A vehicle target detection method, device and vehicle

Abstract

The embodiment of the application discloses a vehicle target detection method, device and vehicle, relates to the automatic driving technical field, and is invented to reduce the self-vehicle false deceleration. The detection method comprises the following steps: acquiring a first target detected by a first sensor, and a second target and a third target detected by a second sensor; if the first target and the second target meet fusion conditions, and the third target does not meet the fusion conditions, then the first target and the second target are fused into a main target, and a split inhibition zone in front of the main target is determined; if the third target is in the split inhibition zone, and a longitudinal speed difference between the main target and the third target is within a speed difference threshold range, then the output of the third target is inhibited. The application is suitable for scenarios such as automatic driving.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to a vehicle target detection method, device and vehicle. BACKGROUND

[0002] In the field of automatic driving, correct identification of targets is crucial, but due to sensor limitations and external environmental influences, misidentification often occurs.

[0003] There are often large vehicles on the road, such as large trucks or large buses, etc., which are tens of meters or even dozens of meters long. When an ordinary millimeter wave radar detects such vehicles, the point cloud is sparse and not continuous, which easily causes a large vehicle to be identified as two or even multiple targets that are split, resulting in a large target splitting situation. When the target split from the large target (also referred to as a false target) intrudes into the lane of the ego vehicle, it is easy to cause the ego vehicle to decelerate. SUMMARY

[0004] Therefore, the embodiments of the present application provide a vehicle target detection method, device and vehicle, which are beneficial to reduce the occurrence of the ego vehicle decelerating.

[0005] In a first aspect, the embodiments of the present application provide a vehicle target detection method, which detects a neighboring vehicle target that travels in the same direction as the ego vehicle in the front adjacent lane of the ego vehicle through a first sensor and a second sensor, wherein the first sensor and the second sensor are sensors on the ego vehicle.

[0006] The first target detected by the first sensor, the second target detected by the second sensor and the third target are obtained. It is determined whether the first target, the second target and the third target meet the fusion condition. If the first target and the second target meet the fusion condition and the third target does not meet the fusion condition, the first target and the second target are fused into a main target, and a splitting suppression zone in front of the main target is determined. It is determined whether the third target is in the splitting suppression zone and whether the longitudinal speed difference between the main target and the third target is within a speed difference threshold range. If the third target is in the splitting suppression zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, the output of the third target is suppressed.

[0007] In an implementable embodiment, the first sensor is a vision sensor, and the second sensor is a radar; wherein the detecting, by the first sensor and the second sensor, of the adjacent vehicle target in the adjacent lane ahead of the ego vehicle and traveling in the same direction as the ego vehicle comprises: collecting, by the vision sensor, an image of the adjacent lane ahead of the ego vehicle, and determining, based on image recognition, the adjacent vehicle target in the adjacent lane ahead of the ego vehicle and traveling in the same direction as the ego vehicle; and detecting, by the radar, a target in the adjacent lane ahead of the ego vehicle, and determining the adjacent vehicle target in the adjacent lane ahead of the ego vehicle and traveling in the same direction as the ego vehicle.

[0008] In an implementable embodiment, the judging whether the first target, the second target and the third target meet the fusion condition comprises: calculating, based on the Mahalanobis distance between the second target and the first target, a correlation degree between the second target and the first target, and determining that the second target and the first target meet the fusion condition if the correlation degree between the second target and the first target is greater than a preset threshold; and judging, based on the Mahalanobis distance between the third target and the first target or the second target, a correlation degree between the third target and the first target or the second target, and determining that the third target and the first target or the second target meet the fusion condition if the correlation degree between the third target and the first target or the second target is greater than a preset threshold.

[0009] In an implementable embodiment, the calculating, based on the Mahalanobis distance between the second target and the first target, of the correlation degree between the second target and the first target comprises: calculating the correlation degree F between the second target and the first target according to the following formula:

[0010] ;

[0011] wherein, ;

[0012] D M1 is a Mahalanobis distance calculated according to a longitudinal distance of the adjacent vehicle relative to the ego vehicle measured by the vision sensor and the radar respectively, D M2 is a Mahalanobis distance calculated according to a lateral distance of the adjacent vehicle relative to the ego vehicle measured by the vision sensor and the radar respectively, D M3 is a Mahalanobis distance calculated according to a longitudinal speed of the adjacent vehicle relative to the ego vehicle measured by the vision sensor and the radar respectively, D M4 is a Mahalanobis distance calculated according to a lateral speed of the adjacent vehicle relative to the ego vehicle measured by the vision sensor and the radar respectively, and σ is an empirical coefficient.

[0013] In an implementable embodiment, the determining the split prevention zone in front of the main target comprises: determining a current longitudinal distance between the main target and the ego vehicle, and a current longitudinal absolute speed of the main target; and determining a length of the split prevention zone in front of the main target based on the current longitudinal distance between the main target and the ego vehicle, the current longitudinal absolute speed of the main target, and a preset mapping relationship between a longitudinal distance between the main target and the ego vehicle, a longitudinal absolute speed of the main target, and a length of the split prevention zone.

[0014] In an implementable embodiment, the determining the split prevention zone in front of the main target comprises: determining a width of the split prevention zone in front of the main target based on a width of the main target.

[0015] In an implementable embodiment, before the determining the split prevention zone in front of the main target, the method further comprises: determining a current traffic scenario, and determining whether to start the step of determining the split prevention zone in front of the main target based on the current traffic scenario; wherein the current traffic scenario comprises at least one of a current road scenario, a current longitudinal speed of the ego vehicle, a vehicle type of the main target, a longitudinal absolute speed of the third target, and a vehicle type of the third target.

[0016] In an implementable embodiment, the determining the current traffic scenario, and determining whether to start the step of determining the split prevention zone in front of the main target based on the current traffic scenario comprises: if the current road scenario is an expressway, the current longitudinal speed of the ego vehicle is greater than 60 kph, the vehicle type of the main target is a large vehicle, the longitudinal absolute speed of the third target is greater than 5 m / s, and the vehicle type of the third target is a small vehicle, then starting the step of determining the split prevention zone in front of the main target.

[0017] In a second aspect, the embodiments of the present application further provide a vehicle target detection device for detecting a neighboring vehicle target in a same direction in a lane adjacent to a front of an ego vehicle, the device comprising:

[0018] a target acquisition module, configured to acquire a first target detected by a first sensor, a second target detected by a second sensor, and a third target; wherein the first sensor and the second sensor are sensors on the ego vehicle;

[0019] a target fusion module configured to determine whether the first target, the second target and the third target meet a fusion condition; if the first target and the second target meet the fusion condition and the third target does not meet the fusion condition, fuse the first target and the second target into a main target and determine a split suppression zone in front of the main target; determine whether the third target is in the split suppression zone and whether a longitudinal speed difference between the main target and the third target is within a speed difference threshold range; and if the third target is in the split suppression zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, suppress output of the third target.

