Vehicle lane change detection method, device, electronic device and storage medium

Abstract

The present application relates to a vehicle lane change detection method, device, electronic device and storage medium, the method comprising: obtaining a video image, obtaining coordinate information of an object to be detected according to the video image; the object to be detected includes a vehicle to be detected and a lane line; calculating the size index of the corresponding vehicle based on the coordinate information of the vehicle in the video image; performing size screening on the vehicle based on the size index of the vehicle to obtain the vehicle to be detected; determining the lane of the vehicle to be detected according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line; and performing lane change detection on the vehicle to be detected according to the lane of the vehicle to be detected. Through the present application, the accuracy of the vehicle lane change detection result is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a vehicle lane change detection method, device, electronic device and storage medium. Background Art

[0002] With the increase of vehicles in cities, traffic is becoming more and more congested. Illegal lane changes occur frequently in real life, which seriously affects traffic order and easily causes traffic accidents. Therefore, the detection of illegal lane changes is an important part of intelligent traffic monitoring, which makes full preparations for the subsequent capture, identification and punishment of illegal vehicles. It is of great significance to study the detection method of illegal lane changes.

[0003] At present, the vehicle lane change penalty technology based on video recognition usually directly tracks the centroid of the detection target or the position relationship between the detection frame and the lane line to determine whether the vehicle appears in multiple lanes within a period of time to identify whether the lane change occurs. However, this lane change judgment method is too simple and can easily lead to lane misjudgment. Summary of the invention

[0004] The embodiments of the present application provide a vehicle lane change detection method, device, electronic device and storage medium to at least solve the problem of low lane judgment accuracy in related technologies.

[0005] In a first aspect, an embodiment of the present application provides a vehicle lane change detection method, comprising:

[0006] Acquire a video image, and acquire coordinate information of an object to be detected according to the video image; the object to be detected includes a vehicle to be detected and a lane line;

[0007] Calculating the size index of the corresponding vehicle based on the coordinate information of the vehicle in the video image;

[0008] A lane change detection is performed on the vehicle to be detected according to the lane in which the vehicle to be detected is located.

[0009] In some embodiments, the vehicle to be detected is screened by the following steps:

[0010] Calculating the size index of the corresponding vehicle based on the coordinate information of the vehicle in the video image;

[0011] The vehicles are screened based on their size indicators to obtain vehicles to be detected.

[0012] In some embodiments, the calculating the size index of the corresponding vehicle based on the coordinate information of the vehicle in the video image includes:

[0013] Based on the coordinate information of the vehicle in the video image, determine the vertex coordinates of the target detection box corresponding to the vehicle;

[0014] Determine the horizontal gradient ratio and / or vertical gradient ratio of the corresponding vehicle according to the vertex coordinates of the target detection frame;

[0015] According to the horizontal gradient ratio and / or the vertical gradient ratio, a size index corresponding to the vehicle is calculated.

[0016] In some embodiments, the body size screening of the vehicle based on the body size index of the vehicle to obtain the vehicle to be detected includes:

[0017] The size index of the vehicle is compared with a preset threshold value. When the size index of the vehicle is less than the preset threshold value, the vehicle is determined as a vehicle to be detected; otherwise,

[0018] The vehicle was screened out.

[0019] In some embodiments, before determining the lane in which the vehicle to be detected is located based on the coordinate information of the vehicle to be detected and the coordinate information of the lane line, the method further includes:

[0020] The integrity information of the vehicle to be detected in the video image is obtained, and the vehicle is screened according to the integrity information of the vehicle to be detected.

[0021] In some embodiments, determining the lane where the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line includes:

[0022] Acquire coordinate information of a first lane line and a second lane line; the first lane line and the second lane line are adjacent;

[0023] Determine the positional relationship between the vehicle to be detected, the first lane line and the second lane line according to the coordinate information of the vehicle to be detected, the coordinate information of the first lane line and the second lane line;

[0024] According to the positional relationship between the vehicle to be detected, the first lane line and the second lane line, it is determined whether the vehicle to be detected is in a lane between the first lane line and the second lane line.

[0025] In some embodiments, determining the positional relationship between the vehicle to be detected, the first lane line, and the second lane line according to the coordinate information of the vehicle to be detected, the coordinate information of the first lane line, and the second lane line includes:

[0026] Determine a first position relationship between a center point of the vehicle to be detected and the first lane line according to the coordinate information of the vehicle to be detected and the coordinate information of the first lane line;

[0027] Determine a second positional relationship between the center point of the vehicle to be detected and the second lane line according to the coordinate information of the vehicle to be detected and the coordinate information of the second lane line;

[0028] The positional relationship among the vehicle to be detected, the first lane line, and the second lane line is determined according to the first positional relationship and the second positional relationship.

