Lane changing behavior recognition method, electronic equipment, vehicle and program product

Abstract

The invention provides a lane changing behavior recognition method, electronic equipment, a vehicle and a program product, and relates to the technical field of intelligent driving. The method comprises the steps that each frame of collection data of a target vehicle is acquired, and each frame of collection data comprises obstacle vehicle information and lane line information; according to the obstacle vehicle information and the lane line information of each frame of acquisition data, determining relative position information of an obstacle vehicle corresponding to each frame of acquisition data and a lane line; and recognizing the lane changing behavior of the obstacle vehicle according to the relative position information corresponding to each frame of acquisition data. The method and device are used for solving the problem that in the prior art, the validity of recognizing the lane changing scene from the data collected from the vehicle end is not high.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and in particular to a lane change behavior recognition method, electronic equipment, vehicle, and program product. Background Art

[0002] In the process of autonomous driving development, the construction of scenario data sets is crucial, as scenario data sets can provide sufficient data support for algorithms, simulations, and tests. Scenario data sets can be obtained through data mining. The core task of data mining is to extract scenario data with specific combination conditions from various raw data collected from the vehicle through various means, such as data on pedestrians "looking out" while the vehicle is driving, data on sudden braking of vehicles in front of the vehicle, etc.

[0003] The vehicle ahead changes lanes left or right, which is a common scenario encountered during the operation of autonomous vehicles. The sudden lane change of the vehicle ahead may increase the driving difficulty of the autonomous vehicle. If the vehicle ahead does not issue a lane change warning in advance or the autonomous vehicle does not respond in time, a traffic accident may occur. Therefore, how to effectively identify the left / right lane change behavior of the vehicle ahead from a large amount of data collected by the vehicle, and then feed back the scene data corresponding to the behavior to the R&D engineers for targeted optimization algorithms is crucial to the continuous iteration of the capabilities of autonomous vehicles. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure provide a lane change behavior recognition method, electronic device, vehicle and program product to solve the problem of low effectiveness in identifying lane change scenarios from data collected from the vehicle in the prior art.

[0005] In a first aspect, the present disclosure provides a lane change behavior recognition method, comprising: Obtaining each frame of collected data of the target vehicle, wherein each frame of collected data includes obstacle vehicle information and lane line information; Determine the relative position information between the obstacle vehicle and the lane line corresponding to each frame of collected data according to the obstacle vehicle information and the lane line information of each frame of collected data; wherein the relative position information includes a line pressing mark, the line pressing mark is used to indicate line pressing or not, and when the line pressing mark is line pressing, the relative position information also includes a line pressing ratio; The lane changing behavior of the obstacle vehicle is identified according to the relative position information corresponding to each frame of collected data.

[0006] In a second aspect, the present disclosure provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores at least one computer program executable by the at least one processor, and the at least one computer program is executed by the at least one processor so that the at least one processor can execute the lane change behavior identification method as described in the first aspect.

[0007] In a third aspect, the present disclosure provides a vehicle, which is configured to execute the lane change behavior recognition method as described in the first aspect.

[0008] In a fourth aspect, the present disclosure provides a computer program product, which includes a computer program. When the computer program is executed in a processor, the lane change behavior recognition method described in the first aspect is implemented.

[0009] Optionally, the computer program may be stored in a readable storage medium of a computer device or in the cloud; and the processor of the computer device reads the computer program from the readable storage medium or in the cloud.

[0010] The embodiments provided by the present disclosure determine the relative position information of the obstacle vehicle and the lane line in each frame of collected data of the target vehicle based on the obstacle vehicle information and lane line information in each frame of collected data, and then identify the lane changing behavior of the obstacle vehicle based on the relative position information corresponding to each frame of collected data, thereby being able to simply and efficiently identify the lane changing behavior of the obstacle vehicle, thereby improving the efficiency of lane changing behavior identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0012] Figure 1 The figure is a schematic flow chart of the lane change behavior identification method in the embodiment of the present disclosure.