[0020] In an implementable embodiment, the first sensor is a vision sensor and the second sensor is a radar; the vision sensor is configured to collect an image of a neighboring lane in front of the ego vehicle, and determine a neighboring vehicle target in the neighboring lane in front of the ego vehicle based on image recognition; and the radar is configured to detect a target in the neighboring lane in front of the ego vehicle, and determine the neighboring vehicle target in the neighboring lane in front of the ego vehicle.

[0021] In an implementable embodiment, the target fusion module includes: a fusion condition determination submodule configured to determine whether the first target, the second target and the third target meet a fusion condition; a target fusion submodule configured to fuse the first target and the second target into a main target if the first target and the second target meet the fusion condition and the third target does not meet the fusion condition; a split suppression zone determination submodule configured to determine a split suppression zone in front of the main target; and a target output suppression submodule configured to determine whether the third target is in the split suppression zone and whether a longitudinal speed difference between the main target and the third target is within a speed difference threshold range, and suppress output of the third target if the third target is in the split suppression zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range.

[0022] In an implementable embodiment, the fusion condition determination submodule is specifically configured to: calculate a correlation degree between the second target and the first target based on a Mahalanobis distance between the second target and the first target, and determine that the second target and the first target meet a fusion condition if the correlation degree between the second target and the first target is greater than a preset threshold; and determine a correlation degree between the third target and the first target or the second target based on a Mahalanobis distance between the third target and the first target or the second target, and determine that the third target and the first target or the second target meet a fusion condition if the correlation degree between the third target and the first target or the second target is greater than a preset threshold.

[0023] In an implementable embodiment, the inhibition zone determining sub-module is specifically configured to: determine a longitudinal distance between the host target and the ego vehicle, and a longitudinal absolute speed of the host target; and determine a length of the split inhibition zone in front of the host target based on the longitudinal distance between the host target and the ego vehicle, the longitudinal absolute speed of the host target, and a preset mapping relationship between the longitudinal distance between the host target and the ego vehicle, the longitudinal absolute speed of the host target, and the length of the split inhibition zone.

[0024] In an implementable embodiment, the inhibition zone determining sub-module is further configured to: determine a width of the split inhibition zone in front of the host target based on a width of the host target.

[0025] In an implementable embodiment, the target fusion module further comprises a scene determining sub-module configured to determine a current traffic scene; wherein the current traffic scene comprises at least one of a current road scene, a longitudinal speed of the ego vehicle, a vehicle type of the host target, a longitudinal absolute speed of the third target, and a vehicle type of the third target.

[0026] In an implementable embodiment, the determination of the current traffic scene and the determination of whether to start the step of determining the split inhibition zone in front of the host target based on the current traffic scene comprise: if the current road scene is an expressway, the longitudinal speed of the ego vehicle is greater than 60 kph, the vehicle type of the host target is a large vehicle, the longitudinal absolute speed of the third target is greater than 5 m / s, and the vehicle type of the third target is a small vehicle, then the step of determining the split inhibition zone in front of the host target is started.

[0027] In a third aspect, the embodiments of the present application further provide a vehicle, comprising: a vehicle body; a first sensor and a second sensor arranged on the vehicle body and configured to detect a neighboring target in a lane adjacent to a lane in front of the vehicle; a target fusion module configured to determine whether a first target detected by the first sensor, a second target detected by the second sensor, and a third target meet a fusion condition; if the first target and the second target meet the fusion condition and the third target does not meet the fusion condition, then fuse the first target and the second target into a host target and determine a split inhibition zone in front of the host target; determine whether the third target is in the split inhibition zone and whether a longitudinal speed difference between the host target and the third target is within a speed difference threshold range; and if the third target is in the split inhibition zone and the longitudinal speed difference between the host target and the third target is within the speed difference threshold range, then inhibit the third target from being output to an electronic control unit in an intelligent driving assistance system.

[0028] The vehicle target detection method, device and vehicle provided by the embodiment of the application detect a neighboring vehicle target running in the same direction as the vehicle in the adjacent lane in front of the vehicle through a first sensor and a second sensor; a first target detected by the first sensor, a second target detected by the second sensor and a third target are acquired; if the first target and the second target meet fusion conditions and the third target does not meet the fusion conditions, the first target and the second target are fused into a main target, and a split suppression zone in front of the main target is determined; if the third target is in the split suppression zone and the longitudinal speed difference between the main target and the third target is within a speed difference threshold range, the output of the third target is suppressed, that is, the third target is not output to an electronic control unit in an intelligent driving assistance system. In this way, the interference of the third target on the electronic control unit can be avoided, and the situation that the vehicle is mistakenly decelerated when the third target intrudes into the lane of the vehicle can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort.

[0030] Figure 1 A flowchart of an embodiment of the vehicle target detection method of the application;

[0031] Figure 2a A schematic diagram of a large vehicle target split in an embodiment of the vehicle target detection method of the application;

[0032] Figure 2b A schematic diagram of a large vehicle target split scene in an embodiment of the vehicle target detection method of the application;

[0033] Figure 3 A schematic diagram of determination of a forward suppression zone of a main target in an embodiment of the vehicle target detection method of the application;

[0034] Figure 4 A schematic diagram of not outputting a radar target in a suppression zone in an embodiment of the vehicle target detection method of the application;

[0035] Figure 5 A flowchart of determination of a forward suppression range of a main target in an embodiment of the vehicle target detection method of the application;

[0036] Figure 6 A flowchart of suppression of a large vehicle target split in another embodiment of the vehicle target detection method of the application;

[0037] Figure 7A functional structure diagram of an embodiment of the vehicle target detection device. DETAILED DESCRIPTION

[0038] The embodiments of the present application will be described in detail below with reference to the drawings. It should be noted that the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0039] The embodiments of the present application provide a vehicle target detection method to reduce the false deceleration of a vehicle equipped with an intelligent driving assistance system.

[0040] In a first aspect, the embodiments of the present application provide a vehicle target detection method, which is suitable for target detection of a neighboring vehicle in the same lane as the ego vehicle in front of the ego vehicle. The detection method comprises the following steps:

[0041] S11, detecting a neighboring vehicle target in the same lane as the ego vehicle in front of the ego vehicle through a first sensor and a second sensor.

[0042] The first sensor and the second sensor are sensors installed on the ego vehicle. The first sensor and the second sensor can be installed on the front of the ego vehicle to detect targets in front of the ego vehicle, including the neighboring vehicle target in the same lane as the ego vehicle in front of the ego vehicle, so as to provide a data basis for the ego vehicle's auxiliary driving system.

