A method, apparatus, equipment, vehicle, and medium for detecting U-turns on solid lines.

Abstract

This invention provides a method, apparatus, device, vehicle, and medium for detecting solid line U-turns, comprising: acquiring multiple frames of road surface images during vehicle travel; and determining whether the vehicle has performed a solid line U-turn based on lane line information in the multiple frames of road surface images and preset lane line features in the U-turn behavior. This invention does not require map information, steering wheel information, or CAN bus access; it can complete solid line U-turn detection solely based on lane line information, thus saving detection costs. Furthermore, determining whether a vehicle has performed a U-turn based on preset lane line features in the U-turn behavior is applicable to multiple U-turns and detour U-turns, exhibiting high detection accuracy.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method, apparatus, equipment, vehicle, and medium for detecting solid line U-turns. Background Technology

[0002] In Level 0 ADAS (Advanced Driving Assistant Systems), existing forward-looking tasks include FCW (Forward Collision Warning), LDW (Lane Departure Warning), PCW (Pedestrian Collision Warning), and TSR (Traffic Sign Recognition). However, in actual use, due to the need for stronger control over driver behavior, new requirements have emerged, such as driving against traffic, changing lanes over solid lines, and making U-turns over solid lines, in order to regulate driver behavior and prevent illegal and irregular behaviors.

[0003] Regarding the new requirement of making a U-turn over a solid line, there are currently two main solutions: 1) Determine whether a U-turn is permitted on the current road segment based on map information. If two consecutive periods of travel occur in a segment where U-turns are not permitted, it is considered a U-turn over a solid line. 2) After determining that a U-turn is not permitted on the current road segment based on map information, determine whether a U-turn is possible based on steering wheel information. Solution 1 is heavily reliant on map information and cannot detect solid line U-turns when positioning is inaccurate (e.g., under elevated roads, inside tunnels). Solution 2 requires the device to be connected to a CAN bus and has poor detection performance for multiple U-turns and U-turns made by borrowing space. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, vehicle, and medium for detecting solid line U-turns, in order to solve the problems of high detection cost and poor detection effect in the existing solid line U-turn detection methods.

[0005] This invention provides a method for detecting solid line U-turns, comprising:

[0006] Acquire multiple frames of road surface images during vehicle movement;

[0007] The determination of whether a vehicle has performed a solid line U-turn is based on the lane line information in the multi-frame road surface images and the preset lane line features in the U-turn behavior.

[0008] According to the present invention, a solid line U-turn detection method is provided, wherein determining whether a vehicle has performed a solid line U-turn based on lane line information in the multi-frame road surface images and preset lane line features in the U-turn behavior includes:

[0009] Lane line detection is performed on the multi-frame road surface images to obtain lane line information corresponding to multiple lane lines. The lane line information includes lane line type and lane line coordinates. The lane line type includes at least solid line type.

[0010] The fitting lines of the multiple lane lines are obtained based on the lane line coordinates, and the lane line vanishing points are determined based on the fitting lines.

[0011] Based on the comparison between the position change of the lane vanishing point in the multi-frame road surface image and the preset lane line features, and the lane line type, it is determined whether the vehicle has performed a solid line U-turn.

[0012] According to a solid line U-turn detection method provided by the present invention, the step of determining whether a vehicle has committed a solid line U-turn based on the comparison result between the position change of the lane line vanishing point in the multi-frame road surface images and the preset lane line features, and the lane line type, includes:

[0013] To determine whether the vehicle has made a U-turn, the vanishing point of the lane line has moved from the target area along the first direction until it disappears from the road surface image in the continuous multi-frame road surface images, and after a preset interval time, it moves along the first direction to the target area.

[0014] In the step of determining whether a vehicle is in a section of road where U-turns are not permitted, it is determined whether the lane line type corresponding to the lane line in the second direction of the vehicle is a solid line; wherein, the first direction and the second direction are opposite directions;

[0015] If the vehicle is determined to have made a U-turn through the step of determining whether the vehicle has made a U-turn, and is determined to be in a section of road where U-turns are not allowed through the step of determining whether the vehicle is in a section of road where U-turns are not allowed, then the vehicle is determined to have made a U-turn across a solid line.