[0013] Figure 2 Shown is a schematic diagram of the obstacle vehicle coordinate system and the coordinates of the four corner points in an embodiment of the present disclosure.

[0014] Figure 3 Shown is a schematic diagram of the relative positions of an obstacle vehicle and a lane line in an embodiment of the present disclosure.

[0015] Figure 4 Shown is a schematic diagram of a method for calculating the pressing line ratio in an embodiment of the present disclosure.

[0016] Figure 5 Shown is a schematic diagram of an example of the implementation process of lane change recognition in an embodiment of the present disclosure.

[0017] Figure 6 Shown is a block diagram of a lane-changing behavior recognition device in an embodiment of the present disclosure.

[0018] Figure 7 FIG. 1 is a schematic diagram of the structure of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0020] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0021] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0022] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "including" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded. "Connected" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0023] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0024] The lane change behavior recognition method provided by the embodiment of the present disclosure is as follows: Figure 1 As shown, it mainly includes the following 101-103: 101. Acquire each frame of collected data of the target vehicle, wherein each frame of collected data includes obstacle vehicle information and lane line information.

[0025] The target vehicle may be any vehicle. In some scenarios, the target vehicle is a vehicle that executes the lane change recognition method. Of course, the lane change behavior recognition method provided by the disclosed embodiment is not limited to being executed by the target vehicle, but may also be executed by other terminal devices or servers that can obtain each frame of collected data of the target vehicle in a timely manner, which is not limited here.

[0026] The obstacle vehicle is a vehicle adjacent to the target vehicle and is a vehicle that requires the target vehicle to drive safely and needs to be paid special attention to. For example, the obstacle vehicle is the vehicle in front of the target vehicle or the vehicle in the adjacent lane adjacent to the target vehicle. For another example, the obstacle vehicle is all vehicles 4-100 meters in front of the target vehicle.

[0027] In the exemplary embodiment, the collected data comes from a data slice file (clip) in the format of .ebag or .record, each data slice file includes 10 seconds (s) of collected data, the collection frequency is 10 Hz, and there are 100 frames in total. This is only an example, and the embodiment of the present disclosure does not limit the specific collection method and storage method of the collected data.

[0028] Among them, each frame of collected data is arranged in the order of collection time.

[0029] It should be noted that each frame of data collected from the target vehicle may be collected using different sensing technologies. For example, each frame of data may be collected from the surrounding environment using sensors such as cameras, radars, and infrared sensors installed on the target vehicle.

[0030] 102. Determine the relative position information of the obstacle vehicle and the lane line corresponding to each frame of collected data based on the obstacle vehicle information and the lane line information; wherein the relative position information includes a line pressing mark, the line pressing mark is used to indicate line pressing or not, and when the line pressing mark is a line pressing, the relative position information also includes a line pressing ratio.

[0031] In some embodiments, determining the relative position information between the obstacle vehicle and the lane line corresponding to each frame of collected data according to the obstacle vehicle information and the lane line information of each frame of collected data includes: performing the following processing on each frame of collected data: According to the obstacle vehicle information of the collected data, the position coordinates of the four corner points of the obstacle vehicle are determined; according to the position coordinates of the four corner points of the obstacle vehicle and the lane line information, the relative position information of the obstacle vehicle and the lane line is determined.

[0032] In an exemplary embodiment, the relative position information of the obstacle vehicle and the lane line is determined based on the position coordinates of the four corner points of the obstacle vehicle and the lane line information, including: determining a lane line equation based on the lane line information; determining the relative position information of the obstacle vehicle and the lane line based on the position coordinates of the four corner points of the obstacle vehicle and the lane line equation.

[0033] Assume that the lane line equation is expressed as: y=a3×x 3 +a2×x 2 +a1×x+a0, substitute the position coordinates of multiple points in the lane line information into the preset lane line equation, determine the coefficients a3, a2, a1 and a0 of the lane line equation, and obtain the final lane line equation. After the lane line equation is determined, the coefficients a3, a2, a1 and a0 are all constants.

[0034] Among them, the position coordinates of multiple points in the lane line information are obtained based on the coordinate system of the collected data.

