Target screening methods, devices, equipment, media and vehicles

Abstract

This disclosure relates to a target selection method, apparatus, device, medium, and vehicle. The target selection method includes: acquiring attribute information corresponding to multiple detected targets; and selecting a first target corresponding to automatic emergency braking control from the multiple targets based on attribute information related to automatic emergency braking control, wherein the attribute information related to automatic emergency braking control includes attribute information used to analyze the probability of a collision between the target and the vehicle. It is evident that adopting the above technical solution can reduce the load on the bus, improve the availability of targets uploaded to the control system, accelerate the decision-making of the control system, and thus improve the timeliness of decision-making.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and more particularly to a target screening method, apparatus, device, medium, and vehicle. Background Technology

[0002] With the development of vehicle technology, vehicles are usually equipped with detection devices (such as millimeter-wave radar) to detect targets around the vehicle and upload the information of the detected targets to the vehicle's control system. The control system can then make effective decisions based on the received target information, such as braking, turning, or deceleration.

[0003] Currently, detection equipment typically uploads the attribute information of all detected targets, resulting in a large load on the bus. Furthermore, since many of the uploaded target attribute information is unusable, the target availability rate is low, which is not conducive to timely decision-making by the control system. Summary of the Invention

[0004] To address the aforementioned technical problems, this disclosure provides a target screening method, apparatus, equipment, medium, and vehicle.

[0005] Firstly, this disclosure provides a target screening method, including:

[0006] Obtain the attribute information corresponding to each of the detected targets;

[0007] Based on the attribute information related to automatic emergency braking control, the first target corresponding to automatic emergency braking control is selected from multiple targets. The attribute information related to automatic emergency braking control includes attribute information used to analyze the probability of a collision between the target and the vehicle.

[0008] Secondly, this disclosure provides a target screening device, comprising:

[0009] The acquisition module is used to acquire the attribute information corresponding to the multiple detected targets.

[0010] The first filtering module is used to filter out the first target corresponding to automatic emergency braking control from multiple targets based on the attribute information related to automatic emergency braking control in the attribute information. The attribute information related to automatic emergency braking control includes attribute information used to analyze the probability of the target colliding with the vehicle.

[0011] Thirdly, this disclosure provides an electronic device, including:

[0012] processor;

[0013] Memory, used to store executable instructions;

[0014] The processor is used to read executable instructions from memory and execute the executable instructions to implement the target screening method described in the first aspect.

[0015] Fourthly, this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the target screening method described in the first aspect.

[0016] Fifthly, this disclosure provides a vehicle comprising at least one of the following:

[0017] The target screening device described in the second aspect;

[0018] The electronic equipment described in the third aspect;

[0019] The computer-readable storage medium described in the fourth aspect.

[0020] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0021] The target screening method, apparatus, device, and medium of this disclosure can acquire attribute information corresponding to multiple detected targets. Based on the attribute information related to automatic emergency braking control, a first target corresponding to automatic emergency braking control is selected from the multiple targets. The attribute information related to automatic emergency braking control includes attribute information used to analyze the probability of a collision between the target and the vehicle. Therefore, by adopting the above technical solution, a first target with a high probability of colliding with the vehicle and suitable for automatic emergency braking control can be selected based on the attribute information related to automatic emergency braking control. This allows the attribute information of the selected first target to be uploaded to the control system instead of uploading the attribute information of all targets. This reduces the load on the bus, increases the availability of targets uploaded to the control system, speeds up the control system's decision-making, and improves the timeliness of decision-making. Attached Figure Description

[0022] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0023] Figure 1 A flowchart illustrating a target screening method provided in an embodiment of this disclosure is shown;

[0024] Figure 2 This illustration shows a schematic diagram of the distribution of a first target, a second target, and a third target according to an embodiment of the present disclosure;

[0025] Figure 3 A flowchart illustrating another target screening method provided in an embodiment of this disclosure is shown;

[0026] Figure 4 A flowchart illustrating another target screening method provided in an embodiment of this disclosure is shown;

[0027] Figure 5 A schematic diagram of the structure of a target screening device provided in an embodiment of this disclosure is shown;

[0028] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0029] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0030] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0031] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0032] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0033] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0034] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0035] To address the aforementioned problems, this disclosure provides a target screening method, apparatus, device, medium, and vehicle. The target screening method provided by this disclosure will be described first.

[0036] Figure 1 A flowchart illustrating a target screening method provided in an embodiment of this disclosure is shown.

[0037] In some embodiments of this disclosure, Figure 1 The target selection method shown can be executed by a target selection device, which can be implemented by software and / or hardware and integrated into a detection device capable of detecting targets around the vehicle, such as millimeter-wave radar, but is not limited thereto.

[0038] like Figure 1 As shown, the target screening method may include the following steps.

[0039] S110. Obtain the attribute information corresponding to the multiple detected targets.

[0040] Specifically, the target can be any target around the vehicle equipped with the detection device, such as vehicles, bicycles, pedestrians, manhole covers, road boundaries, etc., but is not limited to these.

[0041] Specifically, the attribute information may include at least one of the following: location information, motion information, type, probability of movement, probability of existence, probability of obstacle, overlap rate, size information, scattering area, and / or collision probability, but is not limited to these.

[0042] Location information may include at least one of the following: the X-axis distance (i.e., longitudinal distance) between the target and the vehicle, the standard deviation of the X-axis distance, the Y-axis distance (i.e., lateral distance) between the target and the vehicle, the standard deviation of the Y-axis distance, and / or the Z-axis distance (i.e., vertical distance) between the target and the ground. The X, Y, and Z axes are mutually perpendicular. The X-axis can be the vehicle's driving direction (i.e., the vehicle's front-to-back direction), the Y-axis can be perpendicular to the driving direction and parallel to the road surface where the vehicle is located (i.e., the vehicle's left-to-right direction), and the Z-axis can be perpendicular to the road surface where the vehicle is located. However, it is not limited to these.

