False target filtering method, device and equipment and readable storage medium

Abstract

The invention discloses a false target filtering method, device and equipment and a readable storage medium, and is applied to the technical field of computers, and the method comprises the steps: obtaining the target information of a target through a single camera of a vehicle; the target information comprises the longitudinal distance between the vehicle and the target, the duration of continuous appearance of the target and the variation amplitude of the target; if it is determined that the target meets the false target judgment condition according to the target information, whether the target is a false target or not is determined according to the actual vehicle speed and the virtual vehicle speed of the vehicle; and if the target is a false target, filtering the target. According to the method, the virtuality and reality of the target are determined through multi-dimensional target information collection, multi-dimensional preliminary screening and dynamic verification of the actual vehicle speed and the virtual vehicle speed of the vehicle. By means of physical rule constraints, high-precision false target filtering is achieved under low-cost single-camera configuration, and reliable technical support is provided for an environment sensing module of an automatic driving system.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, device, and readable storage medium for filtering false targets. Background Technology

[0002] When a vehicle is in autonomous driving mode, its single camera automatically collects information ahead. Upon detecting a target / vehicle posing a safety risk, it will apply the brakes. However, due to factors such as changes in lighting, weather conditions, and the similarity of objects, false targets may appear. False braking caused by these false targets can lead to a poor user experience. Currently, the common approach to address this issue is to add more sensors to improve the accuracy of target recognition, but this method increases costs.

[0003] Therefore, under the premise of limited cost, how to improve the accuracy of target recognition is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, apparatus, device and readable storage medium for filtering false targets, which solves the problems of poor target recognition accuracy and high recognition cost in the prior art.

[0005] To address the aforementioned technical problems, this invention provides a method for filtering false targets, comprising:

[0006] The target information is acquired through a single camera on the vehicle; the target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes.

[0007] Determine whether the target meets the criteria for judging a false target based on the target information;

[0008] If the conditions are met, the actual vehicle speed and the virtual vehicle speed calculated based on the target are obtained, and it is determined whether the target is a false target based on the magnitude of the actual vehicle speed and the virtual vehicle speed.

[0009] If the target is a false target, then the target will be filtered out.

[0010] Optionally, determining whether the target meets the criteria for judging a false target based on the target information includes:

[0011] If the longitudinal distance exceeds a preset distance threshold and the duration does not exceed a preset duration threshold, then the target satisfies the false target judgment condition.

[0012] Alternatively, if the change in the longitudinal distance of the target exceeds a preset distance range threshold, then the target satisfies the false target judgment condition;

[0013] Alternatively, if the change in the absolute longitudinal velocity of the target exceeds a preset velocity amplitude threshold, then the target satisfies the false target judgment condition.

[0014] Optionally, obtaining the vehicle's actual speed and the vehicle's virtual speed calculated based on the target includes:

[0015] The actual vehicle speed of the current frame is obtained through the vehicle's controller local area network;

[0016] The virtual vehicle speed of the current frame is calculated using the longitudinal distance and absolute longitudinal velocity of the target consecutive frames.

[0017] Optionally, determining whether the target is a false target based on the magnitude of the vehicle's actual speed and the vehicle's virtual speed includes:

[0018] The speed ratio is calculated based on the actual speed of the vehicle and the virtual speed of the vehicle.

[0019] When the speed ratio is greater than a first preset speed ratio threshold, or when the speed ratio is less than a second preset speed ratio threshold, the target is recorded as having speed-distance inconsistency; the first preset speed ratio threshold is greater than the second preset speed ratio threshold.

[0020] If the number of times the target's speed and distance are inconsistent exceeds a preset threshold, then the target is a false target.

[0021] Optionally, after calculating the speed ratio based on the actual vehicle speed and the virtual vehicle speed, the method further includes:

[0022] If the absolute longitudinal velocity of the target is less than a preset velocity threshold, the target is recorded as having velocity-distance inconsistency.

[0023] Optionally, if the target is a false target, after filtering the target, the method further includes:

[0024] Continuously acquire target information of the target;

[0025] When it is determined from the target information that the target does not meet the false target judgment condition, the filtered target is the real target.