[0035] For example, the coordinate system of the collected data is set to have the extension direction of the front of the target vehicle as the x-axis direction, the extension direction of the target vehicle perpendicular to the body to the left as the y-axis direction, and the coordinate origin as the designated position of the target vehicle, such as the middle position of the front of the target vehicle as the coordinate origin. In addition, the coordinate system of the collected data can also be defined in other ways, which is not limited here.

[0036] The four corner points of the obstacle vehicle include the left front corner point, the right front corner point, the left rear corner point and the right rear corner point. It should be noted that the definition of front and back here is consistent with the definition of front and back of the vehicle.

[0037] In an exemplary embodiment, Figure 2 The figure shows a schematic diagram of the coordinate system of the obstacle vehicle and the coordinates of the four corner points. The process of obtaining the position coordinates of the four corner points of the obstacle vehicle includes: the obstacle vehicle information includes the position coordinates of the center point of the obstacle vehicle ( , ), orientation angle θ, length l, width w; Assuming that the orientation of the obstacle vehicle is positive, determine the coordinates of the four corner points A, B, C, and D in the obstacle vehicle coordinate system according to the length and width, which are A (-l / 2, -w / 2), B (l / 2, -w / 2), C (l / 2, w / 2), and D (-l / 2, w / 2); The coordinates of the four corner points in the obstacle vehicle coordinate system are rotated about the center of the obstacle vehicle coordinate system, and the rotated coordinates are expressed as: = The position coordinates of the four corner points in the obstacle vehicle coordinate system are obtained after selection, and the translation of the obstacle vehicle coordinate system relative to the target vehicle coordinate system is added to obtain the position coordinates of the four corner points in the target vehicle coordinate system, which is expressed as: = + ; The translation of the obstacle vehicle coordinate system relative to the target vehicle coordinate system, that is, the position coordinates of the center point of the obstacle vehicle.

[0038] In some embodiments, the four corner points include a left front corner point, a right front corner point, a left rear corner point, and a right rear corner point; the left front corner point and the right rear corner point located on the diagonal line constitute a first group of corner points, and the right front corner point and the left rear corner point located on the diagonal line constitute a second group of corner points; The determining the relative position information between the obstacle vehicle and the lane line according to the position coordinates of the four corner points of the obstacle vehicle and the lane line information includes: According to the position coordinates of the four corner points of the obstacle vehicle and the lane line information, determine whether two corner points in the first group of corner points are located on both sides of the lane line to obtain a first judgment result, and determine whether two corner points in the second group of corner points are located on both sides of the lane line to obtain a second judgment result; if both the first judgment result and the second judgment result are no, determine that the obstacle vehicle does not cross the lane line, and use the no-crossing line as the relative position information; if one of the first judgment result and the second judgment result is yes, determine that the obstacle vehicle crosses the lane line, determine the crossing line ratio according to the position coordinates of two target corner points and the lane line information, and use the crossing line and the crossing line ratio as the relative position information, wherein the target corner points are two corner points among the four corner points that are located on the diagonal line and on both sides of the lane line.

[0039] In an exemplary embodiment, Figure 3 The figure shows the relative position of the obstacle vehicle and the lane line. The obstacle vehicle has four corner points, namely A, B, C and D. A and C are the first set of corner points on the diagonal line, and B and D are the second set of corner points on the diagonal line. Substituting the x coordinate value of A into the lane line equation, the y coordinate y on the lane line is obtained. A_lane , substitute the x coordinate value of C into the lane line equation to get the y coordinate y on the lane line C_lane , determine the product (y A -y A_lane )×(y C -y C_lane ) is less than zero. If so, it means that A and C are on both sides of the lane line and the obstacle vehicle presses the lane line. Otherwise, if not, it means that A and C are on the same side of the lane line and the obstacle vehicle does not press the lane line. Similarly, a similar method is used to determine whether the obstacle vehicle presses the lane line based on B and D.