[0029] In some embodiments, performing lane change detection on the vehicle to be detected according to the lane in which the vehicle to be detected is located includes:

[0030] Determine whether the vehicle to be detected is in the current detection queue;

[0031] When the vehicle to be detected is not in the current detection queue, the vehicle to be detected is added to the current detection queue, and the lane where the vehicle to be detected is located is determined as the initial lane;

[0032] When the vehicle to be detected is in the current detection queue, it is determined whether the lane in which the vehicle to be detected is located is the same as the initial lane, so as to output lane change detection information according to the determination result.

[0033] In a second aspect, an embodiment of the present application provides a vehicle lane change detection device, comprising:

[0034] A coordinate information acquisition unit, used to acquire a video image, and acquire coordinate information of an object to be detected according to the video image; the object to be detected includes a vehicle to be detected and a lane line;

[0035] A lane determination unit, used to determine the lane in which the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line;

[0036] The lane change detection unit is used to perform lane change detection on the vehicle to be detected according to the lane in which the vehicle to be detected is located.

[0037] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the vehicle lane change detection method as described in the first aspect above is implemented.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle lane change detection method as described in the first aspect above.

[0039] Compared with the related art, the vehicle lane change detection method provided in the embodiment of the present application obtains the coordinate information of the object to be detected according to the video image by acquiring a video image; the object to be detected includes the vehicle to be detected and the lane line; by determining the lane in which the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line, the lane change detection is performed on the vehicle to be detected according to the lane in which the vehicle to be detected is located, thereby realizing the execution of lane change detection on the vehicle to be detected after screening according to the body shape, and improving the accuracy of the detection result.

[0040] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 is a flow chart of a vehicle lane change detection method in one of the embodiments of the present application;

[0043] Figure 2 It is a schematic diagram of a flow chart of calculating the size index of a corresponding vehicle based on the coordinate information of the vehicle in a video image in one embodiment of the present application;

[0044] Figure 3 is a schematic diagram of a process for determining the lane in which the vehicle to be detected is located in one of the embodiments of the present application;

[0045] Figure 4 is a flow chart of a vehicle lane change detection method in another embodiment of the present application;

[0046] Figure 5 is a structural block diagram of a vehicle lane change detection device in one of the embodiments of the present application;

[0047] Figure 6 It is a schematic diagram of the structure of an electronic device in one of the embodiments of the present application.

[0048] Description of the drawings: 21. Coordinate information acquisition unit; 22. Lane determination unit; 23. Lane change detection unit; 30. Bus; 31. Processor; 32. Memory; 33. Communication interface. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0050] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0051] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0052] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0053] Lane change detection can generally be achieved by using ground sensor coils, radars, manual measurement, weighbridges, video detection and other means. Among them, the lane change detection method based on video detection technology uses a camera to shoot real-time traffic conditions, and uses a computer to automatically detect illegal lane changes in the captured video. It can not only save a lot of human resources, but also improve the detection efficiency of abnormal traffic events, and realize completely unsupervised automatic intelligent monitoring. Video detection is easy to install and maintain, which can not only reduce the investment of manpower and material resources, but also has a wide detection coverage, which can greatly improve the accuracy and timeliness of vehicle behavior analysis and effectively prevent accidents.

[0054] The lane change detection method provided in this application can be used in intelligent traffic scenarios such as maps, navigation, vehicle networking, and automatic driving, and can be used to detect the lane change behavior of road vehicles. In fact, any application scenario that requires lane recognition is within the protection scope of the application scenario of the embodiment of this application, and the embodiment of this application does not limit the specific application scenario.

[0055] This embodiment provides a vehicle lane change detection method, which can be executed by an electronic device. Figure 1 is a flow chart of a vehicle lane change detection method according to an embodiment of the present application. Figure 1 As shown, the process includes the following steps:

[0056] Step S10, acquiring a video image, and acquiring coordinate information of the object to be detected according to the video image.

[0057] In this embodiment, the electronic device may be a video acquisition device or other computer device connected to the video acquisition device. During the driving process of the vehicle, the video acquisition device may acquire a video image of the road, and acquire detection information by acquiring the video image through image processing. Specifically, each frame of the video image may be detected by image recognition technology to identify the object to be detected in the video image.