[0016] According to the solid line U-turn detection method provided by the present invention, the step of determining whether a vehicle has made a U-turn further includes:

[0017] Determine whether a vehicle is a left-hand drive or right-hand drive vehicle;

[0018] Accordingly, determining whether the lane line vanishing point moves from the target area along the first direction until it disappears from the road surface image in the consecutive multi-frame road surface images, and moves back to the target area along the first direction after a preset interval, includes:

[0019] When the vehicle is a left-hand drive vehicle, it is determined whether the lane line vanishing point moves to the right from the target area until it disappears from the road surface image in the continuous multi-frame road surface image, and moves to the target area to the right after a preset interval time.

[0020] When the vehicle is a right-hand drive vehicle, it is determined whether the lane line vanishing point moves to the left from the target area until it disappears from the road surface image in the continuous multi-frame road surface image, and moves to the target area to the left after a preset interval time.

[0021] According to a solid line U-turn detection method provided by the present invention, the step of determining whether a vehicle is in a section of road where U-turns are not permitted includes:

[0022] The two main lane lines on both sides of the vehicle are determined based on the lane line coordinates.

[0023] Determine whether the lane line type corresponding to the main lane line in the second direction in the consecutive multi-frame road surface images is solid line.

[0024] According to the present invention, a solid line U-turn detection method further includes, after determining whether a vehicle has performed a solid line U-turn based on lane line information in the multi-frame road surface images and preset lane line features in the U-turn behavior:

[0025] If a vehicle is found to be making a U-turn over a solid line, the corresponding road image will be stored and a driving safety warning will be issued to the driver.

[0026] According to the present invention, a solid line U-turn detection method is provided, wherein acquiring multiple frames of road surface images during vehicle travel includes:

[0027] The image acquisition module located in front of the vehicle acquires multiple frames of road surface images in front of the vehicle during its driving process.

[0028] The present invention also provides a solid line U-turn detection device, comprising:

[0029] The image acquisition module is used to acquire multiple frames of road surface images during vehicle movement;

[0030] The solid line U-turn behavior determination module is used to determine whether a vehicle has engaged in a solid line U-turn behavior based on the lane line information in the multi-frame road surface images and the preset lane line features in the U-turn behavior.

[0031] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the solid line turning detection method as described above.

[0032] The present invention also provides a vehicle including the above-described electronic equipment.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the solid line turning detection method as described above.

[0034] The present invention provides a solid line U-turn detection method, apparatus, device, vehicle, and medium. The solid line U-turn detection method analyzes lane line information in multiple frames of road surface images to determine whether the changing characteristics of the lane line information satisfy the characteristics of a vehicle making a solid line U-turn, thereby obtaining the detection result of whether a vehicle has made a solid line U-turn. The entire process uses only lane line information from the road surface images, without needing to incorporate map information, steering wheel information, or connect the device to a CAN bus, thus saving detection costs. Furthermore, it can determine whether a vehicle has made a U-turn based on preset lane line characteristics in the U-turn behavior, and is applicable to multiple U-turns and detour U-turns, exhibiting high detection accuracy. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating the solid line turning detection method provided in an embodiment of the present invention;

[0037] Figure 2 This is a schematic diagram illustrating the positional change of the lane line vanishing point provided in an embodiment of the present invention;

[0038] Figure 3 This is a schematic diagram of the solid line turning detection device provided in an embodiment of the present invention;

[0039] Figure 4 A schematic diagram of the physical structure of an electronic device is provided. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0041] Figure 1 This is a flowchart illustrating the solid line turning detection method provided in an embodiment of the present invention; as shown below. Figure 1 As shown, the solid line U-turn detection method includes the following steps:

[0042] S101, acquire multiple frames of road surface images during vehicle movement.

[0043] Specifically, multiple frames of road surface images in front of the vehicle are acquired by an image acquisition module (i.e., a vehicle-mounted forward-view camera) located at the front of the vehicle during the vehicle's operation.

