Method and device for determining obstacle vehicle behind vehicle

Abstract

The present application discloses a method and device for determining an obstacle vehicle behind a vehicle. The method comprises: first, calculating the historical trajectory of the vehicle for the first N cycles based on the yaw angular velocity and speed of the vehicle, where N is a positive integer greater than 0. Then, using the vehicle's forward-facing camera to obtain lane line information, and based on the lane line information, calculating the lane width of the vehicle's lane and the lateral intercept of the lane centerline, the obstacle vehicle behind the vehicle can be determined based on the historical trajectory of the vehicle for the first N cycles, as well as the lane width of the vehicle's lane and the lateral intercept of the lane centerline. In this way, the obstacle vehicle behind the vehicle can be quickly and accurately determined without increasing the mass production cost of the automatic lane change assisted driving system, providing an effective reference for the automatic lane change assisted driving system's rear lane change safety space estimation, thereby avoiding the occurrence of traffic accidents.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method and device for determining an obstacle vehicle behind a vehicle. Background Art

[0002] With the rapid development of intelligent driving technology, more and more automobile manufacturers want to integrate Adaptive Cruise Control (ACC) with Lane Keeping Assist (LKA) and Autonomous Lane Change (ALC) to form a more powerful driving assistance system. This requires the system to not only screen for ACC's obstacle vehicles (i.e., the nearest vehicle in front of the lane), but also screen the adjacent lane in the direction of the vehicle's lane change, as well as the nearest obstacle vehicles in front and behind the adjacent lane. It also needs to be able to suppress lane changes when there is a risk of collision between the vehicle and the obstacle vehicle to avoid accidents.

[0003] However, due to the widespread application and popularity of ACC, the research on obstacle vehicle screening in the automotive industry is basically focused on the front, while there is little research on the screening method of obstacle vehicles behind the vehicle. Therefore, how to quickly and accurately determine the obstacle vehicles behind the vehicle to provide an effective reference for the rear lane change safety space estimation of the vehicle's automatic lane change assistance system is an urgent problem to be solved. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to provide a method and device for determining an obstacle vehicle behind a vehicle, which can use the on-board forward camera and two rear millimeter-wave corner radars to quickly and accurately determine the obstacle vehicle behind the vehicle without increasing the mass production cost of the automatic lane change assisted driving system, thereby providing an effective reference for the rear lane change safety space estimation of the automatic lane change assisted driving system and avoiding the occurrence of traffic accidents.

[0005] In a first aspect of the present application, a method for determining an obstacle vehicle behind a vehicle is proposed, comprising:

[0006] Calculating the historical trajectory of the vehicle for the previous N cycles based on the yaw rate and speed of the vehicle, where N is a positive integer greater than 0;

[0007] Acquiring lane line information using a forward-facing camera of the vehicle, and calculating the lane width and the lateral intercept of the lane centerline of the lane where the vehicle is located based on the lane line information;

[0008] An obstacle vehicle behind the vehicle is determined based on the historical trajectory of the vehicle in the previous N cycles, as well as the lane width and the lateral intercept of the lane centerline of the lane where the vehicle is located.

[0009] In an optional implementation, the historical trajectory of the vehicle in the first N cycles includes the abscissa and ordinate of the vehicle in the first N cycles;

[0010] After acquiring lane line information using the forward-facing camera of the vehicle and calculating the lane width and the lateral intercept of the lane centerline of the lane where the vehicle is located based on the lane line information, the method further includes:

[0011] Storing the horizontal coordinates and vertical coordinates of the vehicle and the lateral intercept of the lane centerline for the first N cycles;

[0012] determining whether the vehicle is changing lanes;

[0013] If so, updating the stored lateral intercept of the lane centerline;

[0014] If not, the distance between the vehicle behind the vehicle and the center line of the lane is calculated.

[0015] In an optional implementation, calculating the distance between the vehicle behind the vehicle and the centerline of the lane includes:

[0016] Using a vehicle-mounted corner radar behind the vehicle, obtaining the horizontal coordinate and vertical coordinate of the vehicle behind the vehicle in the vehicle coordinate system;

[0017] Associating the moments in the vehicle's historical trajectory at which the vehicle behind the vehicle is aligned in longitudinal position with the vehicle behind the vehicle based on the abscissa and ordinate of the vehicle behind the vehicle in the vehicle coordinate system and the abscissa and ordinate of the vehicle in the previous N cycles;

[0018] According to the time, a distance between a vehicle behind the vehicle and the center line of the lane is calculated.