[0043] Motion information may include at least one of the following: the target's X-axis velocity, X-axis acceleration, standard deviation of X-axis velocity, standard deviation of X-axis acceleration, the target's Y-axis velocity, Y-axis acceleration, standard deviation of Y-axis velocity, standard deviation of Y-axis acceleration, etc., but is not limited to these.

[0044] Types are used to characterize the classification of targets, such as trucks, cars, two-wheeled vehicles, guardrails, etc., but are not limited to these.

[0045] Movement probability is used to characterize the probability that a target is in a moving state relative to the ground.

[0046] Existence probability is used to characterize the probability that a target is a real target (as opposed to a virtual target).

[0047] Obstacle probability is used to characterize the probability that a target will obstruct the vehicle's movement.

[0048] The overlap rate is used to characterize the degree of overlap between the target and the vehicle in the Y direction. For example, when the target is directly in front of the vehicle in the direction of travel, the overlap rate is 100%.

[0049] Size information may include at least one of the following: the length, width, and height of the target.

[0050] The scattering area is used to characterize the intensity of the probe wave reflected back from the target after the probe device emits a probe wave to the target.

[0051] Collision probability is used to characterize the probability of a collision between a target and the vehicle.

[0052] In some embodiments, S110 may include receiving attribute information of multiple targets sent by the detection module.

[0053] Specifically, the vehicle is equipped with detection equipment, which includes a target filtering device and a detection module that can detect targets around the vehicle. The detection module can transmit the attribute information of multiple detected targets to the target filtering device.

[0054] S120. Based on the attribute information related to automatic emergency braking control in the attribute information, select the first target corresponding to automatic emergency braking control from multiple targets.

[0055] Specifically, the attribute information related to automatic emergency braking control refers to attribute information that can be used to analyze the probability of a collision between the target and the vehicle. For example, it may include at least one of the following: movement probability, type, presence probability, obstacle probability, position information, motion information, and overlap rate, but is not limited to these.

[0056] Specifically, the first objective is the target selected by the Automatic Emergency Braking (AEB) system so that the AEB system (part of the control system) in the vehicle can make decisions based on the first objective, thereby realizing the AEB function.

[0057] In some embodiments, S120 may include: selecting, from multiple targets, a target with an overlap rate greater than a second overlap rate threshold and the smallest X-direction distance as a first target based on the overlap rate and X-direction distance in the attribute information.

[0058] Specifically, the specific value of the second overlap rate threshold can be set by those skilled in the art according to the actual situation, and is not limited here.

[0059] This embodiment of the disclosure can acquire attribute information corresponding to multiple detected targets; based on the attribute information related to automatic emergency braking control, a first target corresponding to automatic emergency braking control is selected from the multiple targets. It is evident that by adopting the above technical solution, a first target that can be used for reference by automatic emergency braking control can be selected based on the attribute information related to automatic emergency braking control. This allows the attribute information of the selected first target to be uploaded to the control system instead of uploading the attribute information of all targets to the control system. This reduces the load on the bus, increases the availability of targets uploaded to the control system, accelerates the decision-making of the control system, and thus improves the timeliness of decision-making.

[0060] In another embodiment of this disclosure, S120 may include:

[0061] S121. Based on the movement probability in the attribute information, multiple targets are divided into static targets and moving targets.

[0062] Specifically, if the target's probability of movement is greater than a movement probability threshold, the target is determined to be a moving target; if the target's probability of movement is less than or equal to the movement probability threshold, the target is determined to be a static target. The specific value of the movement probability threshold can be set by those skilled in the art based on actual circumstances, and is not limited here.

[0063] S122. Based on the type, existence probability and obstacle probability in the attribute information, select at least one first candidate target from the moving targets that belongs to the key type, has an existence probability greater than the first existence probability threshold, and has an obstacle probability greater than the first obstacle probability threshold.

[0064] Specifically, key types may include, but are not limited to, large trucks, cars, and / or two-wheeled vehicles.

[0065] Specifically, the specific values ​​of the first existence probability threshold and the first obstacle probability threshold can be set by those skilled in the art according to the actual situation, and are not limited here. For example, the first existence probability threshold can be 0.4, and the first obstacle probability threshold can be 0.4.

[0066] S123. Based on the vehicle's motion information and the position and motion information in the attribute information, filter out first candidate targets that have a Y-direction opposite motion trend to the vehicle and are traveling in the opposite direction to the vehicle from at least one first candidate target, leaving at least one second candidate target.

[0067] Specifically, as mentioned above, the Y-direction, or the left-right direction of the vehicle, has a tendency to move away from the vehicle in the Y-direction, that is, it has a tendency to move away from the vehicle in the lateral direction.

[0068] Specifically, "to travel in the opposite direction of one's own vehicle" means "to travel towards the opposite direction of one's own vehicle".

[0069] In some embodiments, S123 may include: based on the X-axis and Y-axis speeds of the vehicle, and the X-axis and Y-axis speeds in the attribute information, if the Y-axis speed of the first candidate target is detected to be opposite to the Y-axis speed of the vehicle, then the first candidate target is determined to have a Y-axis diverging motion trend from the vehicle, and the first candidate target is filtered out; if the X-axis speed of the target is detected to be opposite to the X-axis speed of the vehicle, then the first candidate target is determined to be traveling in the opposite direction to the vehicle, and the first candidate target is filtered out.

[0070] Understandably, if the target and the vehicle exhibit a Y-axis divergence, it indicates the target is beginning to deviate laterally, making a collision unlikely. This is less useful for AEB (Autonomous Emergency Braking) and can therefore be filtered out. Similarly, if the target is traveling in opposite directions, it indicates a collision with the vehicle. Since vehicles traveling in opposite directions are typically in different lanes, the probability of a collision is also low, making AEB less useful and thus filtering out the target as well. This avoids uploading useless targets with a very low probability of collision to AEB.

