Lane departure detection method, system, electronic device and readable storage medium

Abstract

The application relates to the technical field of intelligent driving, and discloses a lane deviation detection method and system, an electronic device and a readable storage medium, the method obtains lane collection images in a driving direction of a vehicle terminal, identifies a lane vanishing point from the lane collection images, determines a lane deviation detection result according to a lane deviation parameter between the vanishing point coordinates and the driving direction, completes lane deviation detection, compared with detecting lane deviation through lane lines or risk objects, the vanishing point is used as a convergence point of a vehicle driving target, a binocular camera and a vehicle-mounted radar are not needed to assist in collecting data, and lane deviation detection can still be realized even in the case that lane lines are unclear or risk objects cannot be identified, so that the identification difficulty of lane deviation detection is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicles, and in particular to a lane departure detection method and system, an electronic device and a readable storage medium. BACKGROUND

[0002] The lane departure warning system (LDW, Lane Departure Warning System) is a necessary supplement and auxiliary measure for active driving safety, which is a means to assist the driver to reduce traffic accidents caused by lane departure through warning, and improves the driving safety of the driver. At present, the lane departure detection in the lane departure warning system is usually based on image processing, machine learning, deep learning and other methods to identify the lane line of the lane where the vehicle is located or the risk object around the vehicle, and then determine the distance between the lane line or the risk object and the vehicle according to the position information of the lane line or the risk object.

[0003] However, the lane departure detection algorithm based on the lane line or the risk object needs binocular cameras, vehicle-mounted radars and the like to collect real-time data, and relies on clear lane lines or risk objects to calculate the deviation distance, so that the existing lane departure detection algorithm has too high detection difficulty, and the accuracy of the lane departure detection result is low. SUMMARY

[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is presented. This summary is not an extensive overview of the embodiments, nor is it intended to identify key / critical elements of the embodiments or to delineate the scope of the embodiments, but to present some aspects of the later detailed description in a simplified form.

[0005] In view of the above-mentioned shortcomings of the prior art, the present application discloses a lane departure detection method, system, electronic device and readable storage medium to improve the accuracy of the lane departure detection result.

[0006] The present application discloses a lane departure detection method, comprising: acquiring a lane collection image of a vehicle terminal in a driving direction; establishing a reference coordinate system of the driving direction mapped in the lane collection image; identifying a lane vanishing point of the lane in the lane collection image to obtain a vanishing point coordinate of the lane vanishing point mapped in the reference coordinate system; determining a lane deviation parameter between the vanishing point coordinate and the driving direction, and determining the lane deviation detection result according to the lane deviation parameter.

[0007] Optionally, the establishing the driving direction mapping in the reference coordinate system of the lane collection image comprises: obtaining an image size of the lane collection image, and determining an image center point of the lane collection image according to the image size; establishing a Cartesian coordinate system with the image center point as an origin of the coordinate system to obtain the reference coordinate system, wherein a longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal.

[0008] Optionally, the establishing the driving direction mapping in the reference coordinate system of the lane collection image comprises: mapping the vehicle terminal in the lane collection image; establishing a Cartesian coordinate system with the vehicle terminal as an origin of the coordinate system to obtain the reference coordinate system, wherein a longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal.

[0009] Optionally, the establishing the driving direction mapping in the reference coordinate system of the lane collection image comprises: determining a lane center axis according to two lane boundary lines of the lane in the lane collection image, and determining an axis center point of the lane center axis according to an axis length of the lane center axis; if a lane type of the lane in the lane collection image is a straight road, taking the axis center point as an origin of the coordinate system, and taking the lane center axis as a longitudinal axis of a Cartesian coordinate system to establish the Cartesian coordinate system to obtain the reference coordinate system of the driving direction mapping in the lane collection image, wherein a longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal; if the lane type of the lane in the lane collection image is a curved road, taking the axis center point as an origin of the coordinate system, and taking an axis tangent line tangent to the lane center axis as a longitudinal axis of a Cartesian coordinate system to establish the Cartesian coordinate system to obtain the reference coordinate system of the driving direction mapping in the lane collection image, wherein a longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal.

[0010] Optionally, after obtaining the lane collection image of the vehicle terminal in the driving direction, before identifying the lane vanishing point of the lane in the lane collection image, the method further comprises: performing image preprocessing on the lane collection image, wherein the image preprocessing comprises at least one of image denoising, improving image definition, and image size normalization.

[0011] Optionally, the identifying the lane vanishing point of the lane in the lane collection image comprises: extracting local texture features from the lane collection image; determining a road salient region from the lane collection image according to a differential excitation component in the local texture features; and determining the lane vanishing point in the lane collection image based on a linear voting mode through a direction component in the local texture features and the road salient region.

[0012] Optionally, the identifying the lane vanishing point of the lane in the lane collection image further comprises: if the lane type of the lane in the lane collection image is a straight road, taking the intersection point of the two lane lines of the lane in the lane collection image as the lane vanishing point in the lane collection image; if the lane type of the lane in the lane collection image is a curved road, dividing the two lane lines of the lane in the lane collection image into an inner side line and an outer side line, determining an inner tangent line tangent to the inner side line, and taking the intersection point of the inner tangent line and the outer side line as the lane vanishing point in the lane collection image.

[0013] Optionally, the longitudinal axis of the reference coordinate system is used to represent the driving direction of the vehicle terminal, and the lane deviation parameter between the vanishing point coordinate and the driving direction comprises at least one of the following: establishing a reference line between the vanishing point coordinate and the origin of the reference coordinate system, and taking the inner angle between the reference line and the longitudinal axis of the reference coordinate system as the lane deviation parameter between the vanishing point coordinate and the driving direction; determining the shortest distance between the vanishing point coordinate and the longitudinal axis of the reference coordinate system, and taking the shortest distance as the lane deviation parameter between the vanishing point coordinate and the driving direction.