[0026] Optionally, if the target is a false target, after filtering the target, the method further includes:

[0027] If the number of times the target's speed and distance are inconsistent does not exceed a preset threshold within a preset time period, then the filtered target is the real target.

[0028] The present invention also provides a false target filtering device, comprising:

[0029] The information acquisition module is used to acquire target information of a target through a single camera on the vehicle; the target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes;

[0030] The first judgment module is used to determine whether the target meets the false target judgment condition based on the target information;

[0031] The second judgment module is used to obtain the actual vehicle speed and the virtual vehicle speed calculated based on the target if the conditions are met, and to determine whether the target is a false target based on the magnitude of the actual vehicle speed and the virtual vehicle speed.

[0032] A filtering module is used to filter out targets if they are false targets.

[0033] The present invention also provides a decoy target filtering device, comprising:

[0034] Memory, used to store computer programs;

[0035] A processor is used to implement the spoofing filtering method described above when executing the computer program.

[0036] The present invention also provides a computer-readable storage medium storing computer-executable instructions, which, when loaded and executed by a processor, implement the false target filtering method described above.

[0037] As can be seen, this invention acquires target information of a target using a single camera on the vehicle. This target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes. Based on this target information, it determines whether the target meets the criteria for a false target. If so, it acquires the vehicle's actual speed and its virtual speed calculated based on the target, and determines whether the target is a false target based on the magnitude of the actual and virtual speeds. If the target is a false target, it is filtered. This method acquires target information using a single camera on the vehicle, determines whether the target is a suspected false target based on the target information and the criteria for a false target, and further determines whether the target is a false target based on the vehicle's actual and virtual speeds. This method determines the real or false nature of a target through multi-dimensional target information collection and preliminary screening, as well as dynamic verification of the vehicle's actual and virtual speeds. By leveraging physical constraints, it achieves high-precision false target filtering with a low-cost single-camera configuration, providing reliable technical support for the environmental perception module of an autonomous driving system.

[0038] In addition, the present invention also provides a false target filtering device, equipment and readable storage medium, which also have the above-mentioned beneficial effects. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0040] Figure 1 A flowchart of a false target filtering method provided in an embodiment of the present invention;

[0041] Figure 2 This is a schematic diagram of a false target filtering device provided in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of a false target filtering device provided in an embodiment of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] In single-camera autonomous driving projects, because only one camera sensor perceives the target, it is prone to misidentification due to changes in lighting, weather conditions, object similarity, and camera-related issues (such as lens smudges). This can lead to unintended braking during autonomous driving, resulting in a poor driver experience. Existing solutions typically involve adding more camera sensors to improve target recognition accuracy, but this increases costs. Therefore, this invention provides a false target filtering method. By reprocessing the target information acquired by the single camera, false targets are filtered out, reducing the probability of unintended braking and improving the driver's experience.

[0045] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for filtering false targets provided in an embodiment of the present invention. The method may include:

[0046] S101: Acquire target information of the target through a single camera on the vehicle; the target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes.

[0047] The execution subject in this embodiment is an in-vehicle terminal. This embodiment is not limited to any particular type of terminal, as long as it can perform the false target filtering method. This method can be applied in the field of autonomous driving.

[0048] It is understood that the target information collected in this embodiment is related to the criteria for judging false targets. The target information collection frequency in this embodiment can be calculated based on collection frames, for example, one frame is collected every 20ms as a collection cycle. This embodiment does not limit the magnitude of change. For example, it could be the magnitude of change in longitudinal distance; or it could be the magnitude of change in absolute longitudinal vehicle speed. Based on the magnitude of change, it can be determined whether the target exhibits large jumps.

[0049] S102: Determine whether the target meets the criteria for judging a false target based on the target information.

[0050] Specifically, this embodiment does not limit the conditions for judging false targets. It is understood that the conditions for judging false targets in this embodiment are related to longitudinal distance, duration, and magnitude of change. The conditions for judging false targets in this embodiment can be understood as a preliminary judgment of target information, or as the triggering time for entering the next judgment stage. When the conditions for judging false targets are met, step S103 is entered; when the conditions for judging false targets are not met, the target is a normal target, and the target is retained without filtering.