[0019] In an optional implementation, determining an obstacle vehicle behind the vehicle based on the historical trajectory of the vehicle in the previous N cycles, as well as the lane width and the lateral intercept of the lane centerline of the vehicle, includes:

[0020] An obstacle vehicle behind the vehicle is determined from the rear vehicles according to the distance between the rear vehicle and the center line of the lane.

[0021] In an optional implementation, determining an obstacle vehicle behind the vehicle from the rear vehicles based on the distance between the rear vehicle and the center line of the lane includes:

[0022] Determining the lane in which each of the rear vehicles is located based on the distance between the rear vehicle of the vehicle and the center line of the lane;

[0023] According to the principle of the shortest longitudinal distance, the obstacle vehicles located in the lane where the vehicle is located, the lane changing lane and the adjacent lane of the lane changing lane are screened out from the rear vehicles.

[0024] Corresponding to the above-mentioned method for determining an obstacle vehicle behind a vehicle, the present application proposes a device for determining an obstacle vehicle behind a vehicle, comprising:

[0025] A first calculation unit is configured to calculate a historical trajectory of the vehicle for the previous N cycles based on the yaw rate and the vehicle speed of the vehicle, where N is a positive integer greater than 0;

[0026] a second calculation unit, configured to obtain lane line information using a forward-facing camera of the vehicle, and calculate a lane width and a lateral intercept of a lane centerline of the lane where the vehicle is located based on the lane line information;

[0027] The determining unit is used to determine an obstacle vehicle behind the vehicle based on the historical trajectory of the vehicle in the previous N cycles, the lane width of the lane where the vehicle is located, and the lateral intercept of the lane centerline.

[0028] In an optional implementation, the historical trajectory of the vehicle in the first N cycles includes the horizontal coordinates and vertical coordinates of the vehicle in the first N cycles; and the apparatus further includes:

[0029] a storage unit, configured to store the abscissa and ordinate of the vehicle and the lateral intercept of the lane centerline for the first N cycles;

[0030] a judgment unit, configured to judge whether the vehicle is changing lanes;

[0031] an updating unit, configured to update the stored lateral intercept of the lane centerline if it is determined that the vehicle is changing lanes;

[0032] The third calculation unit is configured to calculate the distance between a vehicle behind the vehicle and the center line of the lane if it is determined that the vehicle does not change lanes.

[0033] In an optional implementation, the third computing unit includes:

[0034] an acquisition subunit, configured to acquire the horizontal coordinate and the vertical coordinate of the vehicle behind the vehicle in the vehicle coordinate system using a vehicle-mounted corner radar behind the vehicle;

[0035] an associating subunit, configured to associate, based on the abscissa and ordinate of the vehicle behind the vehicle in the vehicle coordinate system and the abscissa and ordinate of the vehicle in the previous N cycles, the moments in the vehicle's historical trajectory at which the vehicle behind the vehicle is aligned in longitudinal position;

[0036] The calculation subunit is used to calculate the distance between the vehicle behind the vehicle and the center line of the lane according to the moment.

[0037] In an optional implementation manner, the determining unit is specifically configured to:

[0038] An obstacle vehicle behind the vehicle is determined from the rear vehicles according to the distance between the rear vehicle and the center line of the lane.

[0039] In an optional implementation, the determining unit includes:

[0040] a determination subunit, configured to determine the lane in which each of the rear vehicles is located based on the distance between the rear vehicle of the vehicle and the center line of the lane;

[0041] The screening subunit is used to screen out obstacle vehicles located in the lane where the vehicle is located, the lane changing lane, and the adjacent lane of the lane changing lane from each of the rear vehicles based on the principle of the shortest longitudinal distance.