[0071] In other embodiments, S123 may include: filtering out first candidate targets that have a Y-direction opposite motion trend to the vehicle and are traveling in the opposite direction to the vehicle from at least one first candidate target based on the vehicle's yaw angle and steering angle, Y-direction distance and X-direction distance in the position information, and Y-direction velocity and X-direction velocity in the motion information.

[0072] Specifically, the yaw angle refers to the angle at which a vehicle rotates around its Z-axis, which is perpendicular to the ground. The steering angle is the angle formed by the centerline of a vehicle when the front wheels are turned to their extreme left or right positions and the front wheels do not deflect.

[0073] Understandably, judging whether a target has a Y-direction diverging trend from the vehicle or is traveling in the opposite direction based on the vehicle's yaw and steering angles, Y-direction and X-direction distances in position information, and Y-direction and X-direction velocities in motion information can make the reference factors for analysis and judgment more comprehensive, thereby improving the accuracy of judgment and thus improving the accuracy of screening second candidate targets.

[0074] S124. Based on the existence probability and obstacle probability in the attribute information, select at least one third candidate target from the static targets whose existence probability is greater than the first existence probability threshold and whose obstacle probability is greater than the first obstacle probability threshold.

[0075] S125. Based on the X-direction distance and overlap rate in the attribute information, select the target with the overlap rate greater than the first overlap rate threshold and the smallest X-direction distance from at least one second candidate target and at least one third candidate target as the first target.

[0076] Specifically, the specific value of the first overlap rate threshold can be set by those skilled in the art according to the actual situation, and is not limited here. For example, the first overlap rate threshold is 0.4, etc., but it is not limited to this.

[0077] For example, Figure 2 A schematic diagram illustrating the distribution of a first target, a second target, and a third target according to an embodiment of this disclosure is shown. See also... Figure 2 After filtering multiple targets corresponding to vehicle Z, the first target P0 can be selected.

[0078] Understandably, when the overlap rate of a target is greater than the first overlap rate threshold, it indicates that the target is close to the vehicle or overlaps with the vehicle laterally, and the probability of the vehicle colliding with such a target is high. Furthermore, the smaller the longitudinal distance between the target and the vehicle, the easier it is to collide. Therefore, by setting the X-direction distance and overlap rate based on the attribute information, selecting the target with the smallest X-direction distance and the larger overlap rate than the first overlap rate threshold from at least one second candidate target and at least one third candidate target as the first target is beneficial to selecting targets with a relatively higher probability of colliding with the vehicle, thus improving the accuracy of the first target selection.

[0079] Understandably, by filtering out first-candidate targets that exhibit a Y-direction divergence from the vehicle or are traveling in the opposite direction from at least one first-candidate target, at least one second-candidate target remains. Furthermore, from static targets, at least one third-candidate target with a probability of existence greater than the first existence probability threshold and an obstacle probability greater than the first obstacle probability threshold is selected. This allows for the initial filtering out of a large number of targets with a very low probability of colliding with the vehicle. This significantly reduces the base number of targets encountered during subsequent filtering and minimizes the interference of such targets on subsequent filtering. Moreover, by selecting targets with an overlap rate greater than the first overlap rate threshold and the smallest X-direction distance from at least one second-candidate target and at least one third-candidate target based on the X-direction distance and overlap rate in the attribute information, targets with a relatively higher probability of colliding with the vehicle can be selected as the first target. This improves the speed and accuracy of first-target selection.

[0080] Figure 3 This illustration shows a flowchart of another target screening method provided by an embodiment of the present disclosure. The embodiments of the present disclosure are optimizations based on the above embodiments, and can be combined with various optional solutions from one or more of the above embodiments.

[0081] S310. Obtain the attribute information corresponding to the multiple detected targets.

[0082] Specifically, S310 is similar to S110, and will not be described in detail here.

[0083] S320. Based on the attribute information related to automatic emergency braking control in the attribute information, select the first target corresponding to automatic emergency braking control from multiple targets.

[0084] Specifically, S320 is similar to S120, and will not be described in detail here.

[0085] S330. Based on the attribute information related to adaptive cruise control in the attribute information, select at least one second target corresponding to adaptive cruise control from multiple targets.

[0086] Specifically, the attribute information related to adaptive cruise control refers to attribute information that can be used to analyze the probability of a target affecting the vehicle's driving. For example, it may include at least one of the following: type, probability of presence, probability of obstacle, location information, motion information, etc., but is not limited to these.

[0087] Specifically, the second objective is the target selected by Adaptive Cruise Control (ACC) so that the ACC system (part of the control system) in the vehicle can make decisions based on the second objective, thereby realizing the ACC function.

[0088] In some embodiments, S330 may include: based on the type, existence probability, and obstacle probability in the attribute information, selecting from the plurality of targets a target that belongs to a key type, has an existence probability greater than a third existence probability threshold, and has an obstacle probability greater than a third obstacle probability threshold as a second target.

[0089] Specifically, the specific types of key types, the third existence probability threshold, and the specific values ​​of the third obstacle probability threshold can be set by those skilled in the art according to the actual situation, and are not limited here.

[0090] In this embodiment of the disclosure, by being able to filter at least one second target corresponding to adaptive cruise control from multiple targets based on attribute information related to adaptive cruise control in the attribute information, the control system can be provided with a richer set of useful targets for adaptive cruise control reference, thereby enabling the control system to make better decisions.

[0091] In another embodiment of this disclosure, S330 may include:

[0092] S331. Based on the type, existence probability, and obstacle probability in the attribute information, select at least one fourth candidate target from multiple targets that belongs to the key type, has an existence probability greater than the second existence probability threshold, and has an obstacle probability greater than the second obstacle probability threshold.

[0093] Specifically, the specific types of key types can be set by those skilled in the art according to the actual situation, and are not limited here. For example, key types may include large trucks, cars, and / or two-wheeled vehicles, but are not limited to these.