[0043] The first sensor and the second sensor can be visual sensors (such as cameras) and / or radars. The radar can be a laser radar or a millimeter wave radar. The neighboring vehicle target in the same lane as the ego vehicle refers to one or more vehicle targets in the lane adjacent to the lane in which the ego vehicle is currently traveling, which are in the same direction as the ego vehicle and are relatively close to the ego vehicle.

[0044] S12, obtaining a first target detected by the first sensor, a second target detected by the second sensor, and a third target.

[0045] The first sensor and the second sensor can work independently to detect the neighboring vehicle target in the same lane as the ego vehicle in front of the ego vehicle, thereby obtaining the first target detected by the first sensor, the second target detected by the second sensor, and the third target.

[0046] Due to the detection accuracy of the second sensor, the second target and the third target detected by the second sensor can be the same neighboring vehicle (for example, the neighboring vehicle has a long body, and the track of the neighboring vehicle appears to be split), or can be different neighboring vehicles.

[0047] S13, determining whether the first target, the second target, and the third target meet fusion conditions.

[0048] It is determined whether the first target, the second target and the third target meet a fusion condition, so as to determine whether at least two of the first target, the second target and the third target can be fused into one target, that is, to determine whether at least two of the first target, the second target and the third target are one adjacent vehicle.

[0049] The fusion condition can be whether the distance and / or the longitudinal (the driving manner of the vehicle) speed difference of the two targets meet a preset condition. If the first target, the second target and the third target all meet the fusion condition, the first target, the second target and the third target are fused into one target. If the first target and the second target meet the fusion condition, but the third target does not meet the fusion condition, step S14 is performed.

[0050] S14, the first target and the second target are fused into a main target, and a split suppression zone in front of the main target is determined.

[0051] The first target and the second target are fused into the main target, specifically, a maximum circumscribed rectangular frame of the region where the first target and the second target are located is established, and the maximum circumscribed rectangular frame is taken as the main target.

[0052] Figure 2a It is a schematic diagram of the first target and the second target being fused into the main target in an actual scene in an embodiment of the present application. Figure 2a In the figure, the front radar target point is a target point detected by a radar (which can be referred to as a front radar, i.e., a second sensor) installed at the front of the vehicle; and the forward-looking target point is a target point detected by a vision sensor (which can be referred to as a forward-looking, i.e., a first sensor) installed at the front of the vehicle. Figure 2a In the figure, two third targets that do not meet the fusion condition are shown, i.e., split targets.

[0053] Figure 2b It is a schematic diagram of the first target and the second target being fused into the main target in an actual scene in an embodiment of the present application. Figure 2b In the figure, the target formed by the single front radar is a split target formed when the front radar detects the adjacent vehicle. Figure 2b In the figure, one third target that does not meet the fusion condition is shown, i.e., a split target.

[0054] The split suppression zone can be determined according to the safe following distance of the main target, for example, the safe following distance of the main target can be taken as the length of the split suppression zone, and the width of the main target can be taken as the width of the split suppression zone. The split suppression zone can also be determined according to the longitudinal distance between the main target and the vehicle, and the current longitudinal absolute speed of the main target.

[0055] Determining the split inhibition zone in front of the primary target facilitates determining whether the third target is a split target of a neighboring vehicle. A split target of a neighboring vehicle is a target formed in front of the primary target by a portion of the neighboring vehicle's trace that is not associated with the primary target.

[0056] S15: Determine whether the third target is in the splitting inhibition zone and whether the longitudinal speed difference between the main target and the third target is within a speed difference threshold range.

[0057] Whether the third target is within the split inhibition zone may be determined by judging whether the coordinates of the third target are within the split inhibition zone.

[0058] See Figure 3 As shown, assuming that the length of the main target rectangle is I, the length of the inhibition zone is L, and the width is W. The longitudinal distance X of the near edge of the inhibition zone N = D xFus +I, far edge longitudinal distance X F =X N +L, lateral distance Y from the side of the vehicle N =D yFus -W / 2, lateral distance Y from the side of the vehicle F =D yFus +W / 2; where D xFus is the longitudinal distance of the main target relative to the vehicle, D yFus The lateral distance between the center of the main target and the vehicle.

[0059] If the longitudinal coordinate X and the transverse coordinate Y of the third target meet the following conditions, it can be determined that the coordinates of the third target are within the splitting inhibition zone:

[0060] X N <x<X F

[0061] Y N <y<Y F

[0062] The longitudinal speeds of the main target and the third target can be determined based on the detection of the second sensor. The longitudinal speed of the main target can be determined based on the longitudinal speed of the second target that is integrated into the main target, that is, the longitudinal speed of the second target can be used as the longitudinal speed of the main target.

[0063] If the longitudinal speed difference between the primary and tertiary targets is too large, it can be assumed that the primary and tertiary targets correspond to different neighboring vehicles. Therefore, an appropriate speed difference threshold is required. If the longitudinal speed difference between the primary and tertiary targets falls within this speed difference threshold, the tertiary target may be a split target of the neighboring vehicle corresponding to the primary target.

[0064] If the third target is in the splitting inhibition zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, it can be basically determined that the third target is the splitting target of the adjacent vehicle corresponding to the main target, and step S16 can be performed at this time.

[0065] In order to prevent the speed difference between the splitting target and the main target from fluctuating around the speed difference threshold value and causing the splitting target to frequently switch between output and non-output, the speed difference between the splitting target and the main target is set to be continuously exceeded within the speed difference threshold value for a time threshold τ to be inhibited from output.

[0066] S16, inhibit the output of the third target.

[0067] The output of the third target is inhibited, that is, the third target is not output to the electronic control unit in the intelligent driving assistance system, so that the driving control of the ego vehicle by the electronic control unit is not affected by the third target.

[0068] The above steps S12-S16 can be performed by a target fusion module in the intelligent driving assistance system. Figure 4 A schematic diagram of not outputting the third target in the splitting inhibition zone in an embodiment of the present application.

[0069] The target fusion module inside the inhibition zone will start a track for the third target, but will not output it. When the ego vehicle approaches, the length error of the visually recognized target becomes small, and the main target and the splitting target meet the association conditions, and then association is performed, so that one visual target is associated with multiple targets misrecognized by the front radar.

[0070] In the vehicle target detection method embodiment, the adjacent vehicle target in the same direction in the adjacent lane in front of the ego vehicle is detected by the first sensor and the second sensor. The first target detected by the first sensor, the second target detected by the second sensor, and the third target are obtained. If the first target and the second target meet the fusion conditions, and the third target does not meet the fusion conditions, the first target and the second target are fused as the main target, and a splitting inhibition zone in front of the main target is determined. If the third target is in the splitting inhibition zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, the output of the third target is inhibited, that is, the third target is not output to the electronic control unit in the intelligent driving assistance system. In this way, the interference of the third target to the electronic control unit can be avoided, and the situation of the ego vehicle being mistakenly decelerated when the third target intrudes into the lane of the ego vehicle can be reduced.