[0042] It can be seen that the embodiments of the present application have the following beneficial effects:

[0043] An embodiment of the present application provides a method and device for determining an obstructing vehicle behind a vehicle. First, the vehicle's historical trajectory for the previous N cycles is calculated based on the vehicle's yaw rate and speed, where N is a positive integer greater than 0. Lane line information is then acquired using the vehicle's forward-facing camera, and based on the lane line information, the lane width of the vehicle's lane and the lateral intercept of the lane centerline are calculated. Furthermore, the obstructing vehicle behind the vehicle can be determined based on the vehicle's historical trajectory for the previous N cycles, as well as the lane width and the lateral intercept of the lane centerline of the vehicle's lane. This allows for rapid and accurate determination of obstructing vehicles behind the vehicle without increasing the mass production cost of the automatic lane change assisted driving system, providing an effective reference for estimating the rear lane change safety space of the automatic lane change assisted driving system and avoiding traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 A flowchart of a method for determining an obstacle vehicle behind a vehicle provided in an embodiment of the present application;

[0046] Figure 2 A schematic diagram of the positions of the vehicle-mounted forward camera and the rear vehicle-mounted corner radar provided in an embodiment of the present application;

[0047] Figure 3 A schematic diagram showing the position of a vehicle coordinate system at a previous moment relative to the current moment provided in an embodiment of the present application;

[0048] Figure 4 A schematic diagram of the positions of the vehicle and the vehicle behind it in the vehicle's coordinate system at the current moment, provided in an embodiment of the present application;

[0049] Figure 5 A schematic diagram of the position of the vehicle behind the vehicle provided in an embodiment of the present application;

[0050] Figure 6 A schematic diagram of a device for determining an obstacle vehicle behind a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0052] As we all know, the application of intelligent driving technology is becoming more and more extensive because it can not only reduce driving pressure, but also greatly improve the safety factor and effectively reduce the incidence of traffic accidents. In addition, more and more automobile manufacturers hope to integrate ACC with LKA and ALC to form a more powerful driving assistance system. This requires the system to not only screen out ACC's obstacle vehicles (that is, the nearest vehicle in front of the lane), but also screen the adjacent lane in the direction of the vehicle's lane change and the nearest obstacle vehicles in front and behind the adjacent lane. It can also suppress lane changes when there is a risk of collision between the vehicle and the obstacle vehicle to avoid accidents.

[0053] However, due to the widespread application and popularity of ACC, the research on the identification of obstacle vehicles in the automotive industry is basically focused on obstacle vehicles in front, while there is little research on the screening method of obstacle vehicles behind the vehicle. Therefore, how to quickly and accurately identify obstacle vehicles behind the vehicle to provide an effective reference for the rear lane change safety space estimation of the vehicle's automatic lane change assistance system has become an urgent problem to be solved.

[0054] Based on this, the present application proposes a method and device for determining an obstacle vehicle behind a vehicle, which can quickly and accurately determine the obstacle vehicle behind the vehicle without increasing the mass production cost of the automatic lane change assisted driving system.

[0055] The following is a detailed description of the method for determining an obstacle vehicle behind a vehicle provided by the embodiment of the present application with reference to the accompanying drawings. Figure 1 As shown, it shows a flow chart of an embodiment of a method for determining an obstacle vehicle behind a vehicle provided by an embodiment of the present application. This embodiment may include the following steps:

[0056] S101: Calculate the historical trajectory of the vehicle for the previous N cycles based on the yaw rate and speed of the vehicle, where N is a positive integer greater than 0.

[0057] In this embodiment, in order to accurately determine the obstacle vehicle behind the vehicle, it is first necessary to calculate the historical trajectory of the vehicle in the previous N cycles to perform the subsequent step S103, where N is a positive integer greater than 0.

[0058] Specifically, the vehicle's operating data, such as the vehicle's yaw rate, longitudinal speed, and data collection period, can be collected using onboard sensors. The operating data is then preprocessed as follows to obtain a processed data set, as shown below:

[0059] S1={ω,v,T}

[0060] Where ω represents the vehicle's yaw rate; v represents the vehicle's longitudinal speed; and T represents the software operating cycle. The specific value can be set according to actual conditions. For example, if the software operating frequency can be set to 50 Hz, the corresponding software operating cycle is 0.02 s.

[0061] Then, the collected vehicle motion information can be saved for N cycles to obtain the vector corresponding to the vehicle's historical trajectory information for the first N cycles, as shown below:

[0062]

[0063]

[0064] Among them, ω i 、vi represent the yaw rate and longitudinal speed of the vehicle in the previous i cycles, respectively, where i=1, 2, 3, ...N.

[0065] It should be noted that, assuming that Figure 2 The detection range of the rear corner radar of the automatic lane change assist system shown is 80 meters. Therefore, for candidate vehicles behind the vehicle, only the distance 80 meters behind the vehicle needs to be monitored. The minimum speed of the automatic lane change function can be set to 60 km / h. At this time, driving 80 meters at 60 km / h requires 4.8 seconds, or 240 cycles. Therefore, the value of N can be set to 240.