[0094] Specifically, the specific values ​​of the second existence probability threshold and the second obstacle probability threshold can be set by those skilled in the art according to the actual situation, and are not limited here. For example, the second existence probability threshold is 0.4, the second obstacle probability threshold is 0.4, etc., but are not limited to this.

[0095] Understandably, when the probability of a target's existence is less than or equal to the second probability threshold, it indicates that the target is likely a virtual target, i.e., not a real target. Such targets are unlikely to affect the vehicle's driving, and filtering out such targets can further improve the target's availability.

[0096] Understandably, when the obstacle probability of a target is less than or equal to the second obstacle probability threshold, it indicates that the target is less likely to obstruct the target vehicle's movement. Filtering out such targets can further improve the availability of the target.

[0097] S332. Based on the motion information in the attribute information, select at least one fifth candidate target from at least one fourth candidate target whose combination probability is greater than the first combination probability threshold.

[0098] The combined probability is obtained by weighting the entry probability of the fourth candidate target entering the lane, the exit probability of the fourth candidate target exiting the lane, and the retention probability of the fourth candidate target remaining in the original lane.

[0099] Specifically, based on the motion information in the attribute information, the cut-in probability, cut-out probability, and hold probability of each fourth candidate target are calculated; for each fourth candidate target, its corresponding cut-in probability, cut-out probability, and hold probability are weighted and combined to obtain the combined probability of each fourth candidate target; from at least one fourth candidate target, the target with a combined probability greater than the first combined probability threshold is selected as the fifth candidate target.

[0100] For example, the combination probability can be calculated using the following formula: Combination probability = m * cut-in probability * n * cut-out probability * z * lane-keeping probability, where m is the weight of the cut-in probability, the cut-in probability is the cut-in probability, n is the weight of the cut-out probability, the cut-out probability is the cut-out probability, z is the weight of the lane-keeping probability, and the lane-keeping probability is the lane-keeping probability, and m > z > n.

[0101] Specifically, the specific value of the first combination probability threshold can be set by those skilled in the art according to the actual situation, and is not limited here. For example, the first combination probability is 0.4, but it is not limited to this.

[0102] Understandably, the applicant considers that vehicles frequently change lanes during driving. Therefore, vehicles in adjacent lanes may merge into the vehicle's own lane, and vehicles in the vehicle's own lane may merge out of the lane. Thus, vehicles in the vehicle's own lane and adjacent lanes should be the primary focus of ACC (Adaptive Cruise Control). Based on this, this embodiment of the disclosure uses weighted combinations of the probability of merging, merging out, and maintaining the vehicle to obtain a combined probability, enabling the prediction of the likelihood of a vehicle merging. Furthermore, the applicant considers that vehicles merging into the vehicle's own lane have a higher probability of obstructing the vehicle's movement, vehicles remaining in the original lane have a second lower probability of obstructing the vehicle's movement, and vehicles merging out of the vehicle's own lane have the lowest probability of obstructing the vehicle's movement. Therefore, the focus should be on screening vehicles with a higher probability of merging. Based on this, this embodiment of the disclosure uses a weight greater than the weight of the probability of merging into the lane and a weight greater than the weight of the probability of maintaining the vehicle's movement, making the probability of merging into the lane have a greater impact on the combined probability. This is beneficial for focusing on screening vehicles with a higher probability of merging into the lane, i.e., for screening vehicles more likely to obstruct the vehicle's movement, thereby improving the accuracy of the second target screening.

[0103] S333. Based on the X-direction distance and Y-direction distance in the attribute information, select at least one second target from at least one fifth candidate target whose X-direction distance satisfies the first condition.

[0104] The key lanes include the starting lane and the adjacent lane. The starting lane is the lane where the vehicle is located, and the adjacent lane is the lane next to the starting lane.

[0105] In some embodiments, S333 may include: determining the lane where each fifth candidate target is located based on the Y-direction distance in the attribute information; for at least one fifth candidate target, filtering from each key lane according to the X-direction distance from smallest to largest until a first number of second targets are filtered out or at least one fifth candidate target is traversed.

[0106] Specifically, the specific value of the first quantity can be set by those skilled in the art according to the actual situation, and is not limited here. For example, the first quantity may be 2, but it is not limited to this.

[0107] Specifically, the target selection device can construct a lane line model and determine the lane based on the vehicle's position and motion information. In this way, the lane where each fifth candidate target is located can be determined based on the Y-direction distance in the attribute information.

[0108] Specifically, for each critical lane, from the fifth candidate targets located in that critical lane, the selection is carried out in ascending order of distance in the X direction until a first number of second targets are selected or all the fifth candidate targets located in that critical lane are traversed.

[0109] For example, see [link to example]. Figure 2 After filtering multiple targets corresponding to the vehicle in lane Z, for lane Z, the target P0 closest to the vehicle in the X direction can be selected as the second target, and the target P1 closest to the vehicle in the X direction can be selected as the second target; for lane Z, the target P2 closest to the vehicle in the X direction can be selected as the second target, and the target P3 closest to the vehicle in the X direction can be selected as the second target; for lane Z, the target P4 closest to the vehicle in the X direction can be selected as the second target, and the target P5 closest to the vehicle in the X direction can be selected as the second target.

[0110] Understandably, by filtering from each key lane according to the distance in the X direction from smallest to largest until a first number of second targets are selected or at least one fifth candidate target is traversed, the targets that are relatively more likely to obstruct the vehicle's movement in each key lane can be selected, which helps to improve the comprehensiveness and accuracy of the second target selection.

[0111] In other embodiments, S333 may include: determining the lane where each fifth candidate target is located based on the Y-direction distance in the attribute information; and selecting targets located in key lanes and whose X-direction distance is less than a first X-direction distance threshold from at least one fifth candidate target as second targets.

[0112] Specifically, the specific value of the first X-direction distance threshold can be set by those skilled in the art according to the actual situation, and is not limited here.