[0014] Optionally, the lane deviation detection result is determined according to the lane deviation parameter, which comprises: if the lane deviation parameter is greater than or equal to a preset deviation parameter threshold, determining that the lane deviation detection result is lane deviation, determining that the lane vanishing point is located in a quadrant region of the reference coordinate system, and determining the lane deviation direction according to the quadrant region; if the lane deviation parameter is less than the preset deviation parameter threshold, determining that the lane deviation detection result is no lane deviation.

[0015] Optionally, if the lane deviation detection result comprises lane deviation, the method further comprises at least one of the following: collecting an actual correction angle of the vehicle terminal until the lane deviation detection result comprises no lane deviation, and adjusting the deviation parameter threshold according to the comparison result between the collected actual correction angle and a preset expected warning angle; collecting an actual correction angle of the vehicle terminal until the lane deviation detection result comprises no lane deviation, comparing the collected actual correction angle with a preset expected warning angle to obtain an expected comparison result, if the number of obtained comparison results is greater than a preset number threshold, determining the confidence of the deviation parameter threshold according to each expected comparison result, and adjusting the deviation parameter threshold according to the comparison result between the confidence and a preset initial confidence threshold; showing the lane deviation detection result to a user, collecting user feedback information corresponding to the lane deviation detection result, if the user feedback information comprises incorrect result, and adjusting the deviation parameter threshold according to a preset adjustment ratio.

[0016] Optionally, if the lane deviation detection result includes lane deviation, the method further comprises: acquiring a steering wheel angle of the vehicle terminal, determining a pre-warning inhibition state according to a comparison between a direction of the steering wheel angle and a lane deviation direction; if the pre-warning inhibition state is pre-warning inhibition open, re-determining the lane deviation detection result after a preset time period; if the pre-warning inhibition state is pre-warning inhibition closed, performing lane deviation prompting through a preset pre-warning mode, and / or controlling a longitudinal driving direction of the vehicle terminal according to the lane deviation direction until the lane deviation detection result includes no lane deviation.

[0017] Optionally, acquiring the lane collection image of the vehicle terminal in the driving direction comprises: acquiring the lane collection image of the vehicle terminal in the driving direction by a monocular camera arranged on the vehicle terminal.

[0018] The application discloses a lane deviation detection system, comprising: an acquisition module, configured to acquire a lane collection image of a vehicle terminal in a driving direction; an establishment module, configured to establish a reference coordinate system in which the driving direction is mapped to the lane collection image; an identification module, configured to identify a lane vanishing point of a lane in the lane collection image, and obtain a vanishing point coordinate of the lane vanishing point mapped to the reference coordinate system; and a determination module, configured to determine a lane deviation parameter between the vanishing point coordinate and the driving direction, and determine a lane deviation detection result according to the lane deviation parameter.

[0019] The application discloses a computer readable storage medium, which stores a computer program.

[0020] The application has the following beneficial effects:

[0021] The lane deviation detection is completed by acquiring the lane collection image of the vehicle terminal in the driving direction, and identifying the lane vanishing point from the lane collection image, so as to determine the lane deviation detection result according to the lane deviation parameter between the vanishing point coordinate and the driving direction. In this way, compared with detecting lane deviation by lane lines or risk objects, the lane vanishing point is used as a convergence point of the vehicle driving target, and a binocular camera and a vehicle-mounted radar are not needed for assisting data acquisition, and at the same time, the lane deviation detection can still be realized even in the case that the lane lines are unclear or risk objects cannot be identified, so that the identification difficulty of the lane deviation detection is reduced.

[0022] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the application. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0024] Figure 1 This is a schematic diagram of the architecture of an autonomous driving software in an embodiment of the present invention;

[0025] Figure 2 This is a schematic flowchart of a lane departure detection method according to an embodiment of the present invention;

[0026] Figure 3 This is a flowchart illustrating a lane vanishing point identification method in an embodiment of the present invention;

[0027] Figure 4 This is a schematic diagram of a lane disappearance point in an embodiment of the present invention;

[0028] Figure 5 This is a schematic diagram of establishing a Cartesian coordinate system with the driving direction as the vertical axis in an embodiment of the present invention;

[0029] Figure 6 This is a flowchart illustrating another lane departure detection method in an embodiment of the present invention;

[0030] Figure 7 This is a schematic diagram of the structure of a lane departure detection system according to an embodiment of the present invention;

[0031] Figure 8 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0032] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and sub-samples in the embodiments can be combined with each other.

[0033] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0034] In the following description, numerous specific details are discussed in order to provide a thorough understanding of embodiments of the present application. However, those skilled in the art will recognize that the embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and devices are not described in exhaustive detail in order to avoid obscuring the embodiments of the present application.

[0035] The terms "first", "second", and the like, as used in the description and the claims of the present disclosure and the foregoing drawings, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the use of the terms so

[0036] The term "plurality" means two or more, unless otherwise specified.

[0037] In the present disclosure, the character " / " represents an "or" relationship between the preceding and following objects. For example, A / B means A or B.

[0038] The term "and / or" is a description of the relationship between the objects, which means that there can be three relationships. For example, A and / or B means that there are three relationships of A or B, or A and B.

[0039] First of all, it should be pointed out that the embodiments of the present disclosure are based on vanishing point detection technology and act on the automatic driving system of the vehicle.