[0066] Next, using the vehicle's historical yaw rate vector, the vehicle's heading angle vector relative to the vehicle's current coordinate system for the previous N cycles can be calculated as follows:

[0067]

[0068] in, It represents the heading angle of the vehicle in the previous i cycles relative to the current coordinate system of the vehicle, i = 1, 2, 3, ... N, such as like Figure 3 As shown. Further, It can be calculated by the following formula:

[0069]

[0070] Among them, the initial value of the heading angle It represents the heading angle of the vehicle at the current moment relative to the vehicle's coordinate system at the current moment, so the initial value is 0.

[0071] The company that uses the historical heading angle vector of the vehicle to calculate the horizontal and vertical coordinate vectors of the vehicle in the previous N cycles relative to the current coordinate system of the vehicle is as follows:

[0072]

[0073]

[0074] Among them, X i 、Y i They represent the ordinate and abscissa of the vehicle’s previous i cycles in the vehicle’s current coordinate system, i = 1, 2, 3, …N.

[0075] Furthermore, X i 、Y i It can be calculated by the following formula:

[0076]

[0077] Among them, the initial values X0 and Y0 respectively represent the vertical and horizontal coordinates of the vehicle at the current moment in the coordinate system of the vehicle at the current moment, both of which are 0.

[0078] S102: Utilize the vehicle's forward-facing camera to obtain lane line information, and calculate the lane width and the lateral intercept of the lane centerline of the vehicle's lane based on the lane line information.

[0079] In this embodiment, in order to accurately determine the obstacle vehicle behind the vehicle, it is necessary not only to calculate the historical trajectory of the vehicle in the previous N cycles, but also to use the vehicle's forward camera to obtain lane line information, and based on the obtained lane line information, calculate the lane width of the lane where the vehicle is located and the lateral intercept of the lane centerline, which are used together to execute the subsequent step S103.

[0080] Specifically, we can first use Figure 2 The forward camera of the vehicle shown captures the heading angle α of the left and right lane lines of the lane L , α R and the transverse intercept d yL d yR The lane line information data is preprocessed as follows to obtain the processed data set, as shown below:

[0081] S2={α L , d yL , α R , d yR}

[0082] Among them, the heading angle α L , α R Respectively represent the angles between the tangent lines of the left and right lane lines at X=0 and the X-axis of the vehicle coordinate system; the lateral intercept d yL d yL They represent the lateral intercepts of the left and right lane line equations in the vehicle coordinate system, that is, the function values at X=0.

[0083] Then, the lane width of the vehicle can be calculated using the following formula:

[0084]

[0085] Among them, d Lane Indicates the lane width of the vehicle.

[0086] In addition, the lateral intercept of the current lane centerline can be calculated using the following formula:

[0087]

[0088] Among them, d yCIndicates the lateral intercept of the current lane centerline.

[0089] S103: Determine an obstacle vehicle behind the vehicle based on the historical trajectory of the vehicle in the previous N cycles, as well as the lane width and the lateral intercept of the lane centerline of the vehicle.

[0090] In this embodiment, after calculating the historical trajectory of the vehicle in the previous N cycles in step S101 and calculating the lane width and the lateral intercept of the lane centerline of the vehicle in step S102, the obstacle vehicle behind the vehicle can be further determined based on the obtained data.

[0091] It should be noted that, in a possible implementation of the embodiment of the present application, the historical trajectory of the vehicle in the previous N cycles may include the abscissa and ordinate of the vehicle in the previous N cycles. Then, after calculating the lane width and the lateral intercept of the lane centerline of the vehicle, the following steps AD may be further performed:

[0092] Step A: Store the horizontal and vertical coordinates of the vehicle and the lateral intercept of the lane centerline for the first N cycles.

[0093] Step B: Determine whether the vehicle is changing lanes. If so, proceed to step C; if not, proceed to step D.

[0094] Step C: Update the stored lateral intercept of the lane centerline.

[0095] Step D: Calculate the distance between the vehicle behind the vehicle and the center line of the lane.