[0058] The detection information is used to indicate the driving status of the vehicle, and may include the coordinate information of the object to be detected, wherein the object to be detected includes the vehicle to be detected and the lane line. Among them, the vehicle to be detected may be of various types, not limited to a specific party. The coordinate information of the vehicle to be detected is the coordinate position of the vehicle to be detected in the image coordinate system, which may be the coordinates of the four vertices of the vehicle detection frame in the video image, or the coordinates of its centroid or the coordinates of the bottom center point. Lane lines are also called driving lines and carriageways, and are set on roads for vehicles to pass. Lane lines may be solid lines or dotted lines, and different lane types such as driving lanes, emergency lanes, and bus-only lanes may be divided by lane lines. The coordinate information of lane lines may include the ID of lane lines, the starting coordinates of lane lines, the end coordinates, and the like.

[0059] In other embodiments, the detection information also includes feature identification information (such as ID, name, category information) and tracking information of the object to be detected, which is not limited in this application. A deep learning method can be used to analyze the acquired object to be detected to obtain corresponding feature identification information or tracking information.

[0060] Step S12, determining the lane in which the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line.

[0061] In some embodiments, the relative position relationship between the vehicle to be detected and the lane line can be calculated based on the coordinate information of the vehicle to be detected and the coordinate information of the lane line to determine the lane in which the vehicle to be detected is located. In other embodiments, the distance between the vehicle to be detected and the lane line can also be calculated based on the coordinate information of the vehicle to be detected and the coordinate information of the lane line to determine the lane in which the vehicle to be detected is located. Of course, the specific implementation process of lane positioning can be implemented using existing technologies, and this application is not limited here.

[0062] Step S14: performing lane change detection on the vehicle to be detected according to the lane in which the vehicle to be detected is located.

[0063] Specifically, in this embodiment, it is determined whether the lane of the vehicle to be detected changes within the detection time range. When the lane of the vehicle to be detected within the detection time range is different from the historical lane, it is determined that the vehicle to be detected has changed lanes, and the corresponding vehicle information to be detected is output.

[0064] In summary, the vehicle lane change detection method provided in the embodiment of the present application obtains the coordinate information of the object to be detected based on the video image by acquiring a video image; the object to be detected includes the vehicle to be detected and the lane line. By determining the lane in which the vehicle to be detected is located based on the coordinate information of the vehicle to be detected and the coordinate information of the lane line, and performing lane change detection on the vehicle to be detected based on the lane in which the vehicle to be detected is located, lane change detection is performed on the vehicle to be detected after being screened according to the body shape, thereby improving the accuracy of the detection result.

[0065] The embodiments of the present application are described and illustrated below through preferred embodiments.

[0066] On the basis of the above embodiments, in some of the embodiments, the vehicle to be detected is screened by the following steps:

[0067] Step S101, calculating the size index of the corresponding vehicle based on the coordinate information of the vehicle in the video image.

[0068] Step S102, screening the vehicles based on their size indicators to obtain vehicles to be detected.

[0069] Among them, the body size index is used to indicate the size of the vehicle in the current frame video image. The body size index can be calculated based on the coordinate information of the vehicle. The calculation and representation method of the body size index can be customized and configured, and this application is not limited here.

[0070] In this embodiment, due to factors such as the timing of the vehicle's appearance, size, and the installation angle of the video acquisition device, the lane in which the vehicle is located may not be accurately obtained when performing lane change detection calculations based on the vehicle's coordinate information in the video image, which can easily lead to misjudgment of lane change detection results and fail to solve the problem of low lane judgment accuracy for large vehicles. For example, when the vehicle in the video image is too large, it may occupy two or more lane areas. Therefore, it is necessary to obtain the body size indicators of the vehicle in the detection scene before performing lane change detection, so as to perform data screening based on the body size indicators.

[0071] In this embodiment, after determining the size index of the vehicle, the size of the vehicle is screened based on the size index of the vehicle, and obtaining the vehicle to be detected includes: comparing the size index of the vehicle with a preset threshold value, when the size index of the vehicle is less than the preset threshold value, it indicates that the size of the vehicle meets the calculation requirements, and the vehicle is determined as the vehicle to be detected, and the lane change detection is performed on the vehicle. On the contrary, when the size index of the vehicle is greater than the preset threshold value, it indicates that the size of the vehicle is too large, and the vehicle is screened out and the lane change detection is not performed on the vehicle.

[0072] Through the above steps, the size index of the corresponding vehicle is calculated based on the coordinate information of the vehicle in the video image; the vehicle is screened based on the size index of the vehicle to obtain the vehicle to be detected. The detection data corresponding to the abnormal vehicle is screened out to avoid inaccurate lane results calculated using the data when the vehicle accounts for too large a proportion in the video image, thereby reducing the probability of misjudgment of vehicle lane change.