[0071] In some embodiments, the first sensor is a visual sensor (such as a camera), and the second sensor is a radar, specifically a millimeter wave radar.

[0072] Correspondingly, the detection of the adjacent vehicle target in the same direction in the adjacent lane in front of the ego vehicle by the first sensor and the second sensor (step S11) comprises:

[0073] Through the visual sensor, an image of a neighboring lane in front of the ego vehicle is collected, and a neighboring vehicle target in the same direction of travel in the neighboring lane in front of the ego vehicle is determined based on image recognition; through the radar, a target in the neighboring lane in front of the ego vehicle is detected, and the neighboring vehicle target in the same direction of travel in the neighboring lane in front of the ego vehicle is determined.

[0074] By using the visual sensor, the position of the neighboring vehicle target relative to the lane line can be determined based on image information, and then the lane state in which the neighboring vehicle target is located can be confirmed. In addition, a large number of model training can be performed on different vehicle types through the visual sensor, the target type recognition accuracy is high, and whether the target type is a large vehicle (a large truck with a vehicle body length of tens of meters or even dozens of meters) can be more accurately confirmed.

[0075] The visual sensor can process the acquired image information into target information, which includes the distance, speed, type of the neighboring vehicle relative to the ego vehicle, scene information, and the like.

[0076] The millimeter wave radar detects the neighboring vehicle target through radio waves, and by using the principle of Doppler effect and high-resolution measurement technology, higher ranging and speed measurement accuracy can be obtained. The millimeter wave radar can process the reflected wave signal into target information, which can include the distance and speed of the neighboring vehicle relative to the ego vehicle. The speed information output by the millimeter wave radar is the relative speed of the neighboring vehicle relative to the ego vehicle, which can be converted into absolute speed.

[0077] In some embodiments, the relative speed is converted into absolute speed in the following manner:

[0078] The distance R of the target to the origin and the angle θ with the x-axis of the ego vehicle coordinate system are calculated with the center of the rear axle of the ego vehicle as the origin of the coordinate system:

[0079] ;

[0080] θ = artan (dy / dx);

[0081] The lateral and longitudinal speeds generated by the yaw angle of the ego vehicle are superimposed:

[0082] V xhost = V x - ω × R × sin θ

[0083] V yhost = V y + ω × R × cos θ

[0084] where V xhost is the superimposed longitudinal speed of the ego vehicle; V yhost is the superimposed lateral speed of the ego vehicle; ω is the yaw rate of the ego vehicle; Vx is the longitudinal speed of the ego vehicle; Vy is the lateral speed of the ego vehicle;

[0085] According to the relative speed of the radar and the lateral and longitudinal speeds of the vehicle, the absolute speed of the radar target can be calculated:

[0086] V xFR =V xRel +V xhost ;

[0087] V yFR =V yRel +V yhost ;

[0088] Among them, V xFR is the longitudinal absolute velocity of the target in front of the radar; V yFR is the absolute lateral velocity of the radar target.

[0089] In this implementation, the primary target is the fusion result of the association between the target detected by the visual sensor (first sensor) mounted in front of the ego vehicle (referred to as the forward-view target) and the target detected by the radar (second sensor, referred to as the front radar) mounted in front of the ego vehicle (referred to as the front radar target). Split targets are points at other locations on the same neighboring vehicle output by the front radar that cannot be clustered due to a large distance difference.

[0090] In this embodiment, multimodal data analysis can be performed based on the detection data of the visual sensor and the millimeter-wave radar, which facilitates the fusion processing of the targets detected by the visual sensor and the targets detected by the radar, and can greatly improve the accuracy of target detection.

[0091] In some embodiments, determining whether the first target, the second target, and the third target meet the fusion condition (step S13) may include:

[0092] S131. Calculate the correlation between the second target and the first target based on the Mahalanobis distance between the second target and the first target. If the correlation between the second target and the first target is greater than a preset threshold, determine that the second target and the first target meet the fusion condition.

[0093] S132. Based on the Mahalanobis distance between the third target and the first target or the second target, determine the correlation between the third target and the first target or the second target; if the correlation between the third target and the first target or the second target is greater than a preset threshold, determine that the third target and the first target or the second target meet the fusion condition.

[0094] The data measured by the visual sensor can be aligned in time and space with the data measured by the radar. By calculating the Mahalanobis distance of the speed, distance and other dimensions of the targets measured by the visual sensor and the radar, the correlation of the targets can be calculated to determine whether the targets measured by the visual sensor (referred to as sensor targets) and the targets measured by the radar (referred to as radar targets) are correlated.

[0095] In some embodiments, the step S131 of calculating the correlation degree of the second target and the first target based on the Mahalanobis distance between the second target and the first target can include:

[0096] The correlation degree F of the second target and the first target is calculated according to the following formula:

[0097] ;

[0098] wherein, ;

[0099] D M1 is the Mahalanobis distance calculated according to the longitudinal distance of the target (i.e. the adjacent vehicle) relative to the ego vehicle measured by the vision sensor and the radar, respectively, M2 is the Mahalanobis distance calculated according to the lateral distance of the adjacent vehicle relative to the ego vehicle measured by the vision sensor and the radar, respectively, M3 is the Mahalanobis distance calculated according to the longitudinal speed of the adjacent vehicle relative to the ego vehicle measured by the vision sensor and the radar, respectively, M4 is the Mahalanobis distance calculated according to the lateral speed of the adjacent vehicle relative to the ego vehicle measured by the vision sensor and the radar, respectively, and σ is an empirical coefficient.

[0100] In some examples, D M1 may be calculated according to the following formula:

[0101] ;

[0102] wherein x is the longitudinal distance of the second target relative to the ego vehicle measured by the radar (which can be referred to as the radar target longitudinal distance), μ is the longitudinal distance of the first target relative to the ego vehicle measured by the vision sensor (which can be referred to as the vision longitudinal distance), and ∑ is the covariance matrix. It should be understood that, since there is only a single dimension of longitudinal distance here, it can be simplified as the sum of the variance of the radar target longitudinal distance and the variance of the forward distance.

[0103] Similarly, the lateral distance, the longitudinal speed, and the lateral speed of the target relative to the ego vehicle measured by the vision sensor and the radar can be used to calculate the corresponding Mahalanobis distances D M2 , D M3 , and D M4 , respectively.