[0040] It should be noted that when any pair of the two diagonal points AC and BD are located on both sides of the lane line, it can be determined that the obstacle vehicle is pressing the lane line.

[0041] In some embodiments, determining the line pressing ratio based on the position coordinates of the two target corner points and the lane line information includes: determining a first distance value from the first corner point of the two target corner points to the target lane line and a second distance value from the second corner point to the target lane line based on the position coordinates of the two target corner points and the lane line information; wherein the target lane line is pressed by the obstacle vehicle; and determining the line pressing ratio based on the first distance and the second distance.

[0042] In some embodiments, determining the line pressing ratio based on the first distance value and the second distance value includes: determining the sum of the first distance value and the second distance value; determining the ratio of the first distance value to the sum to obtain a first ratio; or determining the ratio of the second distance value to the sum to obtain a second ratio; determining the first ratio or the second ratio as the line pressing ratio.

[0043] In an exemplary embodiment, Figure 4 The figure shows the calculation method of the line pressing ratio. The sum of the distance a1 from point A to the target lane line and the distance c1 from point C to the target lane line is calculated, that is, a1+c1. The distance c1 from point C to the target lane line is divided by (a1+c1), that is, the line pressing ratio = c1 / (a1+c1). It can also be the line pressing ratio = a1 / (a1+c1).

[0044] Similarly, calculate the sum of the distance b1 from point B to the target lane line and the distance d1 from point D to the target lane line, that is, b1+d1, and divide the distance d1 from point D to the target lane line by (b1+d1), that is, the line pressing ratio = d1 / (b1+d1). It can also be the line pressing ratio = b1 / (b1+d1).

[0045] The specific calculation method of the line pressure ratio can be selected according to needs. For example, for point AC, the line pressure ratio = c1 / (a1+c1), for point BD, the line pressure ratio = d1 / (b1+d1), when the line pressure ratio of multiple consecutive frames of data changes from small to large, it can be judged as a left lane change; when the line pressure ratio of multiple consecutive frames of data changes from large to small, it can be judged as a right lane change.

[0046] 103 . Identify the lane-changing behavior of the obstacle vehicle according to the relative position information corresponding to each frame of collected data.

[0047] In some embodiments, identifying the lane changing behavior of the obstructing vehicle based on the relative position information corresponding to each frame of collected data includes: determining a sequence of continuous target frames based on the relative position information of each frame of collected data, wherein the starting target frame and the ending target frame of the sequence are respectively line-pressing, the number of consecutive target frames that do not press the line between the starting target frame and the ending target frame is not greater than a preset number, and the total number of target frames in the sequence is not less than a preset number of frames; identifying the lane changing behavior of the obstructing vehicle based on the line-pressing ratio corresponding to each target frame data in the sequence.

[0048] The preset number and the preset number of frames are pre-configured as needed or obtained from other devices, and the specific values ​​of the preset number and the preset number of frames are designed as needed or determined based on experience, and are not specifically limited here.

[0049] By setting the number of consecutive target frames without overlapping between the start target frame and the end target frame to be no greater than a preset number, occasional detection loss is excluded.

[0050] For example, assuming the preset number of frames is 20 and the preset number is 5, if the line is pressed for more than 20 consecutive frames, no more than 5 consecutive frames are allowed to be free of line pressure, which is used to exclude occasional detection loss. That is, in the continuous n frames (n>=20), the total number of frames that are pressed is >20, and there are no continuous 5 frames without line pressure.

[0051] In some embodiments, identifying the lane changing behavior of the obstacle vehicle based on the line pressing ratio corresponding to each target frame data in the sequence includes: determining a correlation coefficient based on the acquisition time and the line pressing ratio of each target frame data in the sequence, wherein the correlation coefficient is used to characterize the degree of linear correlation between the acquisition time and the line pressing ratio, and a larger correlation coefficient indicates a higher degree of linear correlation; when the correlation coefficient is greater than a preset coefficient and the change in the line pressing ratio between the starting target frame and the ending target frame is greater than a preset change, identifying the lane changing behavior of the obstacle vehicle based on the acquisition data of the starting target frame and the acquisition data of the ending target frame.