[0073] like Figure 2 As shown, based on the above embodiments, in some of the embodiments, the calculation of the size index of the corresponding vehicle based on the coordinate information of the vehicle in the video image includes:

[0074] Step S1011, based on the coordinate information of the vehicle in the video image, determine the vertex coordinates of the target detection box corresponding to the vehicle.

[0075] Generally, the target detection frame can be a rectangular frame covering the entire vehicle body or a rectangular frame covering the vehicle chassis, wheels, etc. It can be adaptively set according to the actual situation. The target detection frame can be obtained by edge recognition of the vehicle contained in the video image and determining the boundary information of the vehicle. After obtaining the detection frame corresponding to the vehicle, the coordinates of the four vertices of the corresponding target detection frame are further obtained.

[0076] Step S1012, determining the horizontal gradient ratio and / or vertical gradient ratio of the corresponding vehicle according to the vertex coordinates of the target detection frame.

[0077] In this embodiment, the horizontal gradient ratio of the vehicle is the ratio of the width of the target detection box where the vehicle is located in the image coordinate system to the width of the image, and the width of the target detection box can be calculated by the horizontal distance between the upper left vertex and the lower right vertex of the target detection box; the vertical gradient ratio of the vehicle is the ratio of the height of the target detection box where the vehicle is located in the image coordinate system to the height of the image, and the height of the target detection box can be calculated by the vertical distance between the upper left vertex and the lower right vertex of the target detection box.

[0078] Step S1013, calculating a size index corresponding to the vehicle according to the horizontal gradient ratio and / or the vertical gradient ratio.

[0079] In this embodiment, the size index of the vehicle is related to the width of the target detection frame corresponding to the vehicle and also to its height. In some embodiments, the size index corresponding to the vehicle can be calculated based on the horizontal gradient ratio of the vehicle; in other embodiments, the size index corresponding to the vehicle can also be calculated based on the vertical gradient ratio of the vehicle, or the size index corresponding to the vehicle can be calculated based on the horizontal gradient ratio and the vertical gradient ratio of the vehicle.

[0080] In a specific implementation, the size index corresponding to the vehicle is obtained by comprehensively calculating the horizontal gradient ratio and the vertical gradient ratio of the vehicle, and the specific calculation formula is as follows:

[0081]

[0082] Among them, R is the body shape index, FH represents the height of the video image, and FW represents the width of the video image; is the vertical distance between the upper left vertex and the lower right vertex of the target detection box, is the horizontal distance between the upper left vertex and the lower right vertex of the target detection box; a and b are coefficient factors.

[0083] Through the above steps, the vehicle size index is calculated, which is convenient for body screening of detected vehicles and filtering out inaccurate vehicle data, thereby avoiding the influence of vehicle size on lane change detection results.

[0084] On the basis of the above embodiments, in some of the embodiments, before determining the lane in which the vehicle to be detected is located based on the coordinate information of the vehicle to be detected and the coordinate information of the lane line, the method also includes: obtaining the integrity information of the vehicle to be detected in the video image, and performing vehicle screening based on the integrity information of the vehicle to be detected.

[0085] In this embodiment, the completeness information is used to indicate the completeness of the vehicle to be detected in the video image. When the vehicle to be detected in the video image is incomplete, the target detection frame corresponding to the vehicle cannot accurately describe the position of the vehicle to be detected and the lane. In order to reduce the probability of misdetection of the target, before performing lane change detection, it is necessary to obtain the completeness information of the vehicle to be detected in the detection scene, so as to screen the vehicle according to the completeness information. In a specific embodiment, the completeness information can be obtained through a model obtained by deep learning training, and the model will output the probability value of the completeness. For the value with high probability, the target is considered to be complete, otherwise the target is incomplete. In another embodiment, the vehicle to be detected can be divided into multiple areas to be identified in advance, and the identification status of each area to be identified is determined according to the image recognition result, so as to obtain the completeness information. Of course, in other embodiments, the calculation method of the completeness information is not limited in this application, as long as the calculated completeness information can indicate the completeness of the vehicle to be detected in the video image.

[0086] In this embodiment, whether the vehicle to be detected is complete is determined based on the integrity information of the vehicle to be detected. When the vehicle to be detected is complete, a lane change detection is performed on the vehicle to be detected; when the vehicle is incomplete, the vehicle to be detected is screened out and no lane change detection is performed on the vehicle to be detected.

[0087] like Figure 3 As shown, based on the above embodiments, in some of the embodiments, determining the lane where the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line includes:

[0088] Step S121, obtaining coordinate information of a first lane line and a second lane line; the first lane line and the second lane line are adjacent.