[0040] According to the principle of projective geometry, parallel line segments in real space will intersect at the same vanishing point (Vanishing Point) on the image plane after perspective projection. Vanishing point detection is derived from the field of visual saliency detection subdivision, as a technology for detecting vanishing points in images, has been relatively mature research, applied to three-dimensional scene reconstruction, camera calibration and auxiliary intelligent driving fields, can be used as the convergence point of the direction information in front of the vehicle.

[0041] The vanishing point detection includes vanishing point detection based on a space conversion technique, vanishing point detection based on intersection information, vanishing point detection based on a statistical algorithm, and vanishing point detection based on a voting method. The vanishing point detection based on the space conversion technique detects a vanishing point by mapping a real image space to a projection space of a certain limited area and detecting the vanishing point through a mapping relationship between the two spaces. The vanishing point detection based on the intersection information detects a vanishing point by calculating intersections of two straight lines and clustering the intersections. The vanishing point detection based on the statistical algorithm detects an image vanishing point by constructing a cost function based on vanishing point feature points. The vanishing point detection based on the voting method detects a vanishing point by using local texture features or straight line edge information of an image and through a voting method. The embodiments of the present disclosure provide but are not limited to the above vanishing point detection methods.

[0042] An automatic driving system is a car system that can automatically and safely operate a motor vehicle without any human initiative operation by relying on artificial intelligence, visual computing, radar, monitoring devices and global positioning system. The automatic driving system usually understands the surrounding traffic conditions through a video camera, a radar sensor and a laser range finder, navigates the road ahead through a detailed map (a map collected by a manned vehicle), realizes real-time continuous control of the car through communication technology, network technology, computer technology and control technology, and realizes two-way data communication between the car and the server through modern communication means.

[0043] Because the car travels at a high speed, the automatic driving system usually collects data and refreshes the state with seconds as the minimum unit to ensure the safety and driving experience of the user. The specific frequency is usually 0.02 s. In other application scenarios, the frequency of refreshing the road conditions of the travel road of the object can be set according to actual conditions, and the embodiments of the present application do not limit this.

[0044] In combination with Figure 1As shown, the embodiment of the present disclosure provides a schematic diagram of the framework of the automatic driving software, the automatic driving software comprises an automatic driving information preprocessing system 101, an automatic driving controller 102 and an automatic driving executor 103, wherein the automatic driving information preprocessing system 101 is configured to acquire vehicle data and fuse the vehicle data; the automatic driving controller 102 is configured to receive the vehicle data output by the automatic driving information preprocessing system 101, reconstruct the environment, predict the data, and make a behavior decision on the received vehicle data, and set the state information of the automatic driving through a state machine, at the same time, the automatic driving controller 102 comprises a longitudinal system and a lateral system, the lateral system is configured to manage the turning in the automatic driving, and the longitudinal system is configured to manage the forward and backward movement in the automatic driving, and the longitudinal system needs to correct the driving direction of the vehicle when the lane deviation occurs; the automatic driving executor 103 comprises a brake, an engine, a gear shifter, an alarm and a steering wheel, the brake, the engine, the gear shifter and the alarm are controlled by the longitudinal system of the automatic driving controller 102, and the steering wheel is controlled by the lateral system of the automatic driving controller 102.

[0045] In combination Figure 2 As shown, the embodiment of the present disclosure provides a lane deviation detection method, comprising:

[0046] In step S201, a lane collection image in the driving direction of a vehicle terminal is acquired;

[0047] In step S202, a reference coordinate system of the lane collection image in which the driving direction is mapped is established;

[0048] In step S203, a lane vanishing point of the lane in the lane collection image is recognized, and a vanishing point coordinate of the lane vanishing point mapped in the reference coordinate system is obtained;

[0049] In step S204, a lane deviation parameter between the vanishing point coordinate and the driving direction is determined, and a lane deviation detection result is determined according to the lane deviation parameter.

[0050] By using the lane deviation detection method provided by the embodiment of the present disclosure, the lane collection image in the driving direction of the vehicle terminal is acquired, and the lane vanishing point is recognized from the lane collection image, so as to determine the lane deviation detection result according to the lane deviation parameter between the vanishing point coordinate and the driving direction, and complete the lane deviation detection. In this way, compared with detecting the lane deviation through the lane line or the risk object, the vanishing point is taken as the convergence point of the vehicle driving target, and it is not necessary to assist in collecting data by using the binocular camera and the vehicle-mounted radar, and at the same time, even in the case that the lane line is unclear or the risk object cannot be recognized, the lane deviation detection can still be realized, so as to reduce the recognition difficulty of the lane deviation detection and improve the detection efficiency of the vanishing point detection.

[0051] Optionally, the lane collection image of the vehicle terminal in the driving direction is obtained by: arranging a vehicle-mounted camera in the middle line of the vehicle terminal, wherein the vehicle-mounted camera comprises one of a monocular camera, a binocular camera, an infrared camera, etc.; and collecting an image of the front of the vehicle terminal by the vehicle-mounted camera to obtain the lane collection image.

[0052] Optionally, the reference coordinate system of the lane collection image in which the driving direction is mapped is established by: obtaining the image size of the lane collection image, and determining the image center point of the lane collection image according to the image size; establishing a Cartesian coordinate system with the image center point as the origin of the coordinate system to obtain the reference coordinate system, wherein the longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal.

[0053] Optionally, the reference coordinate system of the lane collection image in which the driving direction is mapped is established by: mapping the vehicle terminal in the lane collection image; establishing a Cartesian coordinate system with the vehicle terminal as the origin of the coordinate system to obtain the reference coordinate system, wherein the longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal.