[0044] S102, determine whether the vehicle has performed a solid line U-turn based on the lane line information in the multi-frame road surface images and the preset lane line features in the U-turn behavior.

[0045] In this step, lane line information in multiple consecutive frames of road surface images is analyzed to determine whether the lane line information in these frames meets preset lane line features, thereby determining whether the vehicle has performed a solid line U-turn. The lane line features here are set based on the changes in lane lines during the U-turn. Specifically, as the vehicle travels normally along the lane lines, the lane lines on both sides of the vehicle form lane vanishing points in the field of vision ahead. When the vehicle makes a U-turn, due to the change in field of vision, these lane vanishing points disappear from the image and then reappear. The lane line features during the U-turn are determined through this process of lane line change; that is, the lane vanishing points move from the image along a certain direction until they disappear, and then return to the image along the previous direction after a certain time interval.

[0046] Based on the lane line features mentioned above, we further use whether the lane line is a solid line and the vanishing point of the lane line in the current road image to determine whether the vehicle has made a U-turn over a solid line.

[0047] Specifically, lane line detection is first performed on the multi-frame road surface images to obtain lane line information corresponding to multiple lane lines.

[0048] The lane line information includes lane line type and lane line coordinates, and the lane line type includes at least solid line type.

[0049] In this embodiment, lane line detection can be performed using traditional algorithms or by utilizing a deep learning-based network model.

[0050] Traditional lane detection algorithms primarily rely on edge features or image segmentation, combining image preprocessing, feature extraction, and algorithms like the Kalman filter to form the final lane shape after identifying lane lines. Deep learning-based network models, on the other hand, are trained and updated using lane line training images and corresponding label information. Both traditional lane detection algorithms and deep learning-based network model detection methods are conventional techniques, and will not be elaborated upon in this invention.

[0051] After detecting lane lines in a road image using existing lane line detection algorithms, lane line information such as position (including lane line coordinates) and type is obtained. Specifically, lane line types can be categorized as yellow lane lines, white lane lines, solid lines, dashed lines, etc. Further subdivisions include single white solid lines, single white dashed lines, single yellow solid lines, single yellow dashed lines, double white solid lines, double yellow solid lines, double yellow dashed lines, double white solid-dashed lines, double white dashed-solid lines, double white yellow solid lines, etc., but this invention does not limit these categories.

[0052] Then, fitted lines for the multiple lane lines are obtained based on the lane line coordinates, and the lane line vanishing points are determined based on the fitted lines. That is, curve fitting is performed on the lane lines based on the detected lane line positions to obtain the fitted line corresponding to each lane line, and the intersection of multiple fitted lines is taken as the lane line vanishing point.

[0053] Finally, based on the comparison between the positional change of the lane vanishing point in the multi-frame road surface images and the preset lane line features, as well as the lane line type, it is determined whether the vehicle has performed a solid line U-turn.

[0054] Specifically, when a vehicle is traveling normally along the lane lines, the vanishing point of the lane lines is generally located in the central area of ​​the road image. When the vehicle turns left or right, the position of the vanishing point of the lane lines will change in the road image as the vehicle's field of vision changes, that is, it will deviate from the central area. Based on the continuous positional changes of the vanishing point of the lane lines in the road image, it is determined whether the vehicle has made a U-turn. Then, the information of the lane line type is used to determine whether the vehicle has made a solid line U-turn.

[0055] It should be noted that the lane line information and lane line vanishing points in this invention can be directly obtained through the LDW (Lane Departure Warning) function in existing ADAS systems. In other words, the solid line U-turn detection method provided by this invention only needs to rely on the existing LDW function to obtain information such as lane line type and lane line vanishing point. Based on this information, the change process of the lane line vanishing point is analyzed. If the change process satisfies the lane line vanishing point location characteristics of a vehicle U-turn, it is determined that the vehicle has performed a U-turn. Further, by combining the auxiliary information of whether the lane currently occupied by the vehicle is a solid line, it is finally determined whether the vehicle has performed a solid line U-turn. The above solid line U-turn determination process does not require access to map information, nor does it require adding new interfaces to the existing LDW function to obtain new information. The solid line U-turn detection method of this invention can be seamlessly integrated into the existing LDW function.