[0096] Specifically, in this implementation, after calculating the horizontal and vertical coordinates of the vehicle for the first N cycles and the lateral intercept of the centerline of the lane where the vehicle is located in step S101, first, this information can be stored in a storage pool in chronological order. The specific storage format is shown in the following table:

[0097] Period T Lateral intercept of lane centerline The horizontal coordinate of the vehicle The vertical coordinate of the vehicle <![CDATA[T1]]> <![CDATA[d yC1 ]]> <![CDATA[Y1]]> <![CDATA[X1]]> <![CDATA[T2]]> <![CDATA[d yC2 ]]> <![CDATA[Y2]]> <![CDATA[X2]]> <![CDATA[T3]]> <![CDATA[d yC3 ]]> <![CDATA[Y2]]> <![CDATA[X2]]> … … … … <![CDATA[T N ]]> <![CDATA[d yCN ]]> <![CDATA[Y N ]]> <![CDATA[X N ]]>

[0098] Among them, T i represents the first i cycles; d yCi Represents the lateral intercept of the lane centerline in the first i cycles; where i = 1, 2, 3, ...N.

[0099] Then, it is determined whether the vehicle changes lanes. If so, the stored lateral intercept of the lane centerline is updated; if not, the distance between the vehicle behind the vehicle and the lane centerline is calculated.

[0100] The basis for judging whether a vehicle has changed lanes is: if the lateral intercept of the lane centerline changes suddenly and the mutation value exceeds the set threshold, the vehicle is considered to have changed lanes.

[0101] |d yC0 -d yC1 |>d lanechange

[0102] Among them, d yC0 Indicates the lateral intercept of the lane centerline at the current moment; d yC1 Indicates the lateral intercept of the lane centerline at the previous moment; d lanechange The lane centerline sudden change threshold for determining lane change is related to the lane width calculated in step S102. For example, the value can be: d lanechange =d Lane -0.2.

[0103] If a vehicle is determined to be changing lanes, it is further necessary to determine whether the vehicle is changing lanes to the left or right. Specifically, since a vehicle changing lanes will cause its lane to change from the original lane to the target lane, the centerline of its lane will also change from the original lane centerline to the target lane centerline. Therefore, when it is determined that the vehicle is changing lanes to the left, the lateral intercept of the lane centerline in the first N cycles needs to be increased by one lane width. The updated storage pool is shown in the following table:

[0104] Period T Lateral intercept of lane centerline The horizontal coordinate of the vehicle The vertical coordinate of the vehicle <![CDATA[T1]]> <![CDATA[d yC1 +d Lane ]]> <![CDATA[Y1]]> <![CDATA[X1]]> <![CDATA[T2]]> <![CDATA[d yC2 +d Lane ]]> <![CDATA[Y2]]> <![CDATA[X2]]> <![CDATA[T3]]> <![CDATA[d yC3 +d Lane ]]> <![CDATA[Y2]]> <![CDATA[X2]]> … … … … <![CDATA[T N ]]> <![CDATA[d yCN +d Lane ]]> <![CDATA[Y N ]]> <![CDATA[X N ]]>

[0105] Furthermore, the formula for determining whether a vehicle changes lanes to the left is as follows:

[0106] d yC0 -d yC1 >0

[0107] When it is determined that the vehicle is changing lanes to the right, the lateral intercept of the lane centerline in the first N cycles needs to be reduced by one lane width. The updated storage pool is as follows:

[0108]

[0109]

[0110] Furthermore, the formula for determining whether a vehicle changes lanes to the right is as follows:

[0111] d yC0 -d yC1 <0

[0112] However, if it is determined that the vehicle is not changing lanes, the distance between the vehicle behind the vehicle and the center line of the lane can be further calculated. The specific implementation process may include the following steps D1-D3:

[0113] Step D1: Using the on-board corner radar behind the vehicle, obtain the horizontal coordinate and vertical coordinate of the vehicle behind the vehicle in the vehicle coordinate system.

[0114] Step D2: Based on the horizontal and vertical coordinates of the vehicle behind the vehicle in the vehicle coordinate system and the horizontal and vertical coordinates of the vehicle in the previous N cycles, associate the moments in the vehicle's historical trajectory when the longitudinal position of the vehicle behind the vehicle is aligned with that of the vehicle behind the vehicle.

[0115] Step D3: Calculate the distance between the vehicle behind the vehicle and the center line of the lane based on the time

[0116] Specifically, we can first use Figure 2 The vehicle-mounted corner radar behind the vehicle shown collects the horizontal and vertical coordinates of the vehicle behind the vehicle in the coordinate system of the vehicle, and preprocesses these data as follows to obtain the processed data set as shown below:

[0117] S3={x T1 ,y T1 , x T2 ,y T2 , x T3 ,y T3 ,…,x Tn ,y Tn}

[0118] Among them, x T1 , x T2 , x T3 ,...,x Tn Respectively represent the vertical coordinates of the vehicles 1, 2, 3...n behind the vehicle; T1 ,y T2 ,y T3 ,...,y Tn The horizontal coordinates of the vehicles 1, 2, 3, ..., n behind the vehicle are respectively represented. The value of n depends on the number of vehicles behind the vehicle detected by the rear corner radar.