[0054] Optionally, the reference coordinate system of the lane collection image in which the driving direction is mapped is established by: determining the lane center axis according to the two lane boundary lines of the lane in the lane collection image, and determining the axis center point of the lane center axis according to the axis length of the lane center axis; if the lane type of the lane in the lane collection image is a straight road, taking the axis center point as the origin of the coordinate system, and taking the center axis as the longitudinal axis of the Cartesian coordinate system to establish the Cartesian coordinate system, thereby obtaining the reference coordinate system of the lane collection image in which the driving direction is mapped, wherein the longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal; if the lane type of the lane in the lane collection image is a curved road, taking the axis center point as the origin of the coordinate system, and taking the tangent of the axis tangent to the center axis as the longitudinal axis of the Cartesian coordinate system to establish the Cartesian coordinate system, thereby obtaining the reference coordinate system of the lane collection image in which the driving direction is mapped, wherein the longitudinal axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal.

[0055] Optionally, after obtaining the lane collection image of the vehicle terminal in the driving direction, and before identifying the lane vanishing point of the lane in the lane collection image, the method further comprises: performing image preprocessing on the lane collection image, wherein the image preprocessing comprises at least one of image denoising, improving image clarity, and image size normalization.

[0056] Optionally, the lane collection image of the vehicle terminal in the driving direction is obtained by: arranging a vehicle-mounted camera in the middle line of the vehicle terminal, wherein the vehicle-mounted camera comprises one of a monocular camera, a binocular camera, an infrared camera, etc.; and collecting an image of the front of the vehicle terminal by the vehicle-mounted camera to obtain the lane collection image. Figure 3As shown, the lane vanishing point of the lane in the lane collection image is identified, including: extracting local texture features from the lane collection image; determining a road saliency region from the lane collection image according to a difference excitation component in the local texture features; determining the lane vanishing point in the lane collection image based on a linear voting mode, through a direction component in the local texture features and the road saliency region.

[0057] Optionally, in combination with Figure 4 As shown, the lane vanishing point of the lane in the lane collection image is identified, and further includes: if the lane type of the lane in the lane collection image is a straight road, then the intersection point of the two lane edges of the lane in the lane collection image is taken as the lane vanishing point in the lane collection image; if the lane type of the lane in the lane collection image is a curved road, then the two lane edges of the lane in the lane collection image are divided into an inner side edge and an outer side edge, an inner side tangent line is determined which is tangent to the inner side edge, and the intersection point of the inner side tangent line and the outer side edge is taken as the lane vanishing point in the lane collection image.

[0058] In some embodiments, the vanishing point largely reflects the forward direction in the field of view of the vehicle driver, in a road scene with an open field of view and a straight road, when the vanishing point is located at the upper left or lower left of the road image, it indicates that the lane deviates to the left, and the vehicle needs to adjust the direction to follow the left vanishing point. When the vanishing point is in the center of the image, it indicates that the lane is not deviated, and the driver's line of sight is directly in front of him, and when the vanishing point is located at the upper right or lower right of the road image, it indicates that the vehicle needs to adjust the direction to follow the road to the right.

[0059] Optionally, the longitudinal axis of the reference coordinate system is used to represent the driving direction of the vehicle terminal, and the lane deviation parameter between the vanishing point coordinate and the driving direction includes at least one of: establishing a reference line between the vanishing point coordinate and the origin of the reference coordinate system, and taking the inner angle between the reference line and the longitudinal axis of the reference coordinate system as the lane deviation parameter between the vanishing point coordinate and the driving direction; determining the shortest distance between the vanishing point coordinate and the longitudinal axis of the reference coordinate system, and taking the shortest distance as the lane deviation parameter between the vanishing point coordinate and the driving direction.

[0060] In combination with Figure 5 As shown, the inner angle between the reference line and the longitudinal axis of the reference coordinate system (i.e. the projection deviation angle of the vanishing point in the vertical direction of the reference coordinate system) is taken as the lane deviation parameter between the vanishing point coordinate and the driving direction. Since lane deviation detection mainly focuses on the deviation in the left and right directions, factors such as vehicle height, camera installation pitch angle, and uphill and downhill roads do not affect the accuracy of lane deviation measurement. By taking the driving direction as the longitudinal axis of the coordinate system to establish a Cartesian coordinate system, the complexity of the lane deviation parameter can be simplified. When the vanishing point is located in the first quadrant of the reference coordinate system, the lane deviation parameter is Degree vp1; when the vanishing point is located in the second quadrant of the reference coordinate system, the lane deviation parameter is Degree vp2 ; when the vanishing point is located in the third quadrant of the reference coordinate system, the lane deviation parameter is Degree vp3 ; when the vanishing point is located in the fourth quadrant of the reference coordinate system, the lane deviation parameter is Degree vp4 ; the lane deviation parameter is Degree vp as a comprehensive calculation.

[0061] In some embodiments, the present disclosure simplifies the operation between the road image coordinate system and the vehicle body coordinate system through the reference coordinate system and the lane deviation parameter. Since the lane deviation detection mainly focuses on the deviation trend in the horizontal direction, the translation of the vehicle body coordinate system in the vertical direction does not change the calculation of the projection deviation angle in the horizontal direction. Therefore, the horizontal plane of the vehicle body coordinate system is translated to a plane on the horizontal axis of the road image coordinate system, and a coordinate system is established in the road image coordinate system with the image geometric center point as the origin. Thus, the relative value of the angle of the image coordinate vanishing point deviating from the vertical direction of the road image coordinate system can be used as the basis for lane deviation judgment, shielding the influence of the vehicle body height and the difference caused by the installation of the camera with an upward angle, and improving the efficiency of lane deviation angle calculation.