[0104] It should be understood that other conditions, such as the heading angle of the target, can also be added to calculate the Mahalanobis distance to increase the correlation reliability.

[0105] The correlation degree F can also be referred to as a correlation score F. When F ≥ δ, it indicates that the two targets can be correlated; wherein δ is a preset correlation threshold.

[0106] The determination manner of the association degree of the third target to the first target or the second target can be the same as the determination manner of the association degree of the second target to the first target, and details are not repeated.

[0107] The speed and distance of the target detected by each sensor can be quite different, the calculated association score is small, which can cause the target to be unable to be associated, at this time a track can be started for the target that cannot be associated, forming a single sensor target for output. For a super-long truck of tens of meters or even dozens of meters, the radar reflection points are more and sparse and not coherent, the distance difference of the clustered target is far, which can cause the large target to be split into multiple small targets, therefore multiple single radar targets can be formed near the fusion target (main target), as shown in Figure 2a . Figure 2a The figure shows that there are two split targets near the front of the main target, which are single radar targets (targets formed only by radar).

[0108] The associated target is the fusion target (main target), which can combine the following advantages of the visual sensor and the millimeter wave radar:

[0109] (1) The longitudinal position and speed follow the front millimeter wave radar, and the accuracy is higher:

[0110] V xFus =V xFR , D xFus =D xFR

[0111] Wherein, V xFus is the longitudinal speed of the fusion target, V xFR is the longitudinal absolute speed of the associated radar target, D xFus is the longitudinal distance of the fusion target relative to the ego vehicle, and D xFR is the longitudinal distance of the associated radar target relative to the ego vehicle.

[0112] (2) The lateral position and speed follow the visual sensor, and the accuracy is higher:

[0113] V yFus =V yFR , D yFus =D yFR

[0114] Wherein V yFus is the lateral speed of the fusion target, V yFR is the lateral absolute speed of the associated visual sensor target, D yFus is the lateral distance of the fusion target relative to the ego vehicle, and D yFR is the lateral distance of the associated visual sensor target relative to the ego vehicle.

[0115] If there is no new measurement update in the current frame, i.e. the information of radar detection is not updated, the longitudinal velocity and longitudinal distance of the fusion target can be predicted by using the CA motion model (constant acceleration motion model).

[0116] Let state x = (v, d), v represents velocity, d represents distance, and a represents acceleration k . Given the state x k-1 = (v k-1 , d k-1 ) of k-1, the next time x k = (v k , d k )

[0117] d k =d k-1 +Δtv k-1 +1 / 2a k (Δt)²

[0118] v k =v k-1 +a k Δt

[0119] In the form of state transition:

[0120] x k =Fx k-1 +Ba k (1)

[0121] F = : state transition matrix

[0122] B = : control matrix

[0123] In reality, various disturbances exist due to external influences, so noise will be mixed in the state transition process, and the noise cannot be measured, but it can be considered that the noise is subject to a high Gaussian distribution with zero mean, so formula (1) can be rewritten as:

[0124] x k =Fx k-1 +Bu k +w k (2)

[0125] u k is the control input, which is a k in the embodiment, w k is the process noise, w k ~N(0, Q k ), and Q k is the covariance matrix thereof.

[0126] If there is a new measurement update in the current frame, i.e. the information of radar detection is updated, the updated measurement is used to correct the predicted value, and the Kalman filter is used to perform iterative calculation.

[0127] The relationship between the observation value of the current frame (i.e. the updated measurement of the sensor) and the state x k is as follows: y k =Hx k +v k (3)

[0128] H is the observation transition matrix, v k is the observation noise, the observation noise obeys a Gaussian distribution with a mean value of 0, i.e. v k ~N(0,R k ), and R k is the covariance matrix thereof.

[0129] According to equations (2) and (3), it is assumed that, at time k-1, there is an estimated value k-1 of the system, and the covariance of the estimated value is P k-1 . The predicted state is obtained by using the state transition equation as follows: k - =F k-1 +Bu k , and the covariance P k - of the predicted state is as follows: k-1 T +F k

[0130] The Kalman gain K k

[0131] at time k can be derived as follows: k k - H T (HP k - H T +R k ) -1

[0132] According to the predicted value, the observation value and the Kalman gain at the current time, the optimal estimated value at the current time can be derived as follows:

[0133] k = k - +K k (y k -H k ​​- )

[0134] According to the predicted value covariance of the current time, the Kalman gain derives the optimal estimation value covariance of this time

[0135] P k = (1 - K k H) P k -

[0136] The prediction update loop is repeated, and the optimal estimation value of each time can be obtained.

[0137] In some embodiments, in step S14, determining the split suppression zone in front of the main target can include: determining the current longitudinal distance between the main target and the ego vehicle, and the current longitudinal absolute speed of the main target; and determining the length of the split suppression zone in front of the main target based on the current longitudinal distance between the main target and the ego vehicle, the current longitudinal absolute speed of the main target, and a pre-set mapping relationship between the longitudinal distance between the main target and the ego vehicle, the longitudinal absolute speed of the main target, and the length of the split suppression zone.

[0138] The longitudinal distance between the first target and the second target fused into the main target by the foregoing rectangular frame and the rear axle of the ego vehicle can be taken as the current longitudinal distance between the main target and the ego vehicle; and the longitudinal absolute speed of the second target can be taken as the current longitudinal absolute speed of the main target.

[0139] Based on the current longitudinal distance between the main target and the ego vehicle and the current longitudinal absolute speed of the main target, a pre-set mapping relationship table between the longitudinal distance between the main target and the ego vehicle, the longitudinal absolute speed of the main target, and the length of the split suppression zone can be traversed to obtain the length of the split suppression zone in front of the main target.

[0140] In some embodiments, the mapping relationship between the longitudinal distance between the main target and the ego vehicle, the longitudinal absolute speed of the main target, and the length of the split suppression zone can be as shown in Figure 5 .

[0141] Figure 5 It is also a flow chart for determining the front suppression range of the main target in an embodiment of the vehicle target detection method of the present application. According to Figure 5 , if the current longitudinal distance between the main target and the ego vehicle is > 80 m, and the longitudinal absolute speed of the main target is > 80 kph, the length of the split suppression zone in front of the main target (also referred to as the front) can be obtained as 12 m;

[0142] If the current longitudinal distance between the main target and the ego vehicle is > 40 m, and the longitudinal absolute speed of the main target is > 80 kph, the length of the split suppression zone in front of the main target can be obtained as 10 m;

[0143] If the longitudinal distance between the current main target and the ego vehicle is < 40m, and the longitudinal absolute speed of the main target is > 80kph, then the length of the split prevention zone in front of the main target can be 8m;

[0144] If the longitudinal distance between the current main target and the ego vehicle is > 80m, and the longitudinal absolute speed of the main target is > 40kph, then the length of the split prevention zone in front of the main target can be 9m;

[0145] If the longitudinal distance between the current main target and the ego vehicle is > 80m, and the longitudinal absolute speed of the main target is > 18kph, then the length of the split prevention zone in front of the main target can be 7m;

[0146] If the longitudinal distance between the current main target and the ego vehicle is > 80m, and the longitudinal absolute speed of the main target is < 18kph, then there is no split prevention zone in front of the main target, i.e. no split prevention zone.

