate the position of the current target based on the current position and relative distance of other corrected targets. Finally, perform weighted processing on the target perception information of the RSU, the relative position information, and the target information predicted by the target information system to modify the target's historical trajectory.

[0109] In summary, the target perception capability optimization method for vehicle identification systems (VISs) provided in this application improves fusion accuracy, reduces errors, and obtains more accurate target information by utilizing target information provided by the Remote Detection Unit (RSU) to correct the historical trajectory of targets in the VISs. Calculations on the corrected target information show that the accuracy of the warning function is improved compared to before correction. Furthermore, when uploading vehicle location information, the RSU's perception positioning can replace the VISs' own positioning, improving positioning accuracy. Compared to traditional methods that rely solely on cameras to determine road information, the target information provided by the RSU is undoubtedly more accurate and less affected by factors such as camera blur and weather. Therefore, correcting the predicted target information in the VISs using the target information provided by the RSU enhances the VISs' anti-interference capability for target perception.

[0110] Please see Figure 5 In one embodiment of this application, a target perception capability optimization device for a target-oriented machine is also provided, comprising:

[0111] Matching module 01 is used to receive target information transmitted by the road test unit and match the target information with the target perception information of the target detection machine;

[0112] The correction module 02 is used to determine the corresponding correction rule based on the matching result, correct the prediction information of the vehicle using the correction rule, and provide road warning based on the corrected prediction information.

[0113] It is understood that the aforementioned target perception capability optimization device for the target-aware machine can implement the target perception capability optimization method for the target-aware machine described in the above method embodiments. The options in the above method embodiments are also applicable to this embodiment, and will not be detailed here. The remaining content of this application embodiment can be referred to the content of the above method embodiments, and will not be repeated in this embodiment.

[0114] Please see Figure 6In one embodiment of this application, a target perception capability optimization system for a target-oriented machine is also provided, comprising:

[0115] Road test unit, vehicle-mounted unit, standard marking unit and image acquisition unit;

[0116] The drive test unit includes a drive test sensing device, a drive test computing unit, and a drive test communication unit;

[0117] The road test sensing device is used to sense target information and send it to the road test calculation unit; the road test calculation unit is used to calculate the received target information, generate target sensing information, and transmit the target sensing information to the Ministry of Industry and Information Technology (MIIT) standard machine through the road test communication unit and the vehicle-mounted unit.

[0118] The target acquisition unit receives image information collected by the image acquisition unit, analyzes the image information through the advanced driver assistance system to obtain predictive perception information, and uses the target perception information to correct the target trajectory to determine the overall road situation.

[0119] The image acquisition unit includes an ADAS camera and an AVM camera.

[0120] In summary, this system can optimize the target perception capability of the target-aware aircraft, ultimately improving positioning accuracy and early warning accuracy.

[0121] Please see Figure 7 One embodiment of this application provides a computer device, including:

[0122] One or more processors;

[0123] A memory, coupled to the processor, for storing one or more programs;

[0124] When the one or more programs are executed by the one or more processors, the one or more processors implement the target perception capability optimization method of the target machine as described above.

[0125] The processor controls the overall operation of the computer device to complete all or part of the steps of the aforementioned target perception capability optimization method for the target-aware computer. The memory stores various types of data to support the operation of the computer device. This data may include, for example, instructions for any application or method operating on the computer device, as well as application-related data. The memory can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0126] In an exemplary embodiment, the computer device may be implemented by 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), controllers, microcontrollers, microprocessors, or other electronic components to execute the target perception capability optimization method for the target-sensing machine as described in any of the above embodiments, and achieve the same technical effect as the above method.

[0127] In another exemplary embodiment, a computer-readable storage medium including a computer program is also provided. When executed by a processor, the computer program implements the steps of the target perception capability optimization method for a target-aware machine as described in any of the foregoing embodiments. For example, the computer-readable storage medium may be the aforementioned memory including the computer program, which may be executed by a processor of a computer device to complete the target perception capability optimization method for a target-aware machine as described in any of the foregoing embodiments, and achieve the same technical effects as the aforementioned method.

[0128] The above description is the preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications are also considered to be within the scope of protection of this application.

Claims

1. A method for optimizing the target perception capability of a target-sensing machine, characterized in that, include: The system receives target information transmitted by the road test unit and matches the target information with the target perception information of the target detection machine; the target information includes target ID information. Specifically: The system determines whether the target information transmitted by the road test unit exists in the target historical trajectory of the target testing machine; when the target information transmitted by the road test unit exists in the target historical trajectory of the target testing machine, and the target ID information exists in the target ID correspondence list of the target testing machine, the target historical trajectory of the target testing machine is corrected according to the target trajectory of the road test unit; when the target information transmitted by the road test unit does not exist in the target historical trajectory of the target testing machine, the target information transmitted by the road test unit is used as a new target, and a target whose time or position deviation from the new target's time or position is less than a third threshold is searched in the target historical trajectory of the target testing machine, and its approximate target is located, establishing an ID correspondence between the new target and the approximate target; when the target information transmitted by the road test unit exists in the target historical trajectory of the target testing machine, and the target ID information is not in the target ID correspondence list of the target testing machine, similar targets are searched in the target historical trajectory of the target testing machine according to preset conditions, and an ID correspondence between the historical targets in the road test unit and the similar targets is established. Based on the matching results, the corresponding correction rules are determined, and the prediction information of the vehicle is corrected using the correction rules. Road warnings are then issued based on the corrected prediction information.