[0062] Optionally, the lane deviation detection result is determined according to the lane deviation parameter, including: if the lane deviation parameter is greater than or equal to a preset deviation parameter threshold, the lane deviation detection result is determined as lane deviation, and the lane vanishing point is located in a quadrant region of the reference coordinate system, and the lane deviation direction is determined according to the quadrant region; if the lane deviation parameter is less than the preset deviation parameter threshold, the lane deviation detection result is determined as no lane deviation.

[0063] In some embodiments, if the lane deviation parameter includes an inner angle, the deviation parameter threshold is 5° to 30°.

[0064] In some embodiments, the comprehensive calculation of the lane deviation parameter Degree vp is compared with a preset deviation parameter threshold Degree th ; when Degree vp is greater than or equal to Degree th , it indicates that the lane deviation degree exceeds the warning threshold and needs to be warned, and when the vanishing point is located in the first and fourth quadrants of the road image coordinate system, it indicates that the vehicle deviates to the left of the lane, and when the vanishing point is located in the second and third quadrants, it indicates that the vehicle deviates to the right of the lane.

[0065] Optionally, if the lane deviation detection result includes that lane deviation occurs, the method further includes at least one of: collecting an actual correction angle of the vehicle terminal until the lane deviation detection result includes that lane deviation does not occur, and adjusting the deviation parameter threshold according to a comparison result between the collected actual correction angle and the preset expected warning angle; collecting an actual correction angle of the vehicle terminal until the lane deviation detection result includes that lane deviation does not occur, and comparing the collected actual correction angle with the preset expected warning angle to obtain an expected comparison result, if a number of the obtained comparison results is greater than a preset number threshold, determining a confidence of the deviation parameter threshold according to each expected comparison result, and adjusting the deviation parameter threshold according to a comparison result between the confidence and a preset initial confidence threshold; showing the lane deviation detection result to a user, and collecting user feedback information corresponding to the lane deviation detection result, if the user feedback information includes that the result is incorrect, adjusting the deviation parameter threshold according to a preset adjustment ratio.

[0066] In some embodiments, adjusting the deviation parameter threshold according to a comparison result between the collected actual correction angle and the preset expected warning angle includes: if the collected actual correction angle is greater than the preset expected warning angle, decreasing the deviation parameter threshold according to a preset adjustment ratio; if the collected actual correction angle is equal to the preset expected warning angle, not adjusting the deviation parameter threshold; and if the collected actual correction angle is less than the preset expected warning angle, increasing the deviation parameter threshold according to the preset adjustment ratio.

[0067] In some embodiments, the preset number threshold is 3-20.

[0068] In some embodiments, determining the confidence of the deviation parameter threshold according to each comparison result includes: if the comparison result is that the actual correction angle is greater than the expected warning angle, increasing the confidence by one unit; if the comparison result is that the actual correction angle is equal to the expected warning angle, maintaining the current confidence; and if the comparison result is that the actual correction angle is less than the expected warning angle, decreasing the confidence by one unit.

[0069] In some embodiments, adjusting the deviation parameter threshold according to a comparison result between the confidence and the preset initial confidence threshold includes: if the confidence is greater than the initial confidence threshold, decreasing the deviation parameter threshold according to a preset adjustment ratio; if the confidence is equal to the initial confidence threshold, not adjusting the deviation parameter threshold; and if the confidence is less than the initial confidence threshold, increasing the deviation parameter threshold according to the preset adjustment ratio.

[0070] In some embodiments, the vehicle reports the actual correction angle to a big data processing center of the Internet of Vehicles, adjusts the offset parameter threshold based on the actual correction angle, and issues the adjusted offset parameter threshold through vehicle OTA upgrade or vehicle cloud remote control instruction, thereby improving the accuracy of the early warning and the driving experience of the vehicle.

[0071] In some embodiments, the parameters of the lane deviation early warning model based on vanishing point detection are corrected by listening to the user feedback information of the driver. If voice and image warning prompts are used, after the current warning prompt is broadcast, the driver is asked about the accuracy of the current warning prompt. The driver only needs to simply answer yes or no to the vehicle-mounted intelligent robot. If the driver thinks that the current navigation is accurate, no threshold updating process is needed. If the driver thinks that the current warning is not ready or is a false warning, the offset parameter threshold is reduced in range by a preset adjustment ratio (1% of the actual running threshold) until it converges to a relatively accurate critical point. At the same time, the adjustment amount cannot exceed half of Degree th , to avoid the extreme scenario of Degree th becoming too small or even approaching zero, thereby optimizing the detection method and improving the detection and early warning accuracy.

[0072] Optionally, if the lane deviation detection result includes lane deviation, the method further includes: obtaining the steering wheel angle of the vehicle terminal, determining the early warning suppression state according to the comparison between the direction of the steering wheel angle and the direction of the lane deviation; if the early warning suppression state is early warning suppression enabled, the lane deviation detection result is re-determined after a preset time period; if the early warning suppression state is early warning suppression disabled, the lane deviation is prompted through a preset early warning mode, and / or the longitudinal driving direction of the vehicle terminal is controlled according to the lane deviation direction until the lane deviation detection result includes no lane deviation.

[0073] In some embodiments, part of the alarm is suppressed by the left and right signal information of the steering wheel. For example, if the vehicle warns of lane deviation to the right while the steering wheel is turning to the left, the warning prompt is temporarily turned off for N seconds, and after N seconds, the early warning suppression is cancelled and normal detection is restarted. At the same time, the distance data from the lane line can also be used for early warning suppression. If the distance is greater than a certain distance threshold, the early warning can also be temporarily suppressed. Finally, the lane deviation detection function is suspended or turned off by the driver's interactive operation of the overall system configuration switch, etc. The early warning prompt output device and apparatus are notified according to the determined early warning suppression state, or the lane deviation detection result is fed back to the intelligent driving decision center for processing and application.