[0051] Furthermore, the above-mentioned determination of whether the target meets the false target judgment condition based on the target information may specifically include the following steps: if the longitudinal distance exceeds a preset distance threshold and the duration does not exceed a preset duration threshold, then the target meets the false target judgment condition; or, if the change range of the longitudinal distance of the target exceeds a preset distance range threshold, then the target meets the false target judgment condition; or, if the change range of the absolute longitudinal velocity of the target exceeds a preset velocity range threshold, then the target meets the false target judgment condition.

[0052] Specifically, the false target judgment conditions in this embodiment include three sub-conditions: (1) whether the longitudinal distance exceeds a preset distance threshold and whether the duration does not exceed a preset duration threshold; (2) whether the change range of the longitudinal distance exceeds a preset distance range threshold; and (3) whether the change range of the absolute longitudinal speed exceeds a preset speed range threshold. This embodiment does not limit the preset distance threshold, preset duration threshold, preset distance range threshold, and preset speed range threshold; these can be limited according to the actual screening situation. In this embodiment, when a target meets any of the above sub-conditions, the target is at risk of being a suspected false target and needs to proceed to the next stage of judgment.

[0053] The first sub-condition ensures vehicle safety based on distance and determines target credibility based on target duration. For example, if the longitudinal distance exceeds 60m and the duration of the target's appearance does not exceed 3 seconds, the target is considered a suspected false target and proceeds to the next stage of filtering. The longitudinal distance determination is based on safety considerations, treating targets within that distance as normal targets to prevent inaccurate identification due to single-camera errors at close range, and also to prevent the vehicle's safety risks caused by misclassifying normal targets within 60m as false targets during filtering. False targets typically appear for a short time; therefore, the credibility is determined by setting a duration. If it does not exceed 3 seconds, the target is considered a suspected false target; if it exceeds 3 seconds, it is considered a normal target. Road tests showed that this sub-condition could identify the vast majority of suspected false targets. To further improve the accuracy of false target identification, a second and third sub-condition, based on the magnitude of the change in target appearance, were added. These two sub-conditions supplement the first sub-condition. For example, if there is a large jump in longitudinal distance or absolute longitudinal velocity, such as the absolute value of the difference between the current frame and the previous frame in longitudinal distance being greater than 50m, or the absolute value of the difference between the current frame and the previous frame in absolute longitudinal velocity being greater than 20m / s, then the target is suspected to be a false target. These two sub-conditions are to deal with some special cases, such as the special cases mentioned above where the longitudinal distance is less than 60m or the time exceeds 3s.

[0054] S103: If satisfied, obtain the actual vehicle speed and the virtual vehicle speed calculated based on the target, and determine whether the target is a false target based on the magnitude of the actual vehicle speed and the virtual vehicle speed.

[0055] If, after the initial judgment in S102, the target meets the aforementioned criteria for determining a false target, then proceed to step S103. That is, the target is a suspected false target. Furthermore, this embodiment utilizes the constraints of physical laws to perform a secondary judgment on the target. These judgment criteria can effectively reflect whether the changing trends of the target's speed and distance conform to physical laws. Its advantage lies in its ability to accurately filter out abnormal targets that cannot be eliminated by relying solely on a single dimension (such as speed or distance).

[0056] Specifically, in this embodiment, the determination of whether a target is a false target is based on the relationship between the vehicle's actual speed and its virtual speed. The virtual speed is calculated based on the target captured by a single camera on the vehicle.

[0057] Furthermore, the above-mentioned acquisition of the vehicle's actual speed and the vehicle's virtual speed calculated based on the target may specifically include the following steps: acquiring the vehicle's actual speed in the current frame through the vehicle's controller local area network; and calculating the vehicle's virtual speed in the current frame through the longitudinal distance and absolute longitudinal speed of the target consecutive frames.

[0058] Specifically, in this embodiment, the actual vehicle speed v_ibc of the current frame is the speed obtained through the vehicle's CAN (Controller Area Network). The calculation process of the vehicle's virtual speed can be referenced by the following formula:

[0059] Obtain the target's longitudinal distance s2 and absolute longitudinal speed v2 in the current frame;

[0060] Obtain the longitudinal distance s1 and absolute longitudinal speed v1 of the target in the previous frame;

[0061] The formula for calculating the longitudinal distance difference Delta_s is: Delta_s = s2 - s1;

[0062] The formula for calculating the average absolute longitudinal speed, average_v, is: average_v = (v1 + v2) / 2;

[0063] The formula for calculating the virtual vehicle speed v_cal is: v_cal = average_v - Delta_s / cycle.