[0119] Then, for the rear vehicle detected in the current frame, its vertical coordinate x T Compare it with the vertical coordinates of the vehicle in the previous N cycles in the storage pool and find the T corresponding to the closest vertical coordinate k The time is the time when the associated vehicle is aligned with the vehicle behind it in the historical trajectory. The details are shown in the following table:

[0120]

[0121]

[0122] Then, the target vehicle position can be compared with T k The historical position of the vehicle at the moment is restored in the current vehicle coordinate system, such as Figure 4 As shown, based on the geometric relationship in the figure, the following formula is used to calculate the distance between the vehicle behind the vehicle and the center line of the lane:

[0123] Y T2LC =Y T -Y k -d yCk

[0124] Among them, Y T2LC Indicates the distance between the vehicle behind the vehicle and the center line of the lane. T2LC >0, it means the vehicle behind is on the left side of the lane centerline; when Y T2LC When <0, it means the vehicle behind is to the right of the center line of the lane.

[0125] On this basis, an optional implementation method is that the specific implementation process of the above-mentioned step S103 "determining the obstacle vehicle behind the vehicle based on the historical trajectory of the vehicle in the previous N cycles, as well as the lane width of the lane where the vehicle is located and the lateral intercept of the lane centerline" may include: determining the obstacle vehicle behind the vehicle from the rear vehicles based on the distance between the rear vehicle of the vehicle and the lane centerline.

[0126] Specifically, in this implementation, first, the distance Y between the vehicle behind the vehicle and the center line of the lane can be used to calculate the distance between the vehicle behind the vehicle and the center line of the lane. T2LC In different intervals, each vehicle behind the vehicle is matched with different lanes to determine the lanes that each vehicle behind is in. The specific matching interval is determined by the lane width, as shown in the following table:

[0127] <![CDATA[Distance Y between the rear vehicle and the center line of this lane T2LC > Lane of the vehicle behind <![CDATA[[2.5d Lane ,1.5d Lane )]]> Left left lane <![CDATA[[1.5d Lane ,0.5d Lane )]]> Left Lane <![CDATA[[0.5d Lane ,-0.5d Lane ]]>]> This lane <![CDATA[[-1.5d Lane ,-0.5d Lane )]]> Right Lane <![CDATA[[-2.5d Lane ,-1.5d Lane )]]> Right lane

[0128] Then, according to the direction of the driver's turn signal, all the rear vehicles in the lane, the lane changing lane (i.e., the target lane), and the adjacent lane of the lane changing lane (i.e., the adjacent lane in the lane changing direction) can be screened out. Then, according to the principle of the shortest longitudinal distance, the obstacle vehicles located in the lane, the target lane, and the adjacent lane in the lane changing direction can be screened out from these rear vehicles, such as Figure 5 As shown in the obstacle vehicle in the middle frame. This can provide an effective reference for the rear lane change safety space estimation of the automatic lane change assist driving system, thus avoiding the occurrence of traffic accidents.

[0129] In summary, this embodiment provides a method for determining an obstructing vehicle behind a vehicle. First, the vehicle's historical trajectory for the previous N cycles is calculated based on the vehicle's yaw rate and speed, where N is a positive integer greater than 0. Lane line information is then acquired using the vehicle's forward-facing camera. Based on this lane line information, the lane width and lateral intercept of the vehicle's lane centerline are calculated. Furthermore, the obstructing vehicle behind the vehicle can be determined based on the vehicle's historical trajectory for the previous N cycles, as well as the lane width and lateral intercept of the lane centerline of the vehicle's lane. This method allows for rapid and accurate identification of obstructing vehicles behind the vehicle without increasing the mass production cost of the automatic lane change assistance system. This method provides an effective reference for estimating the rear lane change safety space within the automatic lane change assistance system, thereby preventing traffic accidents.