[0074] In some embodiments, the preset warning mode includes sending a warning information to notify a vehicle-mounted audio device to play a preset warning prompt sound, and controlling a display screen to display a virtual lane line jumping and turning red for warning until the warning is automatically eliminated or the driver interacts to restore normality.

[0075] In combination Figure 6 As shown in the drawings, the embodiments of the present disclosure provide a lane departure detection method, comprising:

[0076] In step S601, a lane collection image in a driving direction of a vehicle terminal is acquired;

[0077] In step S602, an image center point of the lane collection image is taken as an origin of a coordinate system to establish a Cartesian coordinate system, and a reference coordinate system is obtained;

[0078] In the reference coordinate system, a longitudinal axis direction is taken as the driving direction of the vehicle terminal;

[0079] In step S603, a lane vanishing point of the lane in the lane collection image is recognized;

[0080] In the vanishing point recognition, image preprocessing is performed on the lane collection image; local texture features are extracted from the lane collection image; a road salient region is determined from the lane collection image according to a difference excitation component in the local texture features; and a lane vanishing point in the lane collection image is determined based on a linear voting mode through a direction component in the local texture features and the road salient region;

[0081] In step S604, a projection offset angle of the vanishing point in a vertical direction of the reference coordinate system is taken as a lane offset parameter between the vanishing point coordinate and the driving direction;

[0082] In step S605, it is determined whether the lane offset parameter is greater than or equal to a preset offset parameter threshold value, if not, the process jumps to step S606, and if yes, the process jumps to step S607;

[0083] In step S606, the lane offset detection result is determined as no lane offset.

[0084] In step S607, the lane offset detection result is determined as lane offset, and the process jumps to step S608 and step S610;

[0085] In step S608, an actual correction angle of the vehicle terminal is collected until the lane offset detection result includes no lane offset;

[0086] In step S609, the offset parameter threshold value is adjusted according to a comparison result between the collected actual correction angle and a preset expected warning angle.

[0087] Step S610, determining a pre-warning suppression state according to a comparison between the direction of the steering wheel angle and the lane deviation direction;

[0088] Step S611, determining whether the pre-warning suppression state is pre-warning suppression opening, if yes, jumping to step S612, if not, jumping to step S613 and step 614;

[0089] Step S612, re-determining the lane deviation detection result after a preset time period.

[0090] Step S613, controlling the longitudinal driving direction of the vehicle terminal according to the lane deviation direction until the lane deviation detection result includes no lane deviation.

[0091] Step S614, prompting lane deviation by a preset pre-warning mode until the lane deviation detection result includes no lane deviation;

[0092] Step S615, collecting user feedback information corresponding to the lane deviation detection result.

[0093] Step S616, if the user feedback information includes incorrect result, adjusting the deviation parameter threshold according to a preset adjustment ratio.

[0094] The lane deviation detection method provided by the embodiment of the present disclosure has the following advantages:

[0095] Firstly, compared with detecting lane deviation by lane lines or risk objects, taking the vanishing point as the convergence point of the vehicle driving target does not need binocular cameras or vehicle-mounted radars to assist in collecting data, and at the same time, lane deviation detection can still be realized even in the case that lane lines are unclear or risk objects cannot be identified, thereby reducing the identification difficulty of lane deviation detection and improving the detection efficiency of vanishing point detection;

[0096] Secondly, the coordinate system is established with the image geometric center point as the origin in the road image coordinate system, so that the angle relative value of the image coordinate vanishing point deviating from the vertical direction of the road image coordinate system can be used as the basis for lane deviation judgment, the influence of the vehicle body height and the difference caused by the installation of the camera itself with the upward angle are shielded, and the complex coordinate system conversion calculation is avoided, thereby improving the efficiency of lane deviation angle calculation;

[0097] Thirdly, vehicle calibration data is collected, and the threshold of the deviation parameter is adjusted according to the vehicle calibration data to optimize the detection method and improve the detection and pre-warning accuracy;

[0098] Fourth, an early warning suppression mechanism is established to improve the flexibility of early warning and the driving experience of the driver.

[0099] In combination Figure 7 As shown in the figure, the embodiment of the disclosure provides a lane departure detection system, comprising an acquisition module 701, an establishment module 702, a failure module 703 and a determination module 704. The acquisition module 701 is configured to acquire lane collection images of a vehicle terminal in a driving direction; the establishment module 702 is configured to establish a reference coordinate system in which the driving direction is mapped on the lane collection images; the failure module 703 is configured to identify a lane vanishing point of the lane in the lane collection images to obtain a vanishing point coordinate of the lane vanishing point mapped on the reference coordinate system; and the determination module 704 is configured to determine a lane deviation parameter between the vanishing point coordinate and the driving direction, and determine a lane deviation detection result according to the lane deviation parameter.

[0100] By using the lane departure detection system provided by the embodiment of the disclosure, the lane collection images of the vehicle terminal in the driving direction are acquired, and the lane vanishing point is identified from the lane collection images, so as to determine the lane deviation detection result according to the lane deviation parameter between the vanishing point coordinate and the driving direction, and complete the lane deviation detection. In this way, compared with detecting the lane deviation by using the lane line or the risk object, the vanishing point is taken as the convergence point of the vehicle driving target, and the binocular camera and the vehicle-mounted radar are not needed to assist in collecting data. At the same time, even in the case that the lane line is unclear or the risk object cannot be identified, the lane deviation detection can still be realized, so as to reduce the identification difficulty of the lane deviation detection and improve the detection efficiency of the vanishing point detection.