[0052] Among them, the preset coefficient and the preset change amount are pre-configured according to needs or obtained from other devices. The specific values ​​of the preset coefficient and the preset change amount can be designed according to needs or determined based on experience, and there is no limitation here.

[0053] For example, the preset change is 70%. From the beginning of crossing the line to the end of crossing the line, the change in the crossing ratio is >70%, and the correlation coefficient is greater than 0.5. Then, it is further determined whether to change lanes. If these two conditions are not met, it is directly determined that no lane change has occurred, and the lane change behavior identification continues through the newly collected data.

[0054] In an exemplary embodiment, a correlation coefficient is determined based on the acquisition time and the line-pressing ratio of each target frame data in the sequence, including: calculating the covariance of the acquisition time and the line-pressing ratio of each target frame data; calculating the variance of the acquisition time and the variance of the line-pressing ratio of each target frame data; taking the covariance as the numerator, multiplying the variance of the acquisition time and the variance of the line-pressing ratio, and taking the square root as the denominator to obtain the correlation coefficient.

[0055] The formula is: in, represents the acquisition time of the i-th target frame data, Indicates the line pressure ratio of the i-th target frame data, represents the average value at the time of collection, It represents the average value of the pressure line ratio. Represents the correlation coefficient.

[0056] The value range of the correlation coefficient is between 0 and 1. The closer the correlation coefficient is to 1, the closer the relationship is to a linear relationship. In the embodiment of the present disclosure, the correlation coefficient is greater than the preset coefficient, indicating that the correlation coefficient is sufficiently close to 1, that is, the line-pressing ratio shows a closer to linear change pattern with the collection time, which is in line with the change pattern of the line-pressing ratio during the lane change process.

[0057] In some embodiments, identifying the lane changing behavior of the obstacle vehicle based on the collected data of the starting target frame and the collected data of the ending target frame includes: determining the distance change value of the obstacle vehicle in the lane width direction based on the collected data of the starting target frame and the collected data of the ending target frame; and determining that the obstacle vehicle has changed lanes when the distance change value is greater than a preset change value.

[0058] By limiting the distance change value of the obstructing vehicle in the lane width direction, the scene where the obstructing vehicle drives on the lane for a long time is avoided from being identified as a lane change scene, thereby improving the accuracy of lane change recognition.

[0059] The specific value of the preset change value is pre-configured as needed or obtained from other devices, and the specific values ​​of the preset coefficient and the preset change amount can be designed as needed or determined based on experience, and are not limited here. For example, the preset change amount is not less than 1 / 3 of the lane width.

[0060] In an exemplary embodiment, assuming that the lane width is 3 meters, if the distance change of the obstacle vehicle in the lane width direction is greater than 1.2 meters, it is identified as a lane change.

[0061] In some embodiments, determining that the obstructing vehicle has changed lanes includes: if the two corner points on the diagonal line on both sides of the lane line are the left front corner point and the right rear corner point, determining that the obstructing vehicle has changed lanes to the left; if the two corner points on the diagonal line on both sides of the lane line are the right front corner point and the left rear corner point, determining that the obstructing vehicle has changed lanes to the right.

[0062] Combination Figure 4 As shown, by identifying the diagonal corner point pairs as pressure lines, it is possible to distinguish between left and right lane changes, making the identified lane change behavior more specific, laying the foundation for obtaining more specific lane change scenarios. In addition, other methods can also be used to determine the lane change direction, such as using different pressure line ratio calculation methods for left and right lane changes, and distinguishing left and right lane changes by the different change trends of the pressure line ratio, which is not limited here. For another example, determine the interval to which the heading angle of the obstructing vehicle belongs, and determine it as a left lane change when it belongs to the first interval, and determine it as a right lane change when it belongs to the second interval. The specific values ​​of the first interval and the second interval can be predetermined and determined based on empirical values, and the first interval and the second interval do not overlap.