[0113] Understandably, by selecting at least one fourth candidate target from multiple targets that belongs to the critical type, has an existence probability greater than a second existence probability threshold, and an obstacle probability greater than a second obstacle probability threshold, and then selecting at least one fifth candidate target from at least one fourth candidate target whose combination probability is greater than a first combination probability threshold, and further selecting at least one second target from at least one fifth candidate target whose X-direction distance satisfies the first condition, multiple targets can be screened layer by layer. During this layer-by-layer screening process, targets with a lower probability of obstructing the vehicle's movement are first filtered out. This significantly reduces the base number of targets encountered in subsequent screenings and minimizes the interference of such targets on subsequent screenings. Furthermore, targets with a relatively higher probability of obstructing the vehicle's movement can be selected as second targets. This improves the speed and accuracy of second target screening.

[0114] Figure 4 This illustration shows a flowchart of another target screening method provided by an embodiment of the present disclosure. This embodiment of the present disclosure is an optimization based on the above embodiments, and can be combined with various optional solutions from one or more of the above embodiments.

[0115] S410. Obtain the attribute information corresponding to the multiple detected targets.

[0116] Specifically, S410 is similar to S110, and will not be described in detail here.

[0117] S420. Based on the attribute information related to automatic emergency braking control in the attribute information, select the first target corresponding to automatic emergency braking control from multiple targets.

[0118] Specifically, S420 is similar to S120, and will not be described in detail here.

[0119] S430. Based on the location information and movement probability in the attribute information, select at least one third target corresponding to the key scene from multiple targets.

[0120] Specifically, the first and second targets are those with a higher potential threat level to the vehicle, selected based on functionality (AEB and ACC functions). The applicant also considered that, in addition to these, a third target with a lower potential threat level could be selected based on scenarios. This would provide the vehicle's control system with sufficient targets for comprehensive analysis, leading to a more accurate decision. When selecting the third target based on scenarios, key scenarios considered could include at least one of the following: potential threat targets in non-primary areas and road edge mapping scenarios; scenarios involving lateral movement, long-distance target tracking, and stationary obstacles (such as fences, walls, etc.), etc., but are not limited to these.

[0121] In some embodiments, S430 may include: filtering out a first target and a second target from a plurality of targets; and selecting, based on the X-direction distance and Y-direction distance, a target whose X-direction distance is less than a second X-direction distance threshold and whose Y-direction distance is less than a first Y-direction distance threshold from the remaining targets after filtering out the first target and the second target as a third target.

[0122] Specifically, the specific values ​​of the second X-direction distance threshold and the distance less than the first Y-direction threshold can be set by those skilled in the art according to the actual situation, and are not limited here.

[0123] This disclosure embodiment, by being able to filter at least one third target corresponding to a key scenario from multiple targets based on location information and movement probability in attribute information, can provide the control system with richer and more useful targets, so that the control system can make better decisions.

[0124] In another embodiment of this disclosure, S430 may include:

[0125] S431. Filter out the first and second targets from multiple targets, leaving at least one sixth candidate target.

[0126] In this way, the third objective selected in the final selection will not overlap with the functional objectives (i.e., the first and second objectives).

[0127] S432. Based on the location information in the attribute information, select at least one seventh candidate target from at least one sixth candidate target that is located in the fan-shaped area corresponding to the vehicle and in the key lane.

[0128] The fan-shaped area is the area in front of the vehicle with the vehicle as the center and the effective detection distance as the radius. The key lanes include the vehicle lane and the adjacent lane.

[0129] Specifically, the effective detection distance is the distance corresponding to the detection accuracy of the detection device reaching the accuracy threshold.

[0130] Detection equipment, such as lidar, can typically detect targets whose straight-line distance from the vehicle is less than a first distance. However, the detection accuracy varies. The detection accuracy is relatively high for targets whose straight-line distance from the vehicle is less than the effective detection distance, and relatively low for targets whose straight-line distance from the vehicle is greater than or equal to the effective detection distance.

[0131] Specifically, the included angle of the sector is the field of view (FOV) of the detection equipment.

[0132] Specifically, based on the Y-direction distance and Y-direction distance in the attribute information, the radial distance (i.e., straight-line distance) between each sixth candidate target and the vehicle is calculated using the Pythagorean theorem; for each sixth candidate target, if the radial distance of the sixth candidate target is detected to be less than the effective distance, it is determined that the sixth candidate target is located within the fan-shaped area corresponding to the vehicle; based on the Y-direction distance in the attribute information, the lane in which each sixth candidate target is located is determined, thereby selecting targets located within the fan-shaped area corresponding to the vehicle and in the key lane as the seventh candidate target.

[0133] Understandably, by selecting at least one seventh candidate target located in the fan-shaped area corresponding to the vehicle and in the critical lane, the third target can be selected from areas with higher detection accuracy and areas with greater impact on the vehicle (i.e., critical lanes), thereby further improving the availability of the third target selected subsequently.

[0134] S433. Based on the position information and movement probability in the attribute information, filter from at least one seventh candidate target that belongs to the static target in ascending order of radial distance until a second number of third targets are selected or at least one seventh candidate target that belongs to the static target is traversed.

[0135] The radial distance is the straight-line distance between the target and the vehicle.

[0136] Specifically, based on the movement probability in the attribute information, the at least one seventh candidate target can be divided into static targets and moving targets.

[0137] If the movement probability of the seventh candidate target is greater than the movement probability threshold, then the seventh candidate target is determined to be a moving target, that is, the seventh candidate target belonging to the moving target category; if the movement probability of the seventh candidate target is less than or equal to the movement probability threshold, then the seventh candidate target is determined to be a static target, that is, the seventh candidate target belonging to the static target category.

[0138] Specifically, the specific value of the second quantity can be set by those skilled in the art according to the actual situation, and is not limited here. For example, the second quantity can be 9, etc., but is not limited to this.

[0139] S434. Based on the position information and movement probability in the attribute information, filter from at least one seventh candidate target that belongs to the moving target in ascending order of radial distance until a third number of third targets are selected or at least one seventh candidate target that belongs to the moving target is traversed.