[0147] Generally, considering the driver reaction time and the driver's sense of crisis when driving close to the target, especially in the case of large truck following, the large truck has a long braking distance, so the greater the speed of the vehicle on the road, the greater the distance between the vehicles. Based on this premise, the length of the split prevention zone in front of the main target (also referred to as the prevention range) is set to be smaller than the normal road following distance.

[0148] Figure 5 In the illustrated embodiment, the length of the split prevention zone in front of the main target is determined.

[0149] In some embodiments, the width of the split prevention zone can be determined based on the width of the main target. In some examples, the width of the main target can be directly used as the width of the split prevention zone in front of the main target.

[0150] Since the lateral distance of the target detected by the radar generally has a large error, the width of the split prevention zone can be expanded by a certain distance based on the width of the main target, such as 0.1m, 0.2m, etc. In one example, the expanded split prevention zone is shown as Figure 3 .

[0151] In other embodiments, the width of the split prevention zone can also be determined according to a certain proportion of the length of the split prevention zone, such as one third or one quarter of the length of the split prevention zone as the width of the split prevention zone.

[0152] In order to prevent frequent calculation of the split prevention zone, in some embodiments, before determining the split prevention zone in front of the main target, the method can further comprise:

[0153] determining a current traffic scenario, and determining whether to start the splitting inhibition zone in front of the main target based on the current traffic scenario; wherein the current traffic scenario comprises at least one of a current road scenario, a current longitudinal speed of the ego vehicle, a vehicle type of the main target, a longitudinal absolute speed of the third target, and a vehicle type of the third target.

[0154] The current road scenario can be determined by information detected by the visual sensor, such as whether it is a high-speed scenario.

[0155] The current longitudinal speed of the ego vehicle (which can be referred to as the ego vehicle speed) can be determined by obtaining vehicle body data, and it is determined whether the current ego vehicle speed meets the requirements of the current road scenario, such as whether the current ego vehicle speed is not less than 60 kph according to the minimum speed requirement of the highway.

[0156] In the case where the current ego vehicle speed meets the requirements of the current road scenario under the current road scenario,

[0157] The vehicle types of the main target and the third target (splitting target) can be determined, specifically, the vehicle type of the main target can be determined by information detected by the visual sensor, and the vehicle type of the third target can be determined by radar detection data. If the vehicle type of the main target is determined to be a large vehicle by information detected by the visual sensor, and the splitting radar target is determined to be a small vehicle (such as a vehicle body length of 3.5-4.6 m) by radar detection data, the longitudinal speed of the third target is calculated. In other embodiments, a target type with a length greater than 7 m is considered a large vehicle, and a target type with a length less than 7 m is considered a small vehicle.

[0158] According to the target speed information provided by the sensor, the longitudinal speed of the third target (radar target) is calculated. Since the radar has a low recognition accuracy for low-speed targets, only radar targets with a longitudinal speed greater than a specified speed are inhibited, such as only radar targets with a longitudinal speed greater than 5 m / s are inhibited. If the calculated longitudinal speed of the third target is greater than the specified speed, such as greater than 5 m / s, the step of starting the splitting inhibition zone in front of the main target is started.

[0159] In some embodiments, determining a current traffic scenario, and determining whether to start the splitting inhibition zone in front of the main target based on the current traffic scenario, comprises: if the current road scenario is a highway, the current longitudinal speed of the ego vehicle is greater than 60 kph, the vehicle type of the main target is a large vehicle, the longitudinal absolute speed of the third target is greater than 5 m / s, and the vehicle type of the third target is a small vehicle, then the step of determining the splitting inhibition zone in front of the main target is started.

[0160] In some embodiments, the speed difference threshold in step S15 can be determined in the following way: the truck is a rigid object, so the movement speed of each point along the truck driving direction is the same, the millimeter wave radar can detect the radial distance, radial speed and angle of the target point to the radar, and the movement speed of each target point can be calculated according to these information, since there is noise in the radar measurement, and different points on the truck have different angles relative to the front radar, so there is an error in the finally calculated movement speed of each target point. Therefore, when |V xFus -V FR ︱≤ξ, it can be considered that they are the same target, wherein V xFus is the longitudinal speed of the fusion target, which is equal to the movement speed of the associated front radar target, V FR is the movement speed of the associated front radar target of the split target, and ξ can be obtained according to a large number of repeated experiments.

[0161] The vehicle target detection method of the present application will be described below with a specific embodiment.

[0162] Referring to Figure 6 , the vehicle target detection method of the embodiment comprises the following steps:

[0163] S601, obtaining the perception data of the front view and the front radar;

[0164] S602, calculating the association score of the front view target and the front radar target;

[0165] S603, judging whether the association score F is greater than or equal to the association score threshold 0.8;

[0166] If the association score is greater than or equal to the association score threshold 0.8, step S604 is executed, otherwise step S605 is executed.

[0167] S604, judging whether the following conditions are met at the same time: the vehicle speed is greater than or equal to 60kph, the fusion target type is truck, the single radar target (i.e. split target) is car, the current is high speed scene, and the single radar target speed is greater than 5m / s;

[0168] If the above conditions are met at the same time, step S606 is executed, otherwise step S610 is executed;

[0169] S605, outputting the single vision and single front radar target;

[0170] S606, calculating the suppression region and the speed difference value of the fusion target and the single radar target;

[0171] S607, judging whether the single radar target is in the suppression region;

[0172] If the single-radar target is in the suppression region, step S608 is performed, otherwise, step S610 is performed.

[0173] S608, determining whether the longitudinal velocity difference between the fusion target and the single-radar target is within a velocity difference threshold 1 m / s and continuously exceeds a predetermined time 0.5 s; if yes, step S609 is performed, otherwise, step S610 is performed.

[0174] S609, suppressing the output of the single-radar target;

[0175] S610, outputting the fusion target and the single-radar target.

[0176] In the embodiment of the application, by suppressing the output of the large truck split target, the track splitting problem of the large truck in the adjacent lane in front of the ego vehicle and the problem of the split target invading the ego lane to cause the ego vehicle to brake incorrectly can be solved. Therefore, the type of the main target is mainly a large truck and is in the adjacent lane in front of the ego vehicle, and the target type and the rectangular box of the target (box frame) can be obtained and assigned based on the target information provided by the front view (visual sensor in the front part of the ego vehicle). The relative position of the lane line and the lane in which the target is located can also be known from the target information perceived by the front view.