[0064] Furthermore, the above-mentioned determination of whether a target is a false target based on the magnitude of the vehicle's actual speed and virtual speed may specifically include the following steps: calculating the speed ratio based on the vehicle's actual speed and virtual speed; when the speed ratio is greater than a first preset speed ratio threshold, or when the speed ratio is less than a second preset speed ratio threshold, the target is recorded as having speed-distance inconsistency; the first preset speed ratio threshold is greater than the second preset speed ratio threshold; when the number of times the target's speed-distance inconsistency exceeds a preset number threshold, the target is a false target.

[0065] It should be noted that this embodiment does not limit the first preset speed ratio threshold and the second preset speed ratio threshold, as long as the first preset speed ratio threshold is greater than the second preset speed ratio threshold. In this embodiment, the speed ratio can be v_cal / v_ibc; or it can be v_ibc / v_cal. In this embodiment, the actual vehicle speed and the virtual vehicle speed are the vehicle speeds of the current frame, i.e., the speed ratio is the speed ratio of the current frame, which determines whether the target speed and distance are consistent in the current frame. This embodiment uses the difference between the virtual vehicle speed and the actual vehicle speed to determine whether the target identified by the single camera is accurate, thereby filtering out false targets. According to this judgment rule, if 6 or more out of every 10 frames show speed-distance inconsistency, the target is filtered as a false target, and the speed-distance inconsistency flag for that target is set to 1. Alternatively, different speed-distance inconsistency judgment rules can be formulated for different false target judgment conditions, and different preset number thresholds can be set. For example, when the change in the target exceeds the preset change threshold, a 2-second speed-distance inconsistency judgment can be performed. That is, the actual speed and virtual speed of the vehicle within 2 seconds are obtained, and the relationship between the speed ratio of each frame within these 2 seconds and the preset speed ratio threshold (first preset speed ratio threshold or second preset speed ratio threshold) is judged.

[0066] For example, if v_cal / v_ibc > 1.5, or v_cal / v_ibc < 0.4, the target in the current frame is recorded as having inconsistent speed and distance. Alternatively, if v_ibc / v_cal > 2.5, or v_ibc / v_cal < 0.67, the target in the current frame is also recorded as having inconsistent speed and distance. In other words, if the vehicle's virtual speed is greater than 1.5 times its actual speed, or less than 0.4 times its actual speed, it indicates a significant difference between the virtual and actual speeds, suggesting that the target attributes identified by a single camera are inaccurate.

[0067] Furthermore, after calculating the speed ratio based on the vehicle's actual speed and virtual speed, the above may also include the following steps: if the target's absolute longitudinal speed is less than a preset speed threshold, the target is recorded as having speed-distance inconsistency.

[0068] Specifically, this embodiment further supplements the judgment of the above-mentioned false targets. Considering that in real road scenarios, due to the existence of errors, the speed of the vehicle directly in front of the vehicle may be a negative value, but it will not be a very large negative value. Therefore, the target can be judged in response to this abnormal situation, and some false targets can be filtered out in this way. Similarly, this embodiment does not limit the preset speed threshold, but it can be understood that the preset speed threshold is a negative value. For example, the condition of absolute longitudinal speed being less than -5m / s can be set. It should be noted that there are two aspects to the judgment condition of speed-distance inconsistency: (1) the relationship between the ratio of the actual vehicle speed and the virtual vehicle speed and the preset speed ratio threshold, such as v_cal / v_ibc > 1.5 or v_cal / v_ibc < 0.4; (2) the relationship between the absolute longitudinal speed and the preset speed threshold, such as the absolute longitudinal speed being less than -5m / s. If either of these two judgment conditions is met, it can be determined that the target in the current frame is speed-distance inconsistent.

[0069] S104: If the target is a false target, then filter the target.