[0130] See also Figure 6 As shown, the present application also provides an embodiment of a device for determining an obstacle vehicle behind a vehicle, which may include:

[0131] A first calculation unit 601 is configured to calculate a historical trajectory of the vehicle for the previous N cycles based on the yaw rate and speed of the vehicle, where N is a positive integer greater than 0;

[0132] A second calculation unit 602 is configured to obtain lane line information using a forward-facing camera of the vehicle, and calculate a lane width and a lateral intercept of a lane centerline of the lane where the vehicle is located based on the lane line information;

[0133] The determination unit 603 is configured to determine an obstacle vehicle behind the vehicle based on the historical trajectory of the vehicle in the previous N cycles, as well as the lane width and the lateral intercept of the lane centerline of the lane where the vehicle is located.

[0134] In some possible implementations of the present application, the historical trajectory of the vehicle in the first N cycles includes the horizontal coordinates and vertical coordinates of the vehicle in the first N cycles; and the apparatus further includes:

[0135] a storage unit, configured to store the abscissa and ordinate of the vehicle and the lateral intercept of the lane centerline for the first N cycles;

[0136] a judgment unit, configured to judge whether the vehicle is changing lanes;

[0137] an updating unit, configured to update the stored lateral intercept of the lane centerline if it is determined that the vehicle is changing lanes;

[0138] The third calculation unit is configured to calculate the distance between a vehicle behind the vehicle and the center line of the lane if it is determined that the vehicle does not change lanes.

[0139] In some possible implementations of the present application, the third computing unit includes:

[0140] an acquisition subunit, configured to acquire the horizontal coordinate and the vertical coordinate of the vehicle behind the vehicle in the vehicle coordinate system using a vehicle-mounted corner radar behind the vehicle;

[0141] an associating subunit, configured to associate, based on the abscissa and ordinate of the vehicle behind the vehicle in the vehicle coordinate system and the abscissa and ordinate of the vehicle in the previous N cycles, the moments in the vehicle's historical trajectory at which the vehicle behind the vehicle is aligned in longitudinal position;

[0142] The calculation subunit is used to calculate the distance between the vehicle behind the vehicle and the center line of the lane according to the moment.

[0143] In some possible implementations of the present application, the determining unit 603 is specifically configured to:

[0144] An obstacle vehicle behind the vehicle is determined from the rear vehicles according to the distance between the rear vehicle and the center line of the lane.

[0145] In some possible implementations of the present application, the determining unit 603 includes:

[0146] a determination subunit, configured to determine the lane in which each of the rear vehicles is located based on the distance between the rear vehicle of the vehicle and the center line of the lane;

[0147] The screening subunit is used to screen out obstacle vehicles located in the lane where the vehicle is located, the lane changing lane, and the adjacent lane of the lane changing lane from each of the rear vehicles based on the principle of the shortest longitudinal distance.

[0148] As can be seen from the above embodiments, the apparatus for determining an obstructing vehicle behind a vehicle provided in the embodiments of the present application first calculates the vehicle's historical trajectory for the previous N cycles based on the vehicle's yaw rate and speed, where N is a positive integer greater than 0. Lane line information is then acquired using the vehicle's forward-facing camera, and based on this lane line information, the lane width and lateral intercept of the centerline of the lane in which the vehicle is located are calculated. Furthermore, the obstructing vehicle behind the vehicle can be determined based on the vehicle's historical trajectory for the previous N cycles, as well as the lane width and lateral intercept of the centerline of the lane in which the vehicle is located. This allows for rapid and accurate determination of obstructing vehicles behind the vehicle without increasing the mass production cost of the automatic lane change assisted driving system, providing an effective reference for estimating the rear lane change safety space of the automatic lane change assisted driving system and thus avoiding the occurrence of traffic accidents.

[0149] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in each embodiment of the present application or certain parts of the embodiments.

[0150] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the methods.

[0151] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further 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 comprising the element.