[0140] Specifically, the specific value of the third quantity can be set by those skilled in the art according to the actual situation, and is not limited here. For example, the third quantity can be 9, etc., but is not limited to this.

[0141] Understandably, by selecting at least one seventh candidate target from at least one sixth candidate target that is located in the fan-shaped area corresponding to the vehicle and in the key lane, targets with high attribute information accuracy and significant impact on the vehicle's driving can be selected. Furthermore, by selecting from at least one seventh candidate target that is a static target in ascending order of radial distance until a second number of third targets are selected or at least one seventh candidate target that is a static target is traversed, and by selecting from at least one seventh candidate target that is a moving target in ascending order of radial distance until a third number of third targets are selected or at least one seventh candidate target that is a moving target is traversed, targets with relatively greater impact on the vehicle's driving can be further selected, and the selected third targets can include both static and moving targets to improve the comprehensiveness and richness of the third targets.

[0142] In another embodiment of this invention, S430 may further include: S435, if the number of selected third targets belonging to static targets is less than the second number, based on the position information and movement probability in the attribute information, filtering from the remaining seventh candidate targets belonging to static targets after filtering at least one seventh candidate target in ascending order of radial distance until the number of all selected third targets belonging to static targets reaches the second number or all remaining seventh candidate targets belonging to static targets have been traversed; and / or; S436, if the number of selected third targets belonging to moving targets is less than the third number, based on the position information and movement probability in the attribute information, filtering from the remaining seventh candidate targets belonging to moving targets after filtering at least one seventh candidate target in ascending order of radial distance until the number of all selected third targets belonging to moving targets reaches the third number or all remaining seventh candidate targets belonging to moving targets have been traversed.

[0143] Optionally, the method further includes: if the number of third targets belonging to static targets selected through S433 and S435 is still less than the second number, based on the position information and movement probability in the attribute information, selecting at least one tenth candidate target located outside the fan-shaped area corresponding to the vehicle from at least one sixth candidate target, and selecting from at least one tenth candidate target in ascending order of radial distance until the number of all selected third targets belonging to static targets reaches the second number or the remaining seventh candidate targets belonging to static targets have been traversed; and / or; if the number of third targets belonging to moving targets selected through S434 and S436 is less than the third number, based on the position information and movement probability in the attribute information, selecting at least one tenth candidate target located outside the fan-shaped area corresponding to the vehicle from at least one sixth candidate target, and selecting from at least one tenth candidate target in ascending order of radial distance until the number of all selected third targets belonging to moving targets reaches the second number or the remaining seventh candidate targets belonging to moving targets have been traversed.

[0144] For example, see Figure 2 After screening multiple targets, nine third targets belonging to static targets (labeled S1-S9 respectively) and nine third targets belonging to moving targets (labeled M1-M9 respectively) can be selected.

[0145] Understandably, when the number of third targets identified in areas with a significant impact on the vehicle (i.e., critical lanes) is small, supplementary screening can be conducted in areas with a relatively smaller impact on the vehicle. If the number of third targets obtained after supplementary screening is still insufficient, supplementary screening can continue in areas with relatively low detection accuracy, thereby identifying a sufficient number of third targets to provide the control system with enough decision-making basis.

[0146] Figure 5 A schematic diagram of the structure of a target screening device provided in an embodiment of the present disclosure is shown.

[0147] In some embodiments of this disclosure, Figure 5 The target screening device shown can be applied to detection equipment, and there are no specific limitations on its application.

[0148] like Figure 5 As shown, the target screening device 500 may include:

[0149] The acquisition module 510 is used to acquire the attribute information corresponding to the multiple detected targets respectively;

[0150] The first filtering module 520 is used to filter out the first target corresponding to automatic emergency braking control from multiple targets based on the attribute information related to automatic emergency braking control in the attribute information. The attribute information related to automatic emergency braking control includes attribute information used to analyze the probability of the target colliding with the vehicle.

[0151] In another embodiment of this disclosure, the first screening module 520 includes:

[0152] The segmentation submodule is used to divide multiple targets into static targets and moving targets based on the movement probability in the attribute information;

[0153] The first filtering submodule is used to filter at least one first candidate target from moving targets based on the type, existence probability and obstacle probability in the attribute information. The first candidate target belongs to the key type, has an existence probability greater than the first existence probability threshold, and has an obstacle probability greater than the first obstacle probability threshold.

[0154] The first filtering submodule is used to filter out first candidate targets that have a Y-direction opposite motion trend to the vehicle and are traveling in the opposite direction to the vehicle from at least one first candidate target based on the vehicle's motion information and the position and motion information in the attribute information, leaving at least one second candidate target;

[0155] The second filtering submodule is used to filter at least one third candidate target from static targets based on the existence probability and obstacle probability in the attribute information, where the existence probability is greater than the first existence probability threshold and the obstacle probability is greater than the first obstacle probability threshold.

[0156] The third filtering submodule is used to filter out the target with the smallest X-direction distance from at least one second candidate target and at least one third candidate target based on the X-direction distance and overlap rate in the attribute information, and select the target with the overlap rate greater than the first overlap rate threshold and the smallest X-direction distance as the first target.

[0157] In yet another embodiment of this disclosure, the device further includes:

[0158] The second filtering module is used to, after acquiring the attribute information corresponding to the multiple detected targets, filter out at least one second target corresponding to adaptive cruise control from the multiple targets based on the attribute information related to adaptive cruise control. The attribute information related to adaptive cruise control includes attribute information used to analyze the probability of the target affecting the vehicle's driving.

[0159] In another embodiment of this disclosure, the second screening module includes:

[0160] The fourth filtering submodule is used to filter at least one fourth candidate target from multiple targets based on the type, existence probability and obstacle probability in the attribute information. The fourth candidate target belongs to the key type, has an existence probability greater than the second existence probability threshold and an obstacle probability greater than the second obstacle probability threshold.