[0089] In this embodiment, the first lane line and the second lane line may be any two adjacent lane lines in the detection area in the video image; or may be a roadside line and a lane line adjacent to the roadside line.

[0090] Step S122: determining a positional relationship between the vehicle to be detected, the first lane line, and the second lane line according to the coordinate information of the vehicle to be detected, the coordinate information of the first lane line, and the second lane line.

[0091] Step S123, judging whether the vehicle to be detected is in a lane between the first lane line and the second lane line according to the positional relationship between the vehicle to be detected, the first lane line and the second lane line.

[0092] In this embodiment, first, based on the coordinate information of the vehicle to be detected and the coordinate information of the first lane line, the first position relationship between the center point of the vehicle to be detected and the first lane line is determined; based on the coordinate information of the vehicle to be detected and the coordinate information of the second lane line, the second position relationship between the center point of the vehicle to be detected and the second lane line is determined; then, based on the first position relationship and the second position relationship, the position relationship between the vehicle to be detected, the first lane line and the second lane line is determined.

[0093] Specifically, the first positional relationship may be that the center point of the vehicle to be detected is located on the first lane line, above the first lane line, or below the first lane line; the second positional relationship may be that the center point of the vehicle to be detected is located on the second lane line, above the second lane line, or below the second lane line. After determining the first positional relationship and the second positional relationship, since the first lane line and the second lane line are adjacent and arranged in parallel, the positional relationship between the vehicle to be detected, the first lane line, and the second lane line can be determined, that is, whether the vehicle to be detected is located between the first lane line and the second lane line. It should be noted that the coordinates of the center point of the vehicle to be detected include but are not limited to the centroid coordinates of the target detection frame corresponding to the vehicle to be detected, the bottom center point coordinates, etc.

[0094] Exemplarily, the calculation formula of the first position relationship or the second position relationship is as follows:

[0095]

[0096] Among them, M i Represents the position discrimination value calculated based on the center point of the vehicle to be detected and the lane line. represents the starting coordinates of the i-th lane line, represents the coordinates of the end point of the i-th lane line, and (x, y) represents the coordinates of the bottom center point of the target detection box.

[0097] For example: M1 represents the first lane line, M2 represents the second lane line, if M1*M2<0, the vehicle to be detected is in the lane between the first lane line and the second lane line; if M1>0 and M2>0, or M1<0 and M2<0, it means that the vehicle to be detected is on the same side of the first lane line and the second lane line, that is, both are on the upper side or both are on the lower side. At this time, the vehicle to be detected is not in the lane between the first lane line and the second lane line.

[0098] On the basis of the above embodiments, in some of the embodiments, the lane change detection of the vehicle to be detected according to the lane in which the vehicle to be detected is located includes:

[0099] Step S141, determining whether the vehicle to be detected is in the current detection queue.

[0100] Step S142: When the vehicle to be detected is not in the current detection queue, the vehicle to be detected is added to the current detection queue, and the lane where the vehicle to be detected is located is determined as the initial lane.

[0101] Step S143, when the vehicle to be detected is in the current detection queue, it is determined whether the lane in which the vehicle to be detected is located is the same as the initial lane, so as to output lane change detection information according to the determination result.

[0102] In this embodiment, the current detection queue is used to store all vehicles to be detected for lane change detection, including vehicle IDs and corresponding initial lanes.

[0103] After the lane of the vehicle to be detected is determined, by judging whether the vehicle to be detected is in the current detection queue, it can be determined whether the current lane is the initial lane. When the vehicle to be detected is not in the current detection queue, the lane where the vehicle to be detected is detected for the first time, at this time, the lane is determined as the initial lane of the vehicle to be detected, and the vehicle to be detected is video tracked and written into the current detection queue.

[0104] When the vehicle to be detected is in the current detection queue, the vehicle to be detected is detected for the second time. At this time, the initial lane of the vehicle to be detected has been written into the current detection queue. It is necessary to further determine whether the lane of the vehicle to be detected is the same as the initial lane in the current detection queue, so as to output lane change detection information according to the determination result. Specifically, if the lane of the vehicle to be detected is not the same as the initial lane in the current detection queue, the lane change information of the vehicle to be detected is output and it is filtered out from the current detection queue; otherwise, the above steps are repeated to continue to perform lane change detection on the vehicle to be detected.