[0177] Because the farther the longitudinal distance position of the target in the adjacent lane in front of the ego vehicle is from the ego vehicle, the less the side information of the target obtained by the front view is, and thus the greater the error in the calculation of the length of the target is, and because the real target at a far distance has relatively more time to react when invading, the suppression distance in front of the main target at a far distance can be increased.

[0178] In a second aspect, the embodiment of the application further provides a vehicle target detection device for detecting a neighbor target of a vehicle in the adjacent lane in front of the ego vehicle and driving in the same direction, referring to Figure 7 The vehicle target detection device of the embodiment includes a target acquisition module 201 and a target fusion module 202.

[0179] The target acquisition module 201 is configured to acquire a first target detected by a first sensor, a second target detected by a second sensor, and a third target; wherein the first sensor and the second sensor are sensors on the ego vehicle.

[0180] The target fusion module 202 is configured to determine whether the first target, the second target and the third target meet a fusion condition; if the first target and the second target meet the fusion condition and the third target does not meet the fusion condition, the first target and the second target are fused into a main target, and a split inhibition zone in front of the main target is determined; it is determined whether the third target is in the split inhibition zone and whether a longitudinal speed difference between the main target and the third target is within a speed difference threshold range; if the third target is in the split inhibition zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, the output of the third target is inhibited.

[0181] The vehicle target detection method of the embodiment can achieve the same implementation process and technical effects as those of the vehicle target detection method of the foregoing embodiment, and thus will not be described herein.

[0182] In some embodiments, the first sensor is a vision sensor, and the second sensor is a radar; the vision sensor is configured to collect an image of a neighboring lane in front of the ego vehicle, and determine a neighboring vehicle target in the neighboring lane in front of the ego vehicle based on image recognition; and the radar is configured to detect a target in the neighboring lane in front of the ego vehicle, and determine the neighboring vehicle target in the neighboring lane in front of the ego vehicle.

[0183] In some embodiments, the target fusion module comprises:

[0184] The fusion condition determination submodule is configured to determine whether the first target, the second target and the third target meet a fusion condition;

[0185] The target fusion submodule is configured to, if the first target and the second target meet the fusion condition and the third target does not meet the fusion condition, fuse the first target and the second target into a main target.

[0186] The split inhibition zone determination submodule is configured to determine a split inhibition zone in front of the main target.

[0187] The target output inhibition submodule is configured to determine whether the third target is in the split inhibition zone and whether a longitudinal speed difference between the main target and the third target is within a speed difference threshold range; if the third target is in the split inhibition zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, the output of the third target is inhibited.

[0188] In some embodiments, the fusion condition judging submodule is specifically configured to: calculate the correlation degree between the second target and the first target based on the Mahalanobis distance between the second target and the first target; if the correlation degree between the second target and the first target is greater than a preset threshold, determine that the second target and the first target meet the fusion condition; and judge the correlation degree between the third target and the first target or the second target based on the Mahalanobis distance between the third target and the first target or the second target; if the correlation degree between the third target and the first target or the second target is greater than a preset threshold, determine that the third target and the first target or the second target meet the fusion condition.

[0189] The method for calculating the correlation degree between the second target and the first target is basically the same as the method in the foregoing method embodiments, and will not be described here again.

[0190] In some embodiments, the suppression zone determining submodule is specifically configured to: determine the longitudinal distance between the host target and the ego vehicle and the longitudinal absolute speed of the host target; and determine the length of the split suppression zone in front of the host target based on the longitudinal distance between the host target and the ego vehicle, the longitudinal absolute speed of the host target, and a preset mapping relationship between the longitudinal distance between the host target and the ego vehicle, the longitudinal absolute speed of the host target and the length of the split suppression zone.

[0191] In some embodiments, the suppression zone determining submodule is further configured to: determine the width of the split suppression zone in front of the host target based on the width of the host target.

[0192] In some embodiments, the target fusion module further includes a scene determining submodule configured to determine a current traffic scene; wherein the current traffic scene includes at least one of a current road scene, a longitudinal speed of the ego vehicle, a vehicle type of the host target, a longitudinal absolute speed of the third target, and a vehicle type of the third target.

[0193] In some embodiments, if the current road scene is an expressway, the longitudinal speed of the ego vehicle is greater than 60 kph, the vehicle type of the host target is a large vehicle, the longitudinal absolute speed of the third target is greater than 5 m / s, and the vehicle type of the third target is a small vehicle, the step of determining the split suppression zone in front of the host target is started.

[0194] In the embodiments of the present application, by suppressing the output of the split target of the large truck, the problem that the target split from the large truck in the adjacent lane in front of the ego vehicle invades the ego lane and causes the ego vehicle to brake mistakenly can be solved.

[0195] In a third aspect, the embodiments of the present application further provide a vehicle, comprising: a vehicle body; a first sensor and a second sensor arranged on the vehicle body and configured to detect a neighboring vehicle target which travels in the same direction as the vehicle in a lane adjacent to a front lane of the vehicle; a target fusion module configured to determine whether a first target detected by the first sensor, a second target detected by the second sensor and a third target meet a fusion condition; if the first target and the second target meet the fusion condition and the third target does not meet the fusion condition, fuse the first target and the second target into a main target, and determine a split suppression zone in front of the main target; determine whether the third target is in the split suppression zone and whether a longitudinal speed difference between the main target and the third target is within a speed difference threshold range; and if the third target is in the split suppression zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, suppress output of the third target to an electronic control unit in an intelligent driving assistance system.

[0196] In some embodiments, the target fusion module in the embodiments of the present application can be the target fusion module in any of the embodiments of the detection device.

[0197] The vehicle provided by the embodiments of the present application detects a neighboring vehicle target which travels in the same direction as the vehicle in a lane adjacent to a front lane of the vehicle through the first sensor and the second sensor, acquires a first target detected by the first sensor, a second target detected by the second sensor and a third target, fuses the first target and the second target into a main target if the first target and the second target meet a fusion condition and the third target does not meet the fusion condition, determines a split suppression zone in front of the main target, and suppresses output of the third target if the third target is in the split suppression zone and a longitudinal speed difference between the main target and the third target is within a speed difference threshold range, i.e. does not output the third target to an electronic control unit in an intelligent driving assistance system. In this way, the third target can be prevented from interfering with the electronic control unit, and the situation that the vehicle is mistakenly decelerated due to the third target invading the lane of the vehicle can be reduced.