[0056] The solid line U-turn detection method provided by this invention analyzes lane line information in multiple frames of road surface images to determine whether the changing characteristics of the lane line information satisfy the characteristics of a vehicle making a solid line U-turn, thereby obtaining the detection result of whether the vehicle has made a solid line U-turn. The entire process uses only lane line information from the road surface images, without needing to incorporate map information, steering wheel information, or connect the device to the CAN bus, thus saving detection costs. Furthermore, it can determine whether a vehicle has made a U-turn based on preset lane line characteristics in the U-turn behavior, and is applicable to multiple U-turns and detour U-turns, exhibiting high detection accuracy.

[0057] Furthermore, based on the above embodiments, the step of determining whether a vehicle has performed a solid line U-turn based on the comparison result between the positional change of the lane line vanishing point in the multi-frame road surface images and the preset lane line features, and the lane line type, includes:

[0058] The process involves determining whether a vehicle has made a U-turn, judging whether the lane line vanishing point has moved from the target area along a first direction until it disappears from the road surface image in the continuous multi-frame road surface images, and then moving back to the target area along the first direction after a preset interval.

[0059] In this step, the determination of whether a vehicle has made a U-turn is made by analyzing the lane line information corresponding to multiple consecutive frames of road surface images.

[0060] To determine whether a vehicle is in a section of road where U-turns are not permitted, it is necessary to determine whether the lane line type corresponding to the lane line in the second direction of the vehicle is a solid line.

[0061] Wherein, the first direction and the second direction are opposite directions.

[0062] If the vehicle is determined to have made a U-turn through the step of determining whether the vehicle has made a U-turn, and is determined to be in a section of road where U-turns are not allowed through the step of determining whether the vehicle is in a section of road where U-turns are not allowed, then the vehicle is determined to have made a U-turn across a solid line.

[0063] Furthermore, the step of determining whether the vehicle has made a U-turn also includes:

[0064] Determine whether a vehicle is a left-hand drive or right-hand drive vehicle.

[0065] Accordingly, determining whether the lane line vanishing point moves from the target area along the first direction until it disappears from the road surface image in the consecutive multi-frame road surface images, and moves back to the target area along the first direction after a preset interval, includes:

[0066] When the vehicle is a left-hand drive vehicle, it is determined whether the lane vanishing point moves to the right from the target area until it disappears from the road surface image in the consecutive multi-frame road surface images, and then moves to the target area to the right after a preset interval. If the lane vanishing point meets the above motion characteristics, it is determined that the vehicle has made a U-turn. At this time, in the step of determining whether the vehicle is in a road section where U-turns are not allowed, it is determined whether the lane line type corresponding to the lane line on the left side of the vehicle is a solid line. If the lane line type corresponding to the lane line on the left side of the vehicle is a solid line, it is determined that the vehicle is in a road section where U-turns are not allowed.

[0067] When the vehicle is a right-hand drive vehicle, it is determined whether the lane vanishing point moves to the left from the target area until it disappears from the road surface image in consecutive multi-frame road surface images, and then moves to the target area to the left after a preset interval. If the lane vanishing point meets the above motion characteristics, it is determined that the vehicle has made a U-turn. At this time, in the step of determining whether the vehicle is in a road section where U-turns are not allowed, it is determined whether the lane line type corresponding to the lane line on the right side of the vehicle is a solid line. If the lane line type corresponding to the lane line on the right side of the vehicle is a solid line, it is determined that the vehicle is in a road section where U-turns are not allowed.

[0068] The following is based on Figure 2 Taking the example of solid and dashed lines on the left and right sides of the main lanes for vehicles, the steps for determining whether a vehicle is in a section where U-turns are not allowed and whether a U-turn has occurred will be explained in detail.