2. The method for optimizing the target perception capability of a target-oriented machine according to claim 1, characterized in that, The target information transmitted by the road test unit includes the target appearance time, target location, target speed, target heading angle, target size, and target-related confidence information; the target includes road vehicles.

3. The method for optimizing the target perception capability of a target-oriented machine according to claim 1, characterized in that, The step of correcting the target historical trajectory corresponding to the target machine based on the target trajectory of the road test unit includes: If the time difference between the target appearance time in the road test unit and a certain time point in the target indicator is less than a first threshold, the target location at the time of the target appearance is obtained. The target location is subjected to a confidence-based weighted average to correct the target's historical trajectory corresponding to the target aircraft.

4. The method for optimizing the target perception capability of a target-oriented machine according to claim 1, characterized in that, The step of correcting the target historical trajectory corresponding to the target machine based on the target trajectory of the road test unit also includes: If the time of the target appearance in the road test unit is between the earliest and latest time of the target appearance in the standard machine, obtain the time point closest to the time of the target appearance in the road test unit; Based on the target information in the road test unit, the location information of the most recent time point is calculated, and the location of the most recent time point is taken as the target location. The target location is subjected to a confidence-based weighted average to correct the target's historical trajectory corresponding to the target aircraft.

5. The method for optimizing the target perception capability of a target-oriented machine according to claim 1, characterized in that, The step of correcting the target historical trajectory corresponding to the target machine based on the target trajectory of the road test unit also includes: If the target in the road test unit appears later than the latest target in the target history of the target system, the target trajectory in the road test unit will be added to the target history trajectory of the target system. Use advanced driver assistance systems to extract new target information and confirm the new target location; The new target location is processed by a confidence-weighted average to correct the target's historical trajectory corresponding to the target aircraft.

6. The method for optimizing the target perception capability of a target-oriented machine according to any one of claims 3-5, characterized in that, Following the target historical trajectory corresponding to the corrected target machine, the following is also included: The current corrected target historical trajectory is used as a constraint to correct the next target historical trajectory, thereby correcting the next target historical trajectory of the target machine, including: Obtain the corrected target ID at the same time point as the current target, determine the corresponding target location information in the road test unit based on the target ID, and calculate the relative distance of the target in the road test unit; Based on the relative distance of the target in the road test unit and the current position information of other target IDs in the target machine, calculate the current position information of the target at the same time point in the trajectory of other targets, and use it as the relative position information; The target perception information, relative position information and target information predicted by the target information machine in the road test unit are weighted and processed to modify the historical trajectory of the next target.

7. The method for optimizing the target perception capability of a target-oriented machine according to claim 1, characterized in that, The step of searching for similar targets in the target history trajectory of the target machine according to preset conditions includes: Based on the historical trajectory of the target in the road test unit, extract the historical target speed information, and calculate the corresponding target position based on the target speed information; Align the target time in the road test unit with the target time of the Ministry of Public Security's target machine, compare the target historical trajectory in the road test unit with the target position on the target historical trajectory of the Ministry of Public Security's target machine one by one, and when the Euclidean distance between the two target positions is less than the second threshold, the corresponding target in the Ministry of Public Security's target machine is regarded as a similar target.

8. A device for optimizing the target perception capability of a target-oriented machine, characterized in that, include: The matching module is used to receive target information transmitted by the road test unit and match the target information with the target perception information of the target detection machine; the target information includes target ID information; Specifically: The system determines whether the target information transmitted by the road test unit exists in the target historical trajectory of the target testing machine; when the target information transmitted by the road test unit exists in the target historical trajectory of the target testing machine, and the target ID information exists in the target ID correspondence list of the target testing machine, the target historical trajectory of the target testing machine is corrected according to the target trajectory of the road test unit; when the target information transmitted by the road test unit does not exist in the target historical trajectory of the target testing machine, the target information transmitted by the road test unit is used as a new target, and a target whose time or position deviation from the new target's time or position is less than a third threshold is searched in the target historical trajectory of the target testing machine, and its approximate target is located, establishing an ID correspondence between the new target and the approximate target; when the target information transmitted by the road test unit exists in the target historical trajectory of the target testing machine, and the target ID information is not in the target ID correspondence list of the target testing machine, similar targets are searched in the target historical trajectory of the target testing machine according to preset conditions, and an ID correspondence between the historical targets in the road test unit and the similar targets is established. The correction module is used to determine the corresponding correction rules based on the matching results, correct the prediction information of the vehicle using the correction rules, and provide road warnings based on the corrected prediction information.

9. A computer device, characterized in that, include: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the target perception capability optimization method for the Ministry of Industry and Information Technology as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the target perception capability optimization method for the Ministry of Industry and Information Technology as described in any one of claims 1-7.

Images