[0161] The fifth filtering submodule is used to filter at least one fifth candidate target from at least one fourth candidate target based on the motion information in the attribute information, where the combined probability is greater than the first combined probability threshold. The combined probability is obtained by weighting the fourth candidate target’s entry probability from the lane, exit probability from the lane, and retention probability in the original lane.

[0162] The sixth filtering submodule is used to filter at least one second target from at least one fifth candidate target based on the X-direction distance and Y-direction distance in the attribute information. The second target is located in the critical lane and the X-direction distance satisfies the first condition. The critical lane includes the lane itself and the adjacent lane.

[0163] In another embodiment of this disclosure, the sixth screening submodule includes:

[0164] The determination unit is used to determine the lane where each fifth candidate target is located based on the Y-direction distance in the attribute information;

[0165] The filtering unit is used to filter from each key lane according to the X-direction distance from small to large for at least one fifth candidate target until a first number of second targets are selected or at least one fifth candidate target has been traversed.

[0166] In another embodiment of this disclosure, the device further includes:

[0167] The third filtering module is used to filter out at least one third target corresponding to the key scene from multiple targets after obtaining the attribute information corresponding to the multiple detected targets, based on the position information and movement probability in the attribute information.

[0168] In another embodiment of this disclosure, the third screening module includes:

[0169] The second filtering submodule is used to filter out the first target and the second target from multiple targets, leaving at least one sixth candidate target;

[0170] The seventh filtering submodule is used to filter at least one seventh candidate target from at least one sixth candidate target based on the location information in the attribute information. The seventh candidate target is located in the fan-shaped area corresponding to the vehicle and in the key lane. The fan-shaped area is the area in front of the vehicle with the vehicle as the center and the effective detection distance as the radius. The key lane includes the vehicle lane and the adjacent lane.

[0171] The eighth filtering submodule is used to filter from at least one seventh candidate target belonging to a static target in ascending order of radial distance based on the position information and movement probability in the attribute information until a second number of third targets are filtered out or at least one seventh candidate target belonging to a static target is traversed. The radial distance is the straight-line distance between the target and the vehicle.

[0172] The ninth filtering submodule is used to filter from at least one seventh candidate target belonging to a moving target according to the radial distance from smallest to largest, based on the position information and movement probability in the attribute information, until a third number of third targets are filtered out or at least one seventh candidate target belonging to a moving target is traversed.

[0173] In another embodiment of this disclosure, the third screening module further includes:

[0174] The tenth filtering submodule is used to filter from the remaining seventh candidate targets belonging to static targets after at least one seventh candidate target has been filtered, in order of increasing radial distance, based on the position information and movement probability in the attribute information if the number of filtered third targets belonging to static targets is less than the second number, until the number of all filtered third targets belonging to static targets reaches the second number or all remaining seventh candidate targets belonging to static targets have been traversed.

[0175] and / or;

[0176] The eleventh filtering submodule is used to filter from the remaining seventh candidate targets belonging to moving targets after at least one seventh candidate target has been filtered, in ascending order of radial distance, based on the position information and movement probability in the attribute information if the number of filtered third targets belonging to moving targets is less than the third number, until the number of all filtered third targets belonging to moving targets reaches the third number or all remaining seventh candidate targets belonging to moving targets have been traversed.

[0177] It should be noted that, Figure 5 The target screening device 500 shown can perform each step in any of the above method embodiments and achieve each process and effect in any of the above method embodiments, which will not be elaborated here.

[0178] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure is shown.

[0179] like Figure 6 As shown, the electronic device may include a controller 601 and a memory 602 storing computer program instructions.

[0180] Specifically, the controller 601 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0181] Memory 602 may include a large-capacity storage for information or instructions. For example, and not limitingly, memory 602 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 602 may include removable or non-removable (or fixed) media. Where appropriate, memory 602 may be internal or external to the integrated gateway device. In a particular embodiment, memory 602 is a non-volatile solid-state memory. In a particular embodiment, memory 602 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (Electrically Programmable ROM, EPROM), an electrically erasable programmable PROM (EEPROM), an electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0182] The controller 601 performs the steps of the target screening method provided in the embodiments of this disclosure by reading and executing computer program instructions stored in the memory 602.

[0183] In one example, the electronic device may also include a transceiver 603 and a bus 604. Wherein, as... Figure 6 As shown, the controller 601, memory 602 and transceiver 603 are connected via bus 604 and communicate with each other.

[0184] Bus 604 includes hardware, software, or both. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 604 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0185] This disclosure also provides a computer-readable storage medium that can store a computer program that, when executed by a processor, causes the processor to implement the target filtering method provided in this disclosure.

[0186] The aforementioned storage medium may, for example, include a memory 602 containing computer program instructions, which can be executed by a controller 601 of an electronic device to perform the target screening method provided in this embodiment. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), compact disc ROM (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0187] This disclosure also provides a vehicle, including at least one of the following:

[0188] The target screening device described above;

[0189] The electronic devices described above;

[0190] The computer-readable storage medium described above.

[0191] It should be noted that, in this document, relational terms 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 term "comprising" is 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 a process, method, article, or apparatus.

[0192] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of target screening, characterized by, The method comprises: obtaining attribute information corresponding to each of a plurality of detected targets; based on attribute information related to automatic emergency braking control, filtering a first target corresponding to automatic emergency braking control from the plurality of targets, wherein the attribute information related to automatic emergency braking control includes attribute information used to analyze the probability of a target colliding with the ego vehicle; the filtering of the first target based on the attribute information related to automatic emergency braking control comprises: based on the movement probability in the attribute information, dividing the plurality of targets into static targets and moving targets; based on the type, existence probability and obstacle probability in the attribute information, filtering at least one first candidate target belonging to a key type, having an existence probability greater than a first existence probability threshold and an obstacle probability greater than a first obstacle probability threshold from the moving targets; based on the motion information of the ego vehicle and the position information and motion information in the attribute information, filtering out, from the at least one first candidate target, a first candidate target having a Y-direction away motion trend from the ego vehicle and a counter-direction driving trend from the ego vehicle, leaving at least one second candidate target; based on the existence probability and obstacle probability in the attribute information, filtering at least one third candidate target having an existence probability greater than the first existence probability threshold and an obstacle probability greater than the first obstacle probability threshold from the static targets; based on the X-direction distance and overlap rate in the attribute information, filtering a target having an overlap rate greater than a first overlap rate threshold and a minimum X-direction distance from the at least one second candidate target and the at least one third candidate target as the first target.