[0101] Figure 8 The structural schematic diagram of the computer system of the electronic device suitable for realizing the embodiment of the disclosure is shown. It should be noted that, Figure 8 The computer system 800 of the electronic device shown is only an example, and should not bring any limitation to the function and use range of the embodiment of the disclosure.

[0102] As Figure 8 shown, the computer system 800 comprises a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 802 or the program loaded from the storage part 808 to the random access memory (RAM) 803, such as performing the method in the above embodiment. In the RAM 803, various programs and data required for system operation are also stored. The CPU 801, the ROM 802 and the RAM 803 are connected to each other through the bus 804. The input / output (I / O) interface 805 is also connected to the bus 804.

[0103] The following components are connected to the I / O interface 805: an input part 806 including a keyboard, a mouse, etc.; an output part 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc.; a storage part 808 including a hard disk, etc.; and a communication part 809 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 810 as necessary, so that a computer program read therefrom is installed in the storage part 808 as necessary.

[0104] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing a computer program for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the central processing unit (CPU) 801, various functions defined in the system of the present application are executed.

[0105] It should be noted that the computer readable medium shown in the embodiments of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable signal medium can include a data signal propagating in the baseband or as a carrier wave part of a signal propagating in the baseband, in which the computer readable computer program is carried. Such a propagating data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit programs for use by or in connection with an instruction execution system, device or apparatus. The computer program contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0106] The embodiments of the present disclosure also provide a computer readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the methods in the embodiments.

[0107] The computer readable storage medium in the embodiments of the present disclosure can be understood by those skilled in the art that all or part of the steps of the above-mentioned method embodiments can be completed by a computer program related hardware. The aforementioned computer program can be stored in a computer readable storage medium. The program, when executed, performs steps including the above-mentioned method embodiments; and the aforementioned storage medium includes ROM, RAM, magnetic disk or optical disk and various media that can store program codes.

[0108] The electronic device disclosed in the embodiments includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected with the processor and the transceiver and complete communication between each other. The memory is used to store a computer program, the communication interface is used for communication, and the processor and the transceiver are used to run the computer program, so that the electronic device executes each step of the method as above.

[0109] In the present embodiment, the memory can comprise a Random Access Memory (RAM) and can also include a non-volatile memory such as at least one disk memory.

[0110] The processor described above can be a general processor, including a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Network Processor (NP), etc.; can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0111] The foregoing description and accompanying drawings fully illustrate embodiments of the present disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Unless explicitly required, individual components and functions are typical of one embodiment of this application, and the order of operation may vary. Parts and subsamples of some embodiments may be included in or replace parts and subsamples of other embodiments. Moreover, the terminology used in this application is for descriptive purposes only and is not intended to limit the claims. As used in the description of the embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used herein means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated subsamples, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other subsamples, wholes, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes the element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0112] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0113] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, apparatuses, etc.) can be implemented in other manners. For example, the described device embodiments are merely schematic. For example, the division of the units is merely a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some of the components can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms. The unit illustrated as a separate component can or can not be physically separate, and can or can not be a physical component. Some or all of the units can be selected according to actual needs to implement the embodiments. In addition, the units in the embodiments disclosed herein can be integrated into one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated into one unit.

[0114] The flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the system, method and computer program product according to the embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code containing one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks can occur in different orders than those noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the drawings, the operations or steps corresponding to different blocks can also occur in different orders from those disclosed in the descriptions, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. Each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A lane departure detection method, characterized in that, include: Acquire lane images of the vehicle terminal in the direction of travel; Establish a reference coordinate system that maps the driving direction to the image acquired in the lane; Identify the vanishing point of the lane in the lane acquisition image, and obtain the vanishing point coordinates mapped to the reference coordinate system; Determine the lane offset parameter between the vanishing point coordinates and the driving direction, and determine the lane offset detection result based on the lane offset parameter and a preset offset parameter threshold; If the lane departure detection result includes lane departure, the method further includes at least one of the following: The actual correction angle of the vehicle terminal is collected until the lane departure detection result includes no lane departure, and the deviation parameter threshold is adjusted according to the comparison result between the collected actual correction angle and the preset expected warning angle. The actual correction angle of the vehicle terminal is collected until the lane departure detection result includes lane no deviation. The collected actual correction angle is compared with the preset expected warning angle to obtain the expected comparison result. If the number of obtained comparison results is greater than the preset number threshold, the confidence level of the offset parameter threshold is determined according to each expected comparison result. The offset parameter threshold is adjusted according to the comparison result between the confidence level and the preset initial confidence level threshold. The system displays the lane departure detection results to the user and collects user feedback information corresponding to the lane departure detection results. If the user feedback information indicates that the results are incorrect, the system adjusts the lane departure parameter threshold according to a preset adjustment ratio.

2. The method according to claim 1, characterized in that, Establishing a reference coordinate system that maps the driving direction to the lane-acquired image includes: Obtain the image size of the lane acquisition image, and determine the image center point of the lane acquisition image based on the image size; A Cartesian coordinate system is established by taking the center point of the image as the origin, thus obtaining a reference coordinate system. The vertical axis of the reference coordinate system is taken as the driving direction of the vehicle terminal.

3. The method according to claim 1, characterized in that, Establishing a reference coordinate system that maps the driving direction to the lane-acquired image includes: The vehicle terminal is mapped onto the lane-collected image; A Cartesian coordinate system is established with the vehicle terminal as the origin, resulting in a reference coordinate system. The vertical axis of the reference coordinate system is taken as the driving direction of the vehicle terminal.