[0070] If the target is a false target, it will be filtered out so that the vehicle will not brake incorrectly because of the target, thereby improving the user experience.

[0071] Furthermore, if the target is a false target, after filtering the target, the following steps may be included: continuously acquiring the target information; when it is determined from the target information that the target does not meet the judgment condition for a false target, the filtered target is a real target.

[0072] It is understood that this embodiment also resets the filtered targets (i.e., false targets). The reset conditions include: when the target does not meet the self-consistent speed-distance calculation criteria, that is, the target does not meet the aforementioned false target judgment criteria. Not meeting the false target judgment criteria means that the target is relatively close to the vehicle in longitudinal distance, has existed for a long time, or has a small change in distance. A relatively close longitudinal distance is mainly considered for safety factors; a longer duration and a smaller change in distance both indicate a higher probability of the target's existence, which are characteristics that normal targets should possess.

[0073] Furthermore, after filtering out false targets, the following steps may also be included:

[0074] If the number of times the target's speed and distance do not match within the preset time does not exceed the preset threshold, then the filtered target is the real target.

[0075] This embodiment further supplements the above-mentioned reset conditions: when the virtual vehicle speed calculated through the target attributes is close to and not significantly negative than the actual vehicle speed, these characteristics represent attributes of a normal target, so no filtering is performed, and it is treated as a normal target. Similarly, this embodiment does not specifically limit the preset number of thresholds. For example, if less than 6 out of every 10 frames are speed-distance consistent, and this consistency lasts for 0.3 seconds, then the speed-distance inconsistency flag of the target changes from 1 to 0, and the filtered target can be released as a normal target. The reason for the 0.3-second duration is to increase hysteresis to prevent the speed-distance inconsistency flag of the target from frequently changing, causing the target to be filtered intermittently.

[0076] The false target filtering method provided in this embodiment of the invention proceeds as follows: S101, target information is acquired using a single camera on the vehicle; the target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes; S102, the target information is used to determine whether the target meets the false target judgment criteria; S103, if it does, the actual vehicle speed and the virtual vehicle speed calculated based on the target are acquired, and the magnitude of the actual and virtual vehicle speeds is used to determine whether the target is a false target; S104, if the target is a false target, it is filtered. Therefore, this method acquires target information using a single camera on the vehicle, determines whether the target is a suspected false target based on the target information and the false target judgment criteria, and further determines whether the target is a false target based on the actual and virtual vehicle speeds. Thus, this method determines the real or false nature of the target through multi-dimensional target information collection and preliminary screening, as well as dynamic verification of the actual and virtual vehicle speeds. By leveraging the constraints of physical laws, high-precision false target filtering was achieved with a low-cost single-camera configuration, providing reliable technical support for the environmental perception module of autonomous driving systems.

[0077] The following describes the false target filtering device provided in the embodiments of the present invention. The false target filtering device described below can be referred to in correspondence with the false target filtering method described above.

[0078] Please refer to the details. Figure 2 , Figure 2 A schematic diagram of a false target filtering device provided in an embodiment of the present invention may include:

[0079] The information acquisition module 100 is used to acquire target information of a target through a single camera on the vehicle; the target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes;

[0080] The first judgment module 200 is used to determine whether the target meets the false target judgment condition based on the target information;

[0081] The second judgment module 300 is used to, if satisfied, obtain the actual vehicle speed and the virtual vehicle speed calculated based on the target, and determine whether the target is a false target based on the magnitude of the actual vehicle speed and the virtual vehicle speed.

[0082] The filtering module 400 is used to filter the target if the target is a false target.

[0083] Based on the above embodiments, the first determination module 200 may include:

[0084] The first judgment unit is used to determine if the target satisfies the false target judgment condition if the longitudinal distance exceeds a preset distance threshold and the duration does not exceed a preset duration threshold.

[0085] Alternatively, the second judgment unit is used to determine if the target satisfies the false target judgment condition if the change in the longitudinal distance of the target exceeds a preset distance range threshold.

[0086] Alternatively, a third judgment unit is configured to determine if the target satisfies the false target judgment condition if the change in the absolute longitudinal velocity of the target exceeds a preset velocity amplitude threshold.