[0063] In an exemplary embodiment, Figure 5 A schematic diagram of an example of an implementation process of lane change recognition is shown, and the implementation process includes: Step 501, obtaining lane line information and timing information of the obstacle vehicle, where the timing information includes the position coordinates and heading angle of the center point; Step 502, obtaining the next frame in the timing information, and determining whether it is the last frame, if yes, ending the process, if no, executing step 503; Step 503, determine whether the distance between the obstacle vehicle and the target vehicle in the extended lane direction is greater than 50 meters, if yes, return to step 502, if no, execute step 504; Step 504, determine whether the speed of the obstacle vehicle in the extended lane direction is less than 2 m / s, if yes, return to step 502, if no, execute step 505; Step 505, calculating the position coordinates of the four corner points of the obstacle vehicle, where the right rear is A, the right front is B, the left front is C, and the left rear is D; Step 506, determine whether the heading angle of the obstacle vehicle is greater than 0, if yes, execute step 507, if no, execute step 508; Step 507, judging the line pressing based on the AC corner points and calculating the line pressing ratio, a line pressing ratio of 0 indicates no line pressing, and a line pressing ratio greater than 0 indicates line pressing, and then proceeding to step 509; Step 508, judging the line pressing based on the BD corner point and calculating the line pressing ratio, a line pressing ratio of 0 indicates no line pressing, and a line pressing ratio greater than 0 indicates line pressing, and then proceeding to step 509; Step 509, adding the line pressing ratio to the line pressing ratio list L1; Step 510, determine whether the number of continuous 0 line pressure ratios in L1 is greater than 5, if yes, clear L1 and go to step 502, if no, go to step 511; Step 511, delete the line pressing ratio with a value of 0 in L1, generate a new list L2, and calculate the absolute value of the difference between the first element and the last element in L2, that is, the line pressing ratio change diff; Step 512, determine whether the line pressing ratio change diff>70%, and the line pressing is continuous for 20 frames, that is, the length of L2>2, if not, go to step 502, if yes, go to step 513; Step 513, calculating the correlation coefficient between the line pressing ratio and time according to L2; Step 514, determine whether the correlation coefficient is greater than 0.5, if not, go to step 502, if yes, go to step 515; Step 515, determine whether the distance change between the first element and the last element of L2 in the direction perpendicular to the lane is greater than 1.2 meters. If not, go to step 502. If yes, go to step 516. Step 516, determine the lane change direction. If the AC corner point is pressed, it is a left lane change. If the BD corner point is pressed, it is a right lane change. If it is a left lane change, execute step 517. If it is a right lane change, execute step 518. Step 517, adding the information of the obstacle vehicle changing lanes to the left to the recognition result, and ending; Step 518, add the information of the obstacle vehicle changing lanes right to the recognition result, and end.

[0064] It should be noted that the execution order of the above steps is not fixed, and the order of some steps can be adjusted as needed without affecting the overall lane change recognition effect.

[0065] The embodiments provided by the present disclosure determine the relative position information of the obstacle vehicle and the lane line in each frame of collected data of the target vehicle based on the obstacle vehicle information and lane line information in each frame of collected data, and then identify the lane changing behavior of the obstacle vehicle based on the relative position information corresponding to each frame of collected data, thereby being able to simply and efficiently identify the lane changing behavior of the obstacle vehicle, thereby improving the efficiency of lane changing behavior identification.

[0066] Furthermore, the lane change behavior recognition method provided by the embodiments of the present disclosure can accurately (with a high accuracy rate) and effectively (with a high recall rate) mine out the left or right lane change scenarios of the vehicle ahead from a large amount of vehicle-side feedback data, which is conducive to the rapid iteration of research and development.

[0067] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, the present disclosure will not repeat them. It can be understood by those skilled in the art that in the above-mentioned method of the specific implementation, the specific execution order of each step should be determined by its function and possible internal logic, and the execution order between the steps is not limited to being implemented according to the step number.

[0068] In addition, the present disclosure also provides a lane change behavior recognition device, an electronic device, and a computer program product, all of which can be used to implement any lane change behavior recognition method provided by the present disclosure. The corresponding technical solutions and descriptions are referred to the corresponding records in the method part and will not be repeated here.