[0069] In the step of determining whether a vehicle has made a U-turn, it is determined whether the lane line information in the multi-frame road surface images meets the preset lane line features in the U-turn behavior. That is, whether the position change of the lane line vanishing point in the continuous multi-frame road surface images first moves from the target area to outside the road surface image along the first direction, and then returns to the target area along the first direction after a period of time.

[0070] The target area refers to the central region of the road surface image. More specifically, the left boundary of the target area is spaced at a predetermined distance from the left boundary of the road surface image, and the right boundary of the target area is spaced at a predetermined distance from the right boundary of the road surface image. These predetermined distances can be set according to actual conditions, such as 1 / 8, 1 / 10, 1 / 6, etc., of the distance between the left and right boundaries of the road surface image. Furthermore, the predetermined distances on the left and right sides can also be set to different values. In this embodiment, the target area is set to the region between the left and right quarters of the road surface image (i.e., the predetermined distance is set to 1 / 8).

[0071] In addition, Figure 2 In the image, the lane vanishing point moves from the target area along the right side (i.e., the vehicle deviates towards the solid left line) and gradually moves outside the road surface image. After a preset interval, the lane vanishing point reappears from the left side of the target area and returns to the target area.

[0072] The preset interval time here can be set directly according to the actual situation, or it can be determined according to the time difference corresponding to a predetermined number of road surface images. For example, in the real-time solid line U-turn detection process, the interval is set to 10-80 frames of road surface images. That is, when the video processing frame rate is 10 frames per second, the preset interval time is 1-4 seconds.

[0073] In determining whether a vehicle is in a section of road where U-turns are not permitted, it is determined whether the lane line on the left side of the vehicle is a solid line.

[0074] If it is determined that the vehicle made a U-turn and the lane line to the left of the vehicle is a solid line, then it is determined that the vehicle made a U-turn over a solid line.

[0075] It should be noted that, in Figure 2 A solid line U-turn refers to a U-turn made under a solid line for left-hand drive vehicles. To confirm a U-turn, the following conditions must be met: the vehicle is turning left, the vanishing point of the lane line moves from the target area to the right off the road surface image, and then moves back to the target area after a short time. If the vehicle is in a section where U-turns are not permitted, the main lane line to the left of the vehicle must be a solid line.

[0076] For right-hand drive vehicles, the specific determination of a solid line U-turn is as follows: The vehicle must turn to the right, and the vanishing point of the lane line must move from the target area to the left out of the road image, and then move back to the target area after a period of time. If the vehicle is in a non-U-turn zone, the main lane line on the right side of the vehicle must be a solid line. That is, the first direction of movement of the lane line vanishing point in determining whether the vehicle is making a U-turn is opposite to the second direction of "lane line in the second direction of the vehicle" in determining whether the vehicle is in a non-U-turn zone, and the second direction is consistent with the vehicle's turning direction. The solid line U-turn detection method provided by this invention is applicable to both left-hand drive and right-hand drive vehicles.

[0077] The solid line U-turn detection method provided by the present invention determines whether a vehicle is making a U-turn by analyzing the position of the lane line vanishing point and which direction the vehicle is making the U-turn. It also determines whether the vehicle has performed a solid line U-turn by combining the lane line types on both sides of the vehicle during the U-turn process. Therefore, it does not require steering wheel information to determine the U-turn direction of the vehicle, and it still has high detection accuracy for solid line U-turns in cases of multiple turns or U-turns with borrowed space.

[0078] Furthermore, based on the above embodiments, the lane line information also includes lane line coordinates.

[0079] Accordingly, the step of determining whether a vehicle is in a section of road where U-turns are not permitted includes:

[0080] The two main lane lines on both sides of the vehicle are determined based on the lane line coordinates.

[0081] Determine whether the lane line type corresponding to the main lane line in the second direction in the consecutive multi-frame road surface images is solid line.

[0082] In this embodiment, all lane lines in the road image are detected using a conventional lane detection algorithm, and the two lane lines closest to the vehicle are determined as the main lane lines based on the coordinate information of each lane line. Figure 2 In the scenario of a U-turn across a solid line, the left lane line of the vehicle is a solid line. To improve the accuracy of solid line U-turn detection, the left lane line needs to be a solid line in multiple consecutive frames of road surface images. This allows for the determination of whether a vehicle is making a U-turn in conjunction with the steps to determine if a U-turn has occurred.