2. The method of claim 1, wherein, After the obtaining of the attribute information corresponding to each of the plurality of detected targets, the method further comprises: based on attribute information related to adaptive cruise control, filtering at least one second target corresponding to adaptive cruise control from the plurality of targets, wherein the attribute information related to adaptive cruise control includes attribute information used to analyze the probability of a target affecting the driving of the ego vehicle.

3. The method of claim 2, wherein, the filtering of the at least one second target based on the attribute information related to adaptive cruise control comprises: based on the type, existence probability and obstacle probability in the attribute information, filtering at least one fourth candidate target belonging to a key type, having an existence probability greater than a second existence probability threshold and an obstacle probability greater than a second obstacle probability threshold from the plurality of targets; based on the motion information in the attribute information, filtering at least one fifth candidate target having a combination probability greater than a first combination probability threshold from the at least one fourth candidate target, wherein the combination probability is obtained by weight combination of a cut-in probability of the fourth candidate target cutting into the ego lane, a cut-out probability of the fourth candidate target cutting out of the ego lane and a keep probability of the fourth candidate target keeping in the original lane; Screening, from the at least one fifth candidate target, the at least one second target located in a key lane and satisfying a first condition in X direction distance based on the attribute information.

4. The method of claim 3, wherein, The screening, from the at least one fifth candidate target, the at least one second target located in a key lane and satisfying a first condition in X direction distance based on the attribute information comprises: Determining, based on Y direction distance in the attribute information, a lane where each fifth candidate target is located; For the at least one fifth candidate target, screening, from each key lane, in X direction distance from small to large until the first number of second targets is screened out or the at least one fifth candidate target is traversed.

5. The method of claim 1, wherein, After the attribute information corresponding to the plurality of detected targets is acquired, the method further comprises: Screening, from the plurality of targets, at least one third target corresponding to a key scene based on position information and a moving probability in the attribute information.

6. The method of claim 5, wherein, The screening, from the plurality of targets, at least one third target corresponding to a key scene based on position information and a moving probability in the attribute information comprises: Filtering out the first target and the second target from the plurality of targets, leaving at least one sixth candidate target; Screening, from the at least one sixth candidate target, at least one seventh candidate target located in a key lane based on position information in the attribute information, wherein the key lane comprises a self lane and a nearby lane; Screening, from at least one seventh candidate target belonging to a static target, in radial distance from small to large until the second number of third targets is screened out or the at least one seventh candidate target belonging to a static target is traversed based on position information and a moving probability in the attribute information, wherein the radial distance is a straight line distance between the target and the ego vehicle; Screening, from at least one seventh candidate target belonging to a moving target, in radial distance from small to large until the third number of third targets is screened out or the at least one seventh candidate target belonging to a moving target is traversed based on position information and a moving probability in the attribute information.

7. The method of claim 6, wherein, Further comprising: If the number of third targets belonging to a static target screened out is less than the second number, screening, from the at least one seventh candidate target belonging to a static target remaining after the screening, in radial distance from small to large until the number of all third targets belonging to a static target screened out reaches the second number or the remaining seventh candidate target belonging to a static target is traversed based on position information and a moving probability in the attribute information; And / or; If the number of the third targets belonging to the moving targets is less than the third number, based on the position information and the moving probability in the attribute information, from the seventh candidate targets belonging to the moving targets remaining after the screening of the at least one seventh candidate target, the seventh candidate targets are screened in a radial distance from small to large until the number of all the third targets belonging to the moving targets screened reaches the third number or the remaining seventh candidate targets belonging to the moving targets are traversed.

8. A target screening apparatus, characterized by, Comprise: An acquisition module, configured to acquire attribute information corresponding to a plurality of targets detected respectively; A first screening module, configured to screen, based on attribute information related to automatic emergency braking control in the attribute information, first targets corresponding to the automatic emergency braking control from the plurality of targets, wherein the attribute information related to the automatic emergency braking control comprises attribute information used to analyze a probability of a target colliding with a host vehicle; The first screening module comprises: a division submodule, configured to divide the plurality of targets into static targets and moving targets based on a moving probability in the attribute information; A first screening submodule, configured to screen, based on a type, a presence probability and an obstacle probability in the attribute information, at least one first candidate target belonging to a key type, having a presence probability greater than a first presence probability threshold and an obstacle probability greater than a first obstacle probability threshold from the moving targets; A first filtering submodule, configured to filter, based on motion information of the host vehicle and position information and motion information in the attribute information, first candidate targets having a Y-direction moving trend away from the host vehicle and driving against the host vehicle from the at least one first candidate target, to leave at least one second candidate target; A second screening submodule, configured to screen, based on a presence probability and an obstacle probability in the attribute information, at least one third candidate target having a presence probability greater than a first presence probability threshold and an obstacle probability greater than a first obstacle probability threshold from the static targets; A third screening submodule, configured to screen, based on an X-direction distance and an overlap rate in the attribute information, a target having a minimum X-direction distance and an overlap rate greater than a first overlap rate threshold from the at least one second candidate target and the at least one third candidate target as the first target.

9. An electronic device, comprising: Comprise: A processor; A memory for storing executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the target screening method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, when the computer program is executed by the processor, so that the processor implements the target screening method of any one of claims 1-7.

11. A vehicle characterized by comprising: Comprise at least one of: The target screening device of claim 8; The electronic device of claim 9; The computer readable storage medium of claim 10.

Images