[0198] It should be noted that the relative terms, such as first and second, are used herein only to differentiate one entity or operation from another entity or operation, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a list of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, an element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0199] Each of the embodiments in the specification is described in a relevant manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments.

[0200] Especially, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the description of the method embodiments.

[0201] For the convenience of description, the above device is described in various units / modules respectively according to functions. Of course, the functions of each unit / module can be implemented in the same or multiple software and / or hardware when implementing the present application.

[0202] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing relevant hardware. The program can be stored in a computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiments can be included. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0203] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A vehicle target detection method, characterized in that: include: Detecting a neighboring vehicle traveling in the same direction in an adjacent lane ahead of the vehicle using a first sensor and a second sensor; wherein the first sensor and the second sensor are sensors on the vehicle; Acquire a first target detected by the first sensor, a second target and a third target detected by the second sensor; Determining whether the first target, the second target, and the third target meet fusion conditions; If the first target and the second target meet the fusion condition, and the third target does not meet the fusion condition, the first target and the second target are fused into a main target, and a splitting inhibition zone in front of the main target is determined; determining whether the third target is within the splitting inhibition zone and whether a longitudinal speed difference between the main target and the third target is within a speed difference threshold range; If the third target is within the split suppression zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, the output of the third target is suppressed.

2. The vehicle target detection method according to claim 1, characterized in that: The first sensor is a visual sensor, and the second sensor is a radar; The detecting of a neighboring vehicle traveling in the same direction in an adjacent lane ahead of the vehicle by using the first sensor and the second sensor includes: The visual sensor collects images of the adjacent lane in front of the vehicle and identifies the adjacent vehicle target traveling in the same direction in the adjacent lane in front of the vehicle based on image recognition; The radar is used to detect targets in the adjacent lane in front of the vehicle, and to determine the adjacent vehicle target traveling in the same direction in the adjacent lane in front of the vehicle.

3. The vehicle target detection method according to claim 2, characterized in that: The determining whether the first target, the second target, and the third target meet the fusion condition includes: Calculating the association degree between the second target and the first target based on the Mahalanobis distance between the second target and the first target; and determining that the second target and the first target meet the fusion condition if the association degree between the second target and the first target is greater than a preset threshold; Based on the Mahalanobis distance between the third target and the first target or the second target, the correlation between the third target and the first target or the second target is determined; if the correlation between the third target and the first target or the second target is greater than a preset threshold, it is determined that the third target and the first target or the second target meet the fusion condition.

4. The vehicle target detection method according to claim 3, characterized in that: The calculating the association degree between the second target and the first target based on the Mahalanobis distance between the second target and the first target includes: The correlation F between the second target and the first target is calculated according to the following formula: ； in, ; D M1 is the Mahalanobis distance calculated based on the longitudinal distances of the neighboring vehicle relative to the vehicle measured by the visual sensor and the radar, respectively, D M2 is the Mahalanobis distance calculated based on the lateral distance of the neighboring vehicle relative to the vehicle measured by the visual sensor and the radar, respectively, D M3 is the Mahalanobis distance calculated based on the longitudinal speed of the neighboring vehicle relative to the vehicle measured by the visual sensor and the radar, respectively, D M4 is the Mahalanobis distance calculated based on the lateral speed of the neighboring vehicle relative to the own vehicle measured by the visual sensor and the radar respectively, and σ is an empirical coefficient.

5. The vehicle target detection method according to claim 2, characterized in that: Determining the splitting inhibition zone in front of the main target includes: Determining a current longitudinal distance between the primary target and the ego vehicle, and a current longitudinal absolute speed of the primary target; Based on the current longitudinal distance between the main target and the vehicle, the current longitudinal absolute speed of the main target, and the pre-set mapping relationship between the longitudinal distance between the main target and the vehicle, the longitudinal absolute speed of the main target and the length of the split inhibition zone, the length of the split inhibition zone in front of the main target is determined.

6. The vehicle target detection method according to claim 2 or 5, characterized in that: Determining the splitting inhibition zone in front of the main target includes: Based on the width of the main target, the width of the splitting inhibition zone in front of the main target is determined.

7. The vehicle target detection method according to claim 2, characterized in that: Before determining the splitting inhibition zone in front of the main target, the method further includes: The step of determining a current traffic scene and determining whether to activate a split inhibition zone in front of the main target based on the current traffic scene; wherein the current traffic scene includes at least one of the current road scene, the current longitudinal speed of the vehicle, the vehicle type of the main target, the longitudinal absolute speed of the third target, and the vehicle type of the third target.

8. The vehicle target detection method according to claim 7, characterized in that: The step of determining the current traffic scene and determining whether to activate the split inhibition zone in front of the main target based on the current traffic scene includes: If the current road scene is a highway, the current longitudinal speed of the vehicle is above 60 kph, the vehicle type of the main target is a large vehicle, the longitudinal absolute speed of the third target is greater than 5 m / s, and the vehicle type of the third target is a small vehicle, then the step of determining the splitting inhibition zone in front of the main target is initiated.

9. A vehicle target detection device, characterized in that: The device is used to detect neighboring vehicles traveling in the same direction in the adjacent lane ahead of the vehicle, and includes: A target acquisition module, configured to acquire a first target detected by a first sensor, a second target detected by a second sensor, and a third target detected by a second sensor; wherein the first sensor and the second sensor are sensors on the vehicle; The target fusion module is used to determine whether the first target, the second target and the third target meet the fusion conditions; if the first target and the second target meet the fusion conditions and the third target does not meet the fusion conditions, the first target and the second target are fused into a main target, and a split inhibition zone in front of the main target is determined; whether the third target is within the split inhibition zone and whether the longitudinal speed difference between the main target and the third target is within a speed difference threshold range; if the third target is within the split inhibition zone and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, the output of the third target is suppressed.

10. A vehicle, characterized in that: include: A vehicle body, wherein the vehicle body is equipped with an intelligent driving assistance system; The first sensor and the second sensor are provided on the vehicle body and are used to detect a neighboring vehicle target traveling in the same direction in an adjacent lane in front of the vehicle; A target fusion module is used to determine whether the first target detected by the first sensor, the second target detected by the second sensor, and the third target meet the fusion conditions; If the first target and the second target meet the fusion conditions, and the third target does not meet the fusion conditions, the first target and the second target are fused into a main target, and a split inhibition zone in front of the main target is determined; it is judged whether the third target is in the split inhibition zone, and whether the longitudinal speed difference between the main target and the third target is within the speed difference threshold range; if the third target is in the split inhibition zone, and the longitudinal speed difference between the main target and the third target is within the speed difference threshold range, the third target is suppressed from being output to the electronic control unit in the intelligent driving assistance system.

Images