[0069] Figure 6 A block diagram of a lane change behavior recognition device provided in an embodiment of the present disclosure, the lane change behavior recognition device mainly includes: The acquisition module 601 is used to acquire each frame of collected data of the target vehicle, wherein each frame of collected data includes obstacle vehicle information and lane line information; The processing module 602 is used to determine the relative position information between the obstacle vehicle and the lane line corresponding to each frame of collected data according to the obstacle vehicle information and the lane line information of each frame of collected data; wherein the relative position information includes a line pressing mark, the line pressing mark is used to indicate whether the line is pressed or not pressed, and when the line pressing mark is a line pressing, the relative position information also includes a line pressing ratio; The identification module 603 is used to identify the lane changing behavior of the obstacle vehicle according to the relative position information corresponding to each frame of collected data.

[0070] Each module in the lane change behavior recognition device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0071] Figure 7 A block diagram of an electronic device provided in an embodiment of the present disclosure.

[0072] Reference Figure 7 An embodiment of the present disclosure provides an electronic device, which includes: at least one processor 701; at least one memory 702, and one or more I / O interfaces 703, connected between the processor 701 and the memory 702; wherein the memory 702 stores one or more computer programs that can be executed by the at least one processor 701, and the one or more computer programs are executed by the at least one processor 701, so that the at least one processor 701 can execute the above-mentioned lane change behavior recognition method.

[0073] Each module in the above electronic device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0074] The embodiment of the present disclosure also provides a vehicle, which is configured to execute the lane change behavior identification method as described above.

[0075] The embodiment of the present disclosure also provides a computer program product, including a computer program, which implements the above lane change behavior identification method when executed in a processor.

[0076] The computer program may be stored in a readable storage medium of a computer device or in the cloud; the processor of the computer device reads the computer program from the readable storage medium or in the cloud.

[0077] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0078] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable storage medium, which may include a computer storage medium (or a non-transitory medium) and a communication medium (or a transient medium).

[0079] As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable program instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is known to those of ordinary skill in the art, communication media typically contain computer readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0080] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0081] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of the computer-readable program instructions to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute the computer-readable program instructions, thereby implementing various aspects of the present disclosure.

[0082] The computer program product described herein may be implemented in hardware, software, or a combination thereof. In one optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), etc.

[0083] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0084] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0085] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0086] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0087] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A lane change behavior recognition method, characterized in that: include: Obtaining each frame of collected data of the target vehicle, wherein each frame of collected data includes obstacle vehicle information and lane line information; Determine the relative position information between the obstacle vehicle and the lane line corresponding to each frame of collected data according to the obstacle vehicle information and the lane line information of each frame of collected data; wherein the relative position information includes a line pressing mark, the line pressing mark is used to indicate line pressing or not, and when the line pressing mark is line pressing, the relative position information also includes a line pressing ratio; The lane changing behavior of the obstacle vehicle is identified according to the relative position information corresponding to each frame of collected data.

2. The method according to claim 1, characterized in that The determining, based on the obstacle vehicle information and the lane line information of each frame of collected data, the relative position information of the obstacle vehicle and the lane line corresponding to each frame of collected data comprises: Perform the following processing on each frame of collected data: Determine the position coordinates of four corner points of the obstacle vehicle according to the obstacle vehicle information of the collected data; The relative position information between the obstacle vehicle and the lane line is determined according to the position coordinates of the four corner points of the obstacle vehicle and the lane line information.