[0152] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining an obstacle vehicle behind a vehicle, characterized in that: include: Calculating the historical trajectory of the vehicle for the previous N cycles based on the yaw rate and speed of the vehicle, where N is a positive integer greater than 0; Acquiring lane line information using a forward-facing camera of the vehicle, and calculating the lane width and the lateral intercept of the lane centerline of the lane where the vehicle is located based on the lane line information; Determine an obstacle vehicle behind the vehicle based on the historical trajectory of the vehicle in the previous N cycles, as well as the lane width and the lateral intercept of the lane centerline of the vehicle; The determining of an obstacle vehicle behind the vehicle based on the historical trajectory of the vehicle in the previous N cycles, as well as the lane width and the lateral intercept of the lane centerline of the lane where the vehicle is located, includes: Using a vehicle-mounted corner radar behind the vehicle, obtaining the horizontal coordinate and vertical coordinate of the vehicle behind the vehicle in the vehicle coordinate system; Based on the horizontal and vertical coordinates of the vehicle behind the vehicle in the vehicle coordinate system, as well as the horizontal and vertical coordinates of the vehicle in the previous N cycles, the moments in the vehicle's historical trajectory at which the vehicle behind the vehicle is aligned in the longitudinal position are associated; based on the moments, the distance between the vehicle behind the vehicle and the centerline of the lane is calculated; and based on the distance between the vehicle behind the vehicle and the centerline of the lane, an obstacle vehicle behind the vehicle is determined from among the rear vehicles.

2. The method according to claim 1, characterized in that The historical trajectory of the vehicle in the first N cycles includes the horizontal coordinates and vertical coordinates of the vehicle in the first N cycles; After acquiring lane line information using the forward-facing camera of the vehicle and calculating the lane width and the lateral intercept of the lane centerline of the lane where the vehicle is located based on the lane line information, the method further includes: Storing the horizontal coordinates and vertical coordinates of the vehicle and the lateral intercept of the lane centerline for the first N cycles; determining whether the vehicle is changing lanes; If so, updating the stored lateral intercept of the lane centerline; If not, the distance between the vehicle behind the vehicle and the center line of the lane is calculated.

3. The method according to claim 1, characterized in that The step of determining an obstacle vehicle behind the vehicle from the rear vehicles based on the distance between the rear vehicle and the center line of the lane includes: Determining the lane in which each rear vehicle is located based on the distance between the rear vehicle of the vehicle and the center line of the lane; According to the principle of the shortest longitudinal distance, the obstacle vehicles located in the lane where the vehicle is located, the lane changing lane and the adjacent lane of the lane changing lane are screened out from the rear vehicles.

4. A device for determining an obstacle vehicle behind a vehicle, characterized in that: include: A first calculation unit is configured to calculate a historical trajectory of the vehicle for the previous N cycles based on the yaw rate and the vehicle speed of the vehicle, where N is a positive integer greater than 0; a second calculation unit, configured to obtain lane line information using a forward-facing camera of the vehicle, and calculate a lane width and a lateral intercept of a lane centerline of the lane where the vehicle is located based on the lane line information; a determining unit, configured to determine an obstacle vehicle behind the vehicle based on a historical trajectory of the vehicle in previous N cycles, a lane width of the lane in which the vehicle is located, and a lateral intercept of a lane centerline; The determining device uses a vehicle-mounted angle radar behind the vehicle to obtain the horizontal coordinate and the vertical coordinate of the vehicle behind the vehicle in the vehicle coordinate system; Correlating, based on the abscissa and ordinate of the vehicle behind the vehicle in the vehicle coordinate system and the abscissa and ordinate of the vehicle in the previous N cycles, the moments in the vehicle's historical trajectory at which the vehicle behind the vehicle is aligned in longitudinal position; and calculating, based on the moments, the distance between the vehicle behind the vehicle and the centerline of the lane; The determining unit is specifically configured to: An obstacle vehicle behind the vehicle is determined from the rear vehicles according to the distance between the rear vehicle and the center line of the lane.

5. The device according to claim 4, characterized in that The historical trajectory of the vehicle in the previous N cycles includes the horizontal coordinates and vertical coordinates of the vehicle in the previous N cycles; the device further includes: a storage unit, configured to store the abscissa and ordinate of the vehicle and the lateral intercept of the lane centerline for the first N cycles; a judgment unit, configured to judge whether the vehicle is changing lanes; an updating unit, configured to update the stored lateral intercept of the lane centerline if it is determined that the vehicle is changing lanes; The third calculation unit is configured to calculate the distance between a vehicle behind the vehicle and the center line of the lane if it is determined that the vehicle does not change lanes.

6. The device according to claim 4, characterized in that The determining unit includes: a determination subunit, configured to determine the lane in which each of the rear vehicles is located based on the distance between the rear vehicle of the vehicle and the center line of the lane; The screening subunit is used to screen out obstacle vehicles located in the lane where the vehicle is located, the lane changing lane, and the adjacent lane of the lane changing lane from each of the rear vehicles based on the principle of the shortest longitudinal distance.

Images