[0083] More specifically, during the real-time solid line U-turn detection process, the lane line type information of each frame of road surface image is stored in a queue of preset length, corresponding to the road surface image. If all lane line types in this queue are solid lines, it is determined that the vehicle is in a section of road where U-turns are not allowed. It should be noted that the preset length queue here maps to a number of consecutive frames of road surface images. Taking a processing frame rate of 10fps as an example, the queue length is generally no less than 20 and no more than 100, that is, 20-100 frames of road surface images.

[0084] Furthermore, based on the above embodiments, after determining whether a vehicle has performed a solid line U-turn based on the lane line information in the multi-frame road surface images and the preset lane line features in the U-turn behavior, the method further includes:

[0085] If a vehicle is found to be making a U-turn over a solid line, the corresponding road image will be stored and a driving safety warning will be issued to the driver.

[0086] In this embodiment, if it is determined that a vehicle is making a U-turn over a solid line, the driver will be warned of a solid line U-turn using the existing warning model in the ADAS system to regulate driver behavior. Additionally, road surface images during the solid line U-turn process are stored for subsequent analysis.

[0087] The solid line U-turn detection device provided by the present invention is described below. The solid line U-turn detection device described below can be referred to in correspondence with the solid line U-turn detection method described above.

[0088] Figure 3 This is a schematic diagram of the solid line turning detection device provided in an embodiment of the present invention; as shown below. Figure 3 As shown, the solid line U-turn detection device includes an image acquisition module 301 and a solid line U-turn behavior determination module 302.

[0089] The image acquisition module 301 is used to acquire multiple frames of road surface images during vehicle travel.

[0090] Specifically, multiple frames of road surface images in front of the vehicle are acquired by an image acquisition module (i.e., a vehicle-mounted forward-view camera) located at the front of the vehicle during the vehicle's operation.

[0091] The solid line U-turn behavior determination module 302 is used to determine whether a vehicle has engaged in a solid line U-turn behavior based on the lane line information in the multi-frame road surface images and the preset lane line features in the U-turn behavior.

[0092] In this module, lane line information in multiple consecutive frames of road surface images is analyzed to determine whether the lane line information in these frames meets preset lane line features, thereby determining whether a vehicle has performed a solid line U-turn. The lane line features here are set based on the changes in lane lines during the U-turn. Specifically, as the vehicle travels normally along the lane lines, the lane lines on both sides of the vehicle form lane vanishing points in the field of view ahead. When the vehicle makes a U-turn, due to the change in field of view, these lane vanishing points disappear from the image and then reappear. The lane line features during the U-turn are determined through this process of lane line change; that is, the lane vanishing points move from the image along a certain direction until they disappear, and then return to the image along the same direction after a certain time interval.

[0093] Based on the lane line features mentioned above, we further use whether the lane line is a solid line and the vanishing point of the lane line in the current road image to determine whether the vehicle has made a U-turn over a solid line.

[0094] Specifically, the solid line U-turn behavior determination module 302 first performs lane line detection on the multi-frame road surface images to obtain lane line information corresponding to multiple lane lines.

[0095] The lane line information includes lane line type and lane line coordinates, and the lane line type includes at least solid line type.

[0096] In this embodiment, lane line detection can be performed using traditional algorithms or by utilizing a deep learning-based network model.

[0097] Traditional lane detection algorithms primarily rely on edge features or image segmentation, combining image preprocessing, feature extraction, and algorithms like the Kalman filter to form the final lane shape after identifying lane lines. Deep learning-based network models, on the other hand, are trained and updated using lane line training images and corresponding label information. Both traditional lane detection algorithms and deep learning-based network model detection methods are conventional techniques, and will not be elaborated upon in this invention.