4. The method according to claim 1, characterized in that, Establishing a reference coordinate system that maps the driving direction to the lane-acquired image includes: The lane centerline is determined based on the two lane edge lines in the lane acquisition image, and the center point of the lane centerline is determined based on the length of the lane centerline. If the lane type in the lane acquisition image is a straight road, then the center point of the axis is taken as the origin of the coordinate system, and the central axis is determined as the vertical axis of the Cartesian coordinate system. The Cartesian coordinate system is established to obtain the reference coordinate system of the lane acquisition image in which the driving direction is mapped. The vertical axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal. If the lane type in the lane acquisition image is a curved road, then the center point of the axis is taken as the origin of the coordinate system, and the tangent line of the axis that is tangent to the central axis is taken as the vertical axis of the Cartesian coordinate system. The Cartesian coordinate system is established to obtain the driving direction mapped to the reference coordinate system of the lane acquisition image. The vertical axis direction of the reference coordinate system is taken as the driving direction of the vehicle terminal.

5. The method according to claim 1, characterized in that, After acquiring the lane image of the vehicle terminal in the direction of travel, and before identifying the lane vanishing point in the lane image, the method further includes: The lane acquisition image is subjected to image preprocessing, wherein the image preprocessing includes at least one of image denoising, improving image clarity, and image size normalization.

6. The method according to claim 1, characterized in that, Identifying the lane vanishing point in the lane acquisition image includes: Extract local texture features from the lane acquisition image; The salient regions of the road are determined from the lane acquisition image based on the differential excitation components in the local texture features; Based on the linear voting model, the lane vanishing point in the lane acquisition image is determined by the directional component in the local texture features and the salient area of ​​the road.

7. The method according to claim 6, characterized in that, Identifying the lane vanishing point in the lane acquisition image further includes: If the lane type in the lane acquisition image is a straight road, then the intersection point of the two lane edge lines in the lane acquisition image is taken as the lane vanishing point in the lane acquisition image. If the lane type in the lane acquisition image is a curved road, then the two lane edge lines in the lane acquisition image are divided into inner edge lines and outer edge lines. The inner tangent line that is tangent to the inner edge line is determined, and the intersection point of the inner tangent line and the outer edge line is taken as the lane vanishing point in the lane acquisition image.

8. The method according to claim 1, characterized in that, The vertical axis of the reference coordinate system is used to characterize the driving direction of the vehicle terminal. The lane offset parameter determined between the vanishing point coordinates and the driving direction includes any of the following: Establish a reference line between the vanishing point coordinates and the origin of the reference coordinate system, and use the interior angle between the reference line and the vertical axis of the reference coordinate system as the lane offset parameter between the vanishing point coordinates and the driving direction; Determine the shortest distance between the vanishing point coordinates and the vertical axis of the reference coordinate system, and use the shortest distance as the lane offset parameter between the vanishing point coordinates and the driving direction.

9. The method according to any one of claims 1 to 8, characterized in that, The lane departure detection result is determined based on the lane departure parameters and a preset lane departure parameter threshold, including: If the lane offset parameter is greater than or equal to the preset offset parameter threshold, the lane offset detection result is determined to be a lane offset, and the lane vanishing point is determined to be located in the quadrant region of the reference coordinate system. The lane offset direction is determined based on the quadrant region. If the lane offset parameter is less than the preset offset parameter threshold, the lane offset detection result is determined as no lane offset.

10. The method according to claim 9, characterized in that, If the lane departure detection result includes lane departure, the method further includes: The steering wheel angle of the vehicle terminal is obtained, and the warning suppression state is determined based on a comparison file between the direction of the steering wheel angle and the direction of lane departure. If the warning suppression state is warning suppression enabled, the lane departure detection result will be re-determined after a preset time period. If the warning suppression state is warning suppression off, then lane departure warning is given through a preset warning method, and / or the longitudinal driving direction of the vehicle terminal is controlled according to the lane departure direction until the lane departure detection result includes lane no departure.

11. The method according to any one of claims 1 to 8, characterized in that, Acquire lane-captured images of the vehicle terminal in the direction of travel, including: The vehicle terminal acquires lane images in the direction of travel using a monocular camera installed on the vehicle terminal.

12. A lane departure detection system employing the method described in any one of claims 1 to 11, characterized in that, include: The acquisition module is used to acquire lane images captured by the vehicle terminal in the direction of travel; A module is established to create a reference coordinate system that maps the driving direction to the image captured in the lane. The recognition module is used to identify the vanishing point of the lane in the lane acquisition image and obtain the vanishing point coordinates mapped to the reference coordinate system. The determination module is used to determine the lane offset parameter between the vanishing point coordinates and the driving direction, and to determine the lane offset detection result based on the lane offset parameter and a preset offset parameter threshold. If the lane departure detection result includes lane departure, the determining module is specifically used for at least one of the following: collecting the actual correction angle of the vehicle terminal until the lane departure detection result includes no lane departure, and adjusting the deviation parameter threshold according to the comparison result between the collected actual correction angle and the preset expected warning angle; The actual correction angle of the vehicle terminal is collected until the lane departure detection result includes lane no deviation. The collected actual correction angle is compared with the preset expected warning angle to obtain the expected comparison result. If the number of obtained comparison results is greater than the preset number threshold, the confidence level of the offset parameter threshold is determined according to each expected comparison result. The offset parameter threshold is adjusted according to the comparison result between the confidence level and the preset initial confidence level threshold. The system displays the lane departure detection results to the user and collects user feedback information corresponding to the lane departure detection results. If the user feedback information indicates that the results are incorrect, the system adjusts the lane departure parameter threshold according to a preset adjustment ratio.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 11.

Images