[0105] like Figure 4 As shown, in some embodiments, the vehicle lane change detection method includes the following steps: first, the coordinate information of the vehicle is obtained according to the video image; the size index of the corresponding vehicle is calculated based on the coordinate information of the vehicle in the video image, and after the size index R of the vehicle is determined, the vehicle is screened based on the size index R of the vehicle. When the size index R of the vehicle is less than the preset threshold value H, the vehicle is determined as a vehicle to be detected, and a lane change detection is performed on the vehicle. Otherwise, the vehicle is screened out and the lane change detection is not performed on the vehicle. Furthermore, the integrity information of the vehicle to be detected in the video image is obtained, and the vehicle is screened according to the integrity information of the vehicle to be detected. When the vehicle to be detected is complete, a lane change detection is performed on the vehicle to be detected; when the vehicle is incomplete, the vehicle to be detected is screened out and the lane change detection is not performed on the vehicle to be detected.

[0106] Next, the lane CR of the vehicle to be detected is determined based on the coordinate information of the vehicle to be detected and the coordinate information of the lane line. After the lane CR of the vehicle to be detected is determined, it is determined whether the vehicle to be detected is in the current detection queue. When the vehicle to be detected is not in the current detection queue, the vehicle to be detected is added to the current detection queue, and the lane of the vehicle to be detected is determined as the initial lane, and the initial lane FR of the vehicle to be detected is updated; when the vehicle to be detected is in the current detection queue, it is determined whether the lane CR of the vehicle to be detected is the same as the initial lane FR. If they are not the same, the lane change information of the vehicle to be detected is output, and it is filtered out from the current detection queue. Otherwise, the above steps are repeated to continue to perform lane change detection on the vehicle to be detected.

[0107] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0108] This embodiment also provides a vehicle lane change detection device, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated here. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0109] Figure 5 is a structural block diagram of a vehicle lane change detection device according to an embodiment of the present application, such as Figure 5 As shown, the device includes: a coordinate information acquisition unit 21, a lane determination unit 22 and a lane change detection unit 23.

[0110] A coordinate information acquisition unit 21 is used to acquire a video image and acquire coordinate information of an object to be detected according to the video image; the object to be detected includes a vehicle to be detected and a lane line;

[0111] A lane determination unit 22, configured to determine the lane in which the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line;

[0112] The lane change detection unit 23 is used to perform lane change detection on the vehicle to be detected according to the lane in which the vehicle to be detected is located.

[0113] In some of the embodiments, the coordinate information acquisition unit 21 includes: a body index calculation module and a to-be-detected vehicle acquisition module.

[0114] A body index calculation module, used to calculate the body index of the corresponding vehicle based on the coordinate information of the vehicle in the video image;

[0115] A vehicle acquisition module to be detected is used to screen the vehicle based on its size index to obtain the vehicle to be detected;

[0116] In some embodiments, the body shape index calculation module includes: a vertex coordinate determination module, a proportion determination module and an index calculation module.

[0117] A vertex coordinate determination module, used to determine the vertex coordinates of the target detection frame corresponding to the vehicle based on the coordinate information of the vehicle in the video image;

[0118] A proportion determination module, used to determine the horizontal gradient proportion and / or vertical gradient proportion of the corresponding vehicle according to the vertex coordinates of the target detection frame;

[0119] The index calculation module is used to calculate the size index corresponding to the vehicle according to the horizontal gradient ratio and / or the vertical gradient ratio.

[0120] In some embodiments, the to-be-detected vehicle acquisition module includes: a first screening module and a second screening module.

[0121] A first screening module, used to compare the size index of the vehicle with a preset threshold, and when the size index of the vehicle is less than the preset threshold, determine the vehicle as a vehicle to be detected;

[0122] The second screening module is used to screen out the vehicle when the size index of the vehicle is greater than or equal to a preset threshold.

[0123] In some of the embodiments, the vehicle lane change detection device further includes: a completeness screening unit.

[0124] The integrity screening unit is used to obtain the integrity information of the vehicle to be detected in the video image, and perform vehicle screening according to the integrity information of the vehicle to be detected.

[0125] In some of the embodiments, the lane determination unit 22 includes: a coordinate information acquisition module, a position relationship acquisition module and a lane judgment module.

[0126] A coordinate information acquisition module, used to acquire coordinate information of a first lane line and a second lane line; the first lane line and the second lane line are adjacent;

[0127] A position relationship acquisition module, used to determine the position relationship between the vehicle to be detected, the first lane line and the second lane line according to the coordinate information of the vehicle to be detected, the coordinate information of the first lane line and the second lane line;

[0128] The lane judgment module is used to judge whether the vehicle to be detected is in a lane between the first lane line and the second lane line according to the position relationship between the vehicle to be detected, the first lane line and the second lane line.

[0129] In some embodiments, the position relationship acquisition module includes: a first position relationship acquisition module, a second position relationship acquisition module and a position relationship determination module.