[0098] After detecting lane lines in a road image using existing lane line detection algorithms, lane line information such as their location (including lane line coordinates) and type is obtained. Lane line types can be specifically categorized as yellow lane lines, white lane lines, solid lines, dashed lines, etc. Further subdivisions include single white solid lines, single white dashed lines, single yellow solid lines, single yellow dashed lines, double white solid lines, double yellow solid lines, double yellow dashed lines, double white solid-dashed lines, double white dashed-solid lines, double white yellow solid lines, etc.

[0099] Then, fitted lines for the multiple lane lines are obtained based on the lane line coordinates, and the lane line vanishing points are determined based on the fitted lines. That is, curve fitting is performed on the lane lines based on the detected lane line positions to obtain the fitted line corresponding to each lane line, and the intersection of multiple fitted lines is taken as the lane line vanishing point.

[0100] Finally, based on the comparison between the positional change of the lane vanishing point in the multi-frame road surface images and the preset lane line features, as well as the lane line type, it is determined whether the vehicle has performed a solid line U-turn.

[0101] Specifically, when a vehicle is traveling normally along the lane lines, the vanishing point of the lane lines is generally located in the central area of ​​the road image. When the vehicle turns left or right, the position of the vanishing point of the lane lines will change in the road image as the vehicle's field of vision changes, that is, it will deviate from the central area. Based on the continuous positional changes of the vanishing point of the lane lines in the road image, it is determined whether the vehicle has made a U-turn. Then, the information of the lane line type is used to determine whether the vehicle has made a solid line U-turn.

[0102] It should be noted that the lane line information and lane line vanishing points in this invention can be directly obtained through the LDW (Lane Departure Warning) function in existing ADAS systems. In other words, the solid line U-turn detection method provided by this invention only needs to rely on the existing LDW function to obtain information such as lane line type and lane line vanishing point. Based on this information, the change process of the lane line vanishing point is analyzed. If the change process satisfies the lane line vanishing point location characteristics of a vehicle U-turn, it is determined that the vehicle has performed a U-turn. Further, by combining the auxiliary information of whether the lane currently occupied by the vehicle is a solid line, it is finally determined whether the vehicle has performed a solid line U-turn. The above solid line U-turn determination process does not require access to map information, nor does it require adding new interfaces to the existing LDW function to obtain new information. The solid line U-turn detection method of this invention can be seamlessly integrated into the existing LDW function.

[0103] The solid line U-turn detection device provided in this embodiment of the invention analyzes lane line information in multiple frames of road surface images to determine whether the changing characteristics of the lane line information satisfy the characteristics of a vehicle making a solid line U-turn, thereby obtaining the detection result of whether the vehicle has made a solid line U-turn. The entire process uses only lane line information from the road surface images, without needing to incorporate map information, steering wheel information, or connect the device to the CAN bus, thus saving detection costs. Furthermore, it can determine whether a vehicle has made a U-turn based on preset lane line characteristics in the U-turn behavior, and is applicable to multiple U-turns and detour U-turns, exhibiting high detection accuracy.

[0104] Figure 4An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440. The processor 410, communication interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute the solid line U-turn detection method provided above. This method includes: acquiring multiple frames of road surface images during vehicle travel; and determining whether the vehicle has performed a solid line U-turn based on lane line information in the multiple frames of road surface images and preset lane line features in the U-turn behavior.

[0105] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] On the other hand, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the solid line U-turn detection method provided above. The method includes: acquiring multiple frames of road surface images during vehicle travel; and determining whether the vehicle has performed a solid line U-turn based on lane line information in the multiple frames of road surface images and preset lane line features in the U-turn behavior.

[0107] On the other hand, embodiments of the present invention also provide a vehicle, which includes the electronic equipment provided in the foregoing embodiments. The vehicle provided in the embodiments of the present invention has the same implementation principle and the same technical effects as those in the foregoing method embodiments, and will not be repeated here.

[0108] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being stored on a non-transitory computer-readable storage medium, the computer program being executed by a processor, the computer being able to execute the solid line U-turn detection method provided above, the method including: acquiring multiple frames of road surface images during vehicle travel; determining whether the vehicle has performed a solid line U-turn based on lane line information in the multiple frames of road surface images and preset lane line features in the U-turn behavior.