[0087] Based on the above embodiments, the second determination module 300 may include:

[0088] The vehicle actual speed acquisition unit is used to acquire the vehicle actual speed of the current frame through the vehicle's controller local area network;

[0089] The virtual vehicle speed calculation unit is used to calculate the virtual vehicle speed of the current frame using the longitudinal distance and absolute longitudinal speed of the target consecutive frames.

[0090] Based on the above embodiments, the second determination module 300 may include:

[0091] A speed ratio calculation unit is used to calculate the speed ratio based on the actual speed of the vehicle and the virtual speed of the vehicle.

[0092] The speed-distance inconsistency calculation unit is used to record the target as having speed-distance inconsistency when the speed ratio is greater than a first preset speed ratio threshold or the speed ratio is less than a second preset speed ratio threshold; the first preset speed ratio threshold is greater than the second preset speed ratio threshold.

[0093] The false target determination unit is used to determine that the target is a false target when the number of times the target's speed and distance are inconsistent exceeds a preset threshold.

[0094] Based on the above embodiments, the false target filtering device may further include:

[0095] The speed-distance inconsistency judgment module is used to determine that if the absolute longitudinal speed of the target is less than a preset speed threshold, the target is considered to have speed-distance inconsistency.

[0096] Based on the above embodiments, the false target filtering device may further include:

[0097] The first false target release module is used to continuously acquire target information of the target after filtering the target if the target is a false target; when it is determined from the target information that the target does not meet the false target judgment condition, the filtered target is a real target.

[0098] Based on the above embodiments, the false target filtering device may further include:

[0099] The second false target release module is used to filter the target if it is a false target. If the number of times the target's speed and distance are inconsistent does not exceed a preset threshold within a preset time, then the filtered target is a real target.

[0100] It should be noted that the order of the modules and units in the aforementioned false target filtering device can be changed without affecting the logic.

[0101] The false target filtering device provided in this embodiment of the invention uses an information acquisition module 100 to acquire target information of a target through a single camera on a vehicle. The target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes. A first judgment module 200 determines whether the target meets the false target judgment criteria based on the target information. A second judgment module 300, if the criteria are met, acquires the vehicle's actual speed and a virtual speed calculated based on the target, and determines whether the target is a false target based on the magnitude of the actual speed and the virtual speed. A filtering module 400 filters the target if it is a false target. Therefore, this device acquires target information through a single camera on the vehicle, determines whether the target is a suspected false target based on the target information and the false target judgment criteria, and further determines whether the target is a false target based on the vehicle's actual speed and virtual speed. This method determines the real or false nature of a target through multi-dimensional target information collection and preliminary screening, as well as dynamic verification of the vehicle's actual speed and virtual speed. By leveraging the constraints of physical laws, high-precision false target filtering was achieved with a low-cost single-camera configuration, providing reliable technical support for the environmental perception module of autonomous driving systems.

[0102] The following describes the false target filtering device provided in the embodiments of the present invention. The false target filtering device described below can be referred to in correspondence with the false target filtering method described above.

[0103] Please refer to Figure 3 , Figure 3 A schematic diagram of a decoy target filtering device provided in an embodiment of the present invention may include:

[0104] Memory 10 is used to store computer programs;

[0105] Processor 20 is used to execute computer programs to implement the aforementioned spoofing filtering method.

[0106] The memory 10, processor 20, and communication interface 31 all communicate with each other through the communication bus 32.

[0107] In this embodiment of the invention, the memory 10 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment of the invention, the memory 10 may store programs for implementing the following functions:

[0108] The vehicle acquires target information using a single camera; the target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes.

[0109] Determine whether the target meets the criteria for judging a false target based on the target information;

[0110] If the conditions are met, the actual vehicle speed and the virtual vehicle speed calculated based on the target are obtained, and the target is determined as a false target based on the magnitude of the actual vehicle speed and the virtual vehicle speed.

[0111] If the target is a false target, then the target will be filtered.

[0112] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0113] Furthermore, memory 10 may include read-only memory and random access memory, providing instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores operating systems and operating instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof, wherein the operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and handling hardware-based tasks.

[0114] Processor 20 can be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic device. Processor 20 can be a microprocessor or any conventional processor. Processor 20 can call programs stored in memory 10.