3. The method according to claim 2, characterized in that The four corner points include a left front corner point, a right front corner point, a left rear corner point and a right rear corner point; the left front corner point and the right rear corner point located on the diagonal line constitute a first group of corner points, and the right front corner point and the left rear corner point located on the diagonal line constitute a second group of corner points; The determining the relative position information between the obstacle vehicle and the lane line according to the position coordinates of the four corner points of the obstacle vehicle and the lane line information includes: According to the position coordinates of the four corner points of the obstacle vehicle and the lane line information, determine whether two corner points in the first group of corner points are located on both sides of the lane line to obtain a first determination result, and determine whether two corner points in the second group of corner points are located on both sides of the lane line to obtain a second determination result; If both the first judgment result and the second judgment result are negative, it is determined that the obstacle vehicle does not cross the lane line, and the non-crossing line is used as the relative position information; If one of the first judgment result and the second judgment result is yes, determine whether the obstacle vehicle is pressing the lane line, determine the pressing ratio based on the position coordinates of the two target corner points and the lane line information, and use the pressing line and the pressing ratio as the relative position information, wherein the target corner points are two corner points among the four corner points that are located on the diagonal line and on both sides of the lane line.

4. The method according to claim 3, characterized in that The determining the lane pressing ratio according to the position coordinates of the two target corner points and the lane line information includes: According to the position coordinates of the two target corner points and the lane line information, determine a first distance value from a first corner point of the two target corner points to a target lane line, and a second distance value from a second corner point to the target lane line; wherein the target lane line is pressed by the obstacle vehicle; A pressing line ratio is determined according to the first distance and the second distance.

5. The method according to claim 4, characterized in that The determining the line pressing ratio according to the first distance value and the second distance value includes: Determine a sum of the first distance value and the second distance value; Determine a ratio of the first distance value to the sum value to obtain a first ratio; or determine a ratio of the second distance value to the sum value to obtain a second ratio; The first ratio or the second ratio is determined as the line pressing ratio.

6. The method according to any one of claims 3 to 5, characterized in that: The identifying the lane-changing behavior of the obstacle vehicle according to the relative position information corresponding to each frame of collected data includes: Determine a sequence of continuous target frames according to the relative position information of each frame of collected data, wherein the starting target frame and the ending target frame of the sequence are respectively pressed lines, the number of continuous target frames that are not pressed lines between the starting target frame and the ending target frame is not greater than a preset number, and the total number of target frames in the sequence is not less than a preset number of frames; The lane changing behavior of the obstacle vehicle is identified based on the line pressing ratio corresponding to each target frame data in the sequence.

7. The method according to claim 6, characterized in that The identifying the lane changing behavior of the obstacle vehicle based on the line pressing ratio corresponding to each target frame data in the sequence includes: Determine a correlation coefficient according to the acquisition time and the line pressing ratio of each target frame data in the sequence, wherein the correlation coefficient is used to characterize the degree of linear correlation between the acquisition time and the line pressing ratio, and a larger correlation coefficient indicates a higher degree of linear correlation; When the correlation coefficient is greater than the preset coefficient and the change in the line pressure ratio between the starting target frame and the ending target frame is greater than the preset change, the lane changing behavior of the obstacle vehicle is identified based on the collected data of the starting target frame and the collected data of the ending target frame.

8. The method according to claim 7, characterized in that The identifying the lane-changing behavior of the obstacle vehicle according to the collected data of the starting target frame and the collected data of the ending target frame includes: Determine the distance change value of the obstacle vehicle in the lane width direction according to the collected data of the starting target frame and the collected data of the ending target frame; When the distance change value is greater than a preset change value, it is determined that the obstacle vehicle changes lanes.

9. The method according to claim 8, characterized in that The determining that the obstacle vehicle changes lanes includes: If the two corner points on the diagonal lines on both sides of the lane line are the left front corner point and the right rear corner point, it is determined that the obstacle vehicle has changed lanes to the left; If the two corner points on the diagonal line on both sides of the lane line are the right front corner point and the left rear corner point, it is determined that the obstacle vehicle changes lanes to the right.

10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores at least one computer program executable by the at least one processor, and the at least one computer program is executed by the at least one processor so that the at least one processor can execute the lane change behavior recognition method according to any one of claims 1 to 9.

11. A vehicle, characterized in that: The vehicle is configured to execute the lane change behavior recognition method according to any one of claims 1-9.

12. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed in a processor, the lane change behavior recognition method according to any one of claims 1 to 9 is implemented.

Images