[0109] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0110] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A solid line U-turn detection method, characterized by, include: Acquire multiple frames of road surface images during vehicle movement; Based on the lane line information in the multi-frame road surface images and the preset lane line features in the U-turn behavior, it is determined whether the vehicle has performed a solid line U-turn behavior. The step of determining whether a vehicle has performed a solid line U-turn based on lane line information in the multi-frame road surface images and preset lane line features in the U-turn behavior includes: Lane line detection is performed on the multi-frame road surface images to obtain lane line information corresponding to multiple lane lines. The lane line information includes lane line type and lane line coordinates. The lane line type includes at least solid line type. The fitting lines of the multiple lane lines are obtained based on the lane line coordinates, and the lane line vanishing points are determined based on the fitting lines. Based on the comparison between the position change of the lane line vanishing point in the multi-frame road surface image and the preset lane line features, and the lane line type, it is determined whether the vehicle has performed a solid line U-turn; wherein, the preset lane line features refer to the position features of the lane line vanishing point of the vehicle's U-turn behavior.

2. The solid-line U-turn detection method of claim 1, wherein, The step of determining whether a vehicle has performed a solid line U-turn based on the comparison result between the position change of the lane vanishing point in the multi-frame road surface images and the preset lane line features, and the lane line type, includes: To determine whether the vehicle has made a U-turn, the vanishing point of the lane line has moved from the target area along the first direction until it disappears from the road surface image in the continuous multi-frame road surface images, and after a preset interval time, it moves along the first direction to the target area. In the step of determining whether a vehicle is in a section of road where U-turns are not permitted, it is determined whether the lane line type corresponding to the lane line in the second direction of the vehicle is a solid line; wherein, the first direction and the second direction are opposite directions; If the vehicle is determined to have made a U-turn through the step of determining whether the vehicle has made a U-turn, and is determined to be in a section of road where U-turns are not allowed through the step of determining whether the vehicle is in a section of road where U-turns are not allowed, then the vehicle is determined to have made a U-turn across a solid line.

3. The solid-line U-turn detection method of claim 2, wherein, The step of determining whether a vehicle has made a U-turn also includes: Determine whether a vehicle is a left-hand drive or right-hand drive vehicle; Accordingly, determining whether the lane line vanishing point moves from the target area along the first direction until it disappears from the road surface image in the consecutive multi-frame road surface images, and moves back to the target area along the first direction after a preset interval, includes: When the vehicle is a left-hand drive vehicle, it is determined whether the lane line vanishing point moves to the right from the target area until it disappears from the road surface image in the continuous multi-frame road surface image, and moves to the target area to the right after a preset interval time. When the vehicle is a right-hand drive vehicle, it is determined whether the lane line vanishing point moves to the left from the target area until it disappears from the road surface image in the continuous multi-frame road surface image, and moves to the target area to the left after a preset interval time.

4. The solid-line U-turn detection method of claim 2, wherein, The steps for determining whether a vehicle is in a section of road where U-turns are not permitted include: The two main lane lines on both sides of the vehicle are determined based on the lane line coordinates. Determine whether the lane line type corresponding to the main lane line in the second direction in the consecutive multi-frame road surface images is solid line.

5. The solid line turning detection method according to any one of claims 1-4, characterized in that, After determining whether a vehicle has performed a solid line U-turn based on lane line information in the multi-frame road surface images and preset lane line features in the U-turn behavior, the method further includes: If a vehicle is found to be making a U-turn over a solid line, the corresponding road image will be stored and a driving safety warning will be issued to the driver.

6. The solid line U-turn detection method according to claim 1, characterized in that, The acquisition of multiple frames of road surface images during vehicle movement includes: The image acquisition module located in front of the vehicle acquires multiple frames of road surface images in front of the vehicle during its driving process.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the solid line turning detection method as described in any one of claims 1-6.

8. A vehicle, characterized in that, Includes the electronic device as described in claim 7.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the solid line turning detection method as described in any one of claims 1-6.

Images