[0130] A first position relationship acquisition module, used to determine a first position relationship between a center point of the vehicle to be detected and the first lane line according to coordinate information of the vehicle to be detected and coordinate information of the first lane line;

[0131] A second position relationship acquisition module, used to determine a second position relationship between the center point of the vehicle to be detected and the second lane line according to the coordinate information of the vehicle to be detected and the coordinate information of the second lane line;

[0132] A position relationship determination module is used to determine the position relationship between the vehicle to be detected, the first lane line and the second lane line according to the first position relationship and the second position relationship.

[0133] In some of the embodiments, the lane change detection unit 23 includes: a detection queue determination module, a first processing module and a second processing module.

[0134] A detection queue judgment module is used to judge whether the vehicle to be detected is in the current detection queue;

[0135] A first processing module, configured to, when the vehicle to be detected is not in the current detection queue, add the vehicle to be detected to the current detection queue, and determine the lane where the vehicle to be detected is located as the initial lane;

[0136] The second processing module is used to determine whether the lane where the vehicle to be detected is located is the same as the initial lane when the vehicle to be detected is in the current detection queue, so as to output lane change detection information according to the determination result.

[0137] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0138] In addition, combined Figure 1 The vehicle lane change detection method described in the embodiment of the present application can be implemented by an electronic device. Figure 6Schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application.

[0139] The electronic device may include a processor 31 and a memory 32 storing computer program instructions.

[0140] Specifically, the processor 31 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0141] Among them, the memory 32 may include a large capacity memory for data or instructions. For example, but not limitation, the memory 32 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 32 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 32 may be inside or outside the data processing device. In a specific embodiment, the memory 32 is a non-volatile memory. In a specific embodiment, the memory 32 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable ProgrammableRead-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable ProgrammableRead-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0142] The memory 32 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 31 .

[0143] The processor 31 implements any one of the vehicle lane change detection methods in the above embodiments by reading and executing computer program instructions stored in the memory 32 .

[0144] In some embodiments, the electronic device may further include a communication interface 33 and a bus 30. Figure 6 As shown, the processor 31, the memory 32, and the communication interface 33 are connected via a bus 30 and communicate with each other.

[0145] The communication interface 33 is used to realize the communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication interface 33 can also realize data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0146] The bus 30 includes hardware, software or both, and couples the components of the electronic device to each other. The bus 30 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 30 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 30 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0147] The electronic device can execute the vehicle lane change detection method in the embodiment of the present application based on the acquired program instructions, thereby realizing the combination Figure 1 A vehicle lane change detection method is described.

[0148] In addition, in combination with the vehicle lane change detection method in the above embodiment, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the vehicle lane change detection methods in the above embodiment is implemented.

[0149] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A vehicle lane change detection method, characterized in that: include: Acquire a video image, and acquire coordinate information of an object to be detected according to the video image; The objects to be detected include vehicles to be detected and lane lines; The screening method of the vehicle to be detected includes: determining the vertex coordinates of the target detection frame corresponding to the vehicle based on the coordinate information of the vehicle in the video image; determining the horizontal gradient ratio and / or the vertical gradient ratio of the corresponding vehicle according to the vertex coordinates of the target detection frame; calculating the size index of the corresponding vehicle according to the horizontal gradient ratio and / or the vertical gradient ratio; and screening the vehicle based on the size index of the vehicle to obtain the vehicle to be detected; Acquire the integrity information of the vehicle to be detected in the video image, and perform vehicle screening according to the integrity information of the vehicle to be detected; wherein the integrity information is used to indicate the integrity of the vehicle to be detected in the video image. When the vehicle to be detected in the video image is incomplete, the target detection frame corresponding to the vehicle cannot accurately describe the position of the vehicle to be detected and the lane; Determine the lane where the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line; wherein the lane where the vehicle to be detected is located is determined according to the positional relationship between the center point of the vehicle to be detected and the lane line according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line, and is determined according to the positional relationship; the lane line includes a first lane line and a second lane line; the coordinates of the center point of the vehicle to be detected include the coordinates of the center of mass or the coordinates of the bottom center point of the target detection frame corresponding to the vehicle to be detected; A lane change detection is performed on the vehicle to be detected according to the lane in which the vehicle to be detected is located.

2. The vehicle lane change detection method according to claim 1, characterized in that: The body size screening of the vehicle based on the body size index of the vehicle to obtain the vehicle to be detected includes: The size index of the vehicle is compared with a preset threshold value. When the size index of the vehicle is less than the preset threshold value, the vehicle is determined as a vehicle to be detected; otherwise, The vehicle was screened out.