[0115] Communication interface 31 can be an interface for the communication module, used to connect with other devices or systems.

[0116] Of course, it should be noted that, Figure 3 The structure shown does not constitute a limitation on the false target filtering device in the embodiments of the present invention. In practical applications, the false target filtering device may include more than Figure 3 More or fewer components as shown, or combinations of certain components.

[0117] The following describes the computer-readable storage medium provided in the embodiments of the present invention. The computer-readable storage medium described below can be referred to in correspondence with the false target filtering method described above.

[0118] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described false target filtering method.

[0119] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0121] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0122] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0123] The foregoing has provided a detailed description of a method, apparatus, device, and readable storage medium for filtering false targets provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for filtering false targets, characterized in that, include: Target information is obtained through a single camera on the vehicle. The target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes; Determine whether the target meets the criteria for judging a false target based on the target information; If the conditions are met, the actual vehicle speed and the virtual vehicle speed calculated based on the target are obtained, and it is determined whether the target is a false target based on the magnitude of the actual vehicle speed and the virtual vehicle speed. If the target is a false target, then the target will be filtered out.

2. The false target filtering method according to claim 1, characterized in that, Determining whether the target meets the criteria for judging a false target based on the target information includes: If the longitudinal distance exceeds a preset distance threshold and the duration does not exceed a preset duration threshold, then the target satisfies the false target judgment condition. Alternatively, if the change in the longitudinal distance of the target exceeds a preset distance range threshold, then the target satisfies the false target judgment condition; Alternatively, if the change in the absolute longitudinal velocity of the target exceeds a preset velocity amplitude threshold, then the target satisfies the false target judgment condition.

3. The method for filtering false targets according to claim 1, characterized in that, Obtaining the vehicle's actual speed and the vehicle's virtual speed calculated based on the target includes: The actual vehicle speed of the current frame is obtained through the vehicle's controller local area network; The virtual vehicle speed of the current frame is calculated using the longitudinal distance and absolute longitudinal velocity of the target consecutive frames.

4. The method for filtering false targets according to claim 1, characterized in that, Determining whether the target is a false target based on the magnitude of the vehicle's actual speed and its virtual speed includes: The speed ratio is calculated based on the actual speed of the vehicle and the virtual speed of the vehicle. When the speed ratio is greater than a first preset speed ratio threshold, or the speed ratio is less than a second preset speed ratio threshold, the target is recorded as having speed-distance inconsistency; the first preset speed ratio threshold is greater than the second preset speed ratio threshold. If the number of times the target's speed and distance are inconsistent exceeds a preset threshold, then the target is a false target.

5. The false target filtering method according to claim 4, characterized in that, After calculating the speed ratio based on the actual vehicle speed and the virtual vehicle speed, the method further includes: If the absolute longitudinal velocity of the target is less than a preset velocity threshold, the target is recorded as having velocity-distance inconsistency.

6. The method for filtering false targets according to claim 1, characterized in that, If the target is a false target, after filtering the target, the method further includes: Continuously acquire target information of the target; When it is determined from the target information that the target does not meet the false target judgment condition, the filtered target is the real target.

7. The method for filtering false targets according to claim 1, characterized in that, If the target is a false target, after filtering the target, the method further includes: If the number of times the target's speed and distance are inconsistent does not exceed a preset threshold within a preset time period, then the filtered target is the real target.

8. A decoy target filtering device, characterized in that, include: The information acquisition module is used to acquire target information of the target through the vehicle's single camera; The target information includes the longitudinal distance between the vehicle and the target, the duration of the target's continuous appearance, and the magnitude of the target's changes; The first judgment module is used to determine whether the target meets the false target judgment condition based on the target information; The second judgment module is used to obtain the actual vehicle speed and the virtual vehicle speed calculated based on the target if the conditions are met, and to determine whether the target is a false target based on the magnitude of the actual vehicle speed and the virtual vehicle speed. A filtering module is used to filter out targets if they are false targets.

9. A decoy target filtering device, characterized in that, include: Memory, used to store computer programs; A processor for implementing the false target filtering method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when loaded and executed by a processor, implement the false target filtering method as described in any one of claims 1 to 7.

Images