3. The vehicle lane change detection method according to claim 1, characterized in that: The determining, based on the coordinate information of the vehicle to be detected and the coordinate information of the lane line, the lane in which the vehicle to be detected is located comprises: Acquire coordinate information of a first lane line and a second lane line; the first lane line and the second lane line are adjacent; Determine the positional relationship between the vehicle to be detected, the first lane line and the second lane line according to the coordinate information of the vehicle to be detected, the coordinate information of the first lane line and the second lane line; According to the positional relationship between the vehicle to be detected, the first lane line and the second lane line, it is determined whether the vehicle to be detected is in a lane between the first lane line and the second lane line.

4. The vehicle lane change detection method according to claim 3, characterized in that: The determining the positional relationship between the vehicle to be detected, the first lane line, and the second lane line according to the coordinate information of the vehicle to be detected, the coordinate information of the first lane line, and the second lane line comprises: Determine a first position relationship between a center point of the vehicle to be detected and the first lane line according to the coordinate information of the vehicle to be detected and the coordinate information of the first lane line; Determine a second positional relationship between the center point of the vehicle to be detected and the second lane line according to the coordinate information of the vehicle to be detected and the coordinate information of the second lane line; The positional relationship among the vehicle to be detected, the first lane line, and the second lane line is determined according to the first positional relationship and the second positional relationship.

5. The vehicle lane change detection method according to claim 1, characterized in that: The performing lane change detection on the vehicle to be detected according to the lane in which the vehicle to be detected is located comprises: Determine whether the vehicle to be detected is in the current detection queue; When the vehicle to be detected is not in the current detection queue, the vehicle to be detected is added to the current detection queue, and the lane where the vehicle to be detected is located is determined as the initial lane; When the vehicle to be detected is in the current detection queue, it is determined whether the lane in which the vehicle to be detected is located is the same as the initial lane, so as to output lane change detection information according to the determination result.

6. The method according to claim 1, characterized in that The performing lane change detection on the vehicle to be detected according to the lane in which the vehicle to be detected is located includes: Determine whether the lane of the vehicle to be detected has changed within the detection time range. When the lane of the vehicle to be detected within the detection time range is different from the historical lane, determine that the vehicle to be detected has changed lanes and output the corresponding vehicle information to be detected.

7. The method according to claim 1, characterized in that The completeness information is obtained through a model trained by deep learning, or by pre-dividing the vehicle to be detected into multiple areas to be identified, and determining the identification status of each area to be identified based on the image recognition result, so as to obtain the completeness information.

8. A vehicle lane change detection device, characterized in that: include: A coordinate information acquisition unit, used to acquire a video image, and acquire coordinate information of an object to be detected according to the video image; the object to be detected includes a vehicle to be detected and a lane line; A body shape index calculation module, the body shape index calculation module comprising a vertex coordinate determination module, a proportion determination module and an index calculation module; The vertex coordinate determination module is used to determine the vertex coordinates of the target detection frame corresponding to the vehicle based on the coordinate information of the vehicle in the video image; The proportion determination module is used to determine the horizontal gradient proportion and / or vertical gradient proportion of the corresponding vehicle according to the vertex coordinates of the target detection frame; The index calculation module is used to calculate the size index corresponding to the vehicle according to the horizontal gradient ratio and / or the vertical gradient ratio; A vehicle acquisition module to be detected is used to screen the vehicle based on its size index to obtain the vehicle to be detected; A lane determination unit, configured to determine the lane in which the vehicle to be detected is located according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line; wherein the lane in which the vehicle to be detected is located is determined according to the positional relationship between the center point of the vehicle to be detected and the lane line according to the coordinate information of the vehicle to be detected and the coordinate information of the lane line, and is determined according to the positional relationship; the lane line includes a first lane line and a second lane line; the coordinates of the center point of the vehicle to be detected include the coordinates of the centroid or the bottom center point of the target detection frame corresponding to the vehicle to be detected; A completeness screening unit, used to obtain the completeness information of the vehicle to be detected in the video image, and screen the vehicle according to the completeness information of the vehicle to be detected; wherein the completeness information is used to indicate the completeness of the vehicle to be detected in the video image, and when the vehicle to be detected in the video image is incomplete, the target detection frame corresponding to the vehicle cannot accurately describe the position of the vehicle to be detected and the lane; The lane change detection unit is used to perform lane change detection on the vehicle to be detected according to the lane in which the vehicle to be detected is located.

9. An electronic device, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the vehicle lane change detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle lane change detection method according to any one of claims 1 to 7 is implemented.

Images