Assisted driving method, apparatus, device, and medium

Abstract

The present disclosure relates to an assisted driving method, device, equipment and medium. The method includes: expanding the current driving image of the target vehicle to obtain an expanded image; wherein the expanded image includes an expansion area, the expansion area includes a target point, the target point is a position point corresponding to the image acquisition device in the image coordinate system, and the current driving image is captured by the image acquisition device; based on the expanded image, identifying the lane centerline of the lane where the target vehicle is located in the current driving image; based on the extension line of the lane centerline and the target point, determining the deviation value between the target vehicle and the extension line. By obtaining the lane centerline, the influence of the vehicle head occlusion and the field of view angle of the image acquisition device is eliminated, and the deviation value can be obtained without performing an inverse perspective transformation, thereby avoiding the influence of the road curvature and slope on the inverse perspective transformation matrix, improving the accuracy of the judgment of the positional relationship between the vehicle and the lane line of the lane in which it is located, and thus improving the effect of assisted driving.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of autonomous driving, in particular, to an assisted driving method and device, equipment and medium. BACKGROUND

[0002] With the popularity of cars, traffic accidents gradually increase, in order to reduce the occurrence of accidents, the application of assisted driving increases. Assisted driving refers to providing assistance support in the process of driving a vehicle by a driver, so that the driver can drive the vehicle more easily and safely on the road, which can avoid traffic accidents to a certain extent.

[0003] The assisted driving is based on the relative position relationship between the vehicle and the lane line of the lane where the vehicle is located, but the accuracy of obtaining the position relationship in the prior art is poor due to the installation position and angle of the image acquisition device installed on the vehicle, which affects the effect of assisted driving. SUMMARY

[0004] The purpose of the present disclosure is to provide an assisted driving method, device, equipment and medium, which aims to solve the technical problem of poor accuracy of obtaining the distance between the vehicle and the lane line of the lane where the vehicle is located in the prior art.

[0005] To achieve the above purpose, the present disclosure provides an assisted driving method, comprising:

[0006] extending a current driving image of a target vehicle to obtain an extended image, wherein the extended image contains an extended area, the extended area contains a target point, the target point is a position point corresponding to an image acquisition device in an image coordinate system, and the current driving image is captured by the image acquisition device;

[0007] According to the extended image, a lane center line of a lane where the target vehicle is located in the current driving image is identified;

[0008] According to the extension line of the lane center line and the target point, a deviation value of the target vehicle from the extension line is determined.

[0009] Optionally, the extending the current driving image of the target vehicle to obtain the extended image comprises:

[0010] extending the current driving image downward to obtain a blank area with a preset width, and obtaining the extended image, wherein the blank area is the extended area.

[0011] Optionally, the offset value is a corresponding cross-intercept of the extended line in a target coordinate system; and the target coordinate system is a plane rectangular coordinate system with the target point as an origin, or a plane rectangular coordinate system with a point obtained after the target point is calibrated according to the installation position of the image acquisition device as an origin.

[0012] Optionally, the method further comprises:

[0013] According to the expanded image, a lane width value of the lane is identified.

[0014] According to the offset value and the lane width value, it is determined whether the target vehicle deviates from a lane line of the lane in which the target vehicle is located.

[0015] Optionally, the determination whether the target vehicle deviates from the lane line of the lane in which the target vehicle is located according to the offset value and the lane width value comprises:

[0016] A vehicle width value of the target vehicle is obtained.

[0017] If the offset value is greater than an offset threshold value, it is determined that the target vehicle deviates from the lane line; and the offset threshold value is half of a difference between the lane width value and the vehicle width value.

[0018] Optionally, the determination whether the target vehicle deviates from the lane line of the lane in which the target vehicle is located according to the offset value and the lane width value comprises:

[0019] A vehicle width value of the target vehicle is obtained.

[0020] According to the offset value corresponding to the current driving image and the offset value corresponding to each of a plurality of continuous historical driving images before the current driving image, offset rate information corresponding to a plurality of time points of the target vehicle is determined.

[0021] According to the first distance value and the offset rate information, time information of the target vehicle deviating from the lane line is determined; and the first distance value is a difference between half of the lane width value and a second distance value, and the second distance value is a sum of half of the vehicle width value and the offset value corresponding to the current driving image.

[0022] If the time information is less than a preset safety warning time threshold value, it is determined that the target vehicle deviates from the lane line.

[0023] Optionally, the identification of the lane center line of the lane in which the target vehicle is located in the current driving image according to the expanded image comprises:

[0024] identify the extended image to determine lane line feature points of a lane where the target vehicle is located;

[0025] determine a lane center position point according to the lane line feature points;

[0026] fit the lane center position point to obtain a lane center line equation;

[0027] determine the deviation value of the target vehicle from the extension line of the lane center line according to the extension line of the lane center line and the target point, comprising:

[0028] determine a horizontal distance of the target point relative to the lane center line equation to obtain the deviation value.

[0029] In addition, to achieve the above object, the present disclosure further provides an apparatus, comprising:

[0030] an image extension module configured to extend a current driving image of a target vehicle to obtain an extended image, wherein the extended image comprises an extended area, the extended area comprises a target point, the target point is a position point corresponding to an image acquisition device in an image coordinate system, and the current driving image is captured by the image acquisition device;

[0031] a lane center line identification module configured to identify a lane center line of a lane where the target vehicle is located in the current driving image according to the extended image;

[0032] a deviation value determination module configured to determine a deviation value of the target vehicle from an extension line of the lane center line according to the extension line of the lane center line and the target point.

[0033] In addition, to achieve the above object, the present disclosure further provides a non-transitory computer readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the steps of the above method provided by the present disclosure.

[0034] In addition, to achieve the above object, the present disclosure further provides an electronic device, comprising:

[0035] a memory having a computer program stored thereon;

[0036] a processor configured to execute the computer program in the memory to implement the steps of the above method provided by the present disclosure.

[0037] By the technical solution, the lane center line of the lane where the target vehicle is located is recognized and the deviation value is obtained by expanding the current driving image, the relative position relationship between the target vehicle and the lane line can be determined according to the deviation value, and then the relative position relationship is applied to assist driving. By obtaining the lane center line, the influence of the head shielding and the field of view angle of the image acquisition device is eliminated, the accuracy of the deviation value is improved, and the position relationship between the target vehicle and the lane line is truly reflected. At the same time, the deviation value can be obtained without inverse perspective transformation, avoiding the influence of road curvature and slope on the inverse perspective transformation matrix, and improving the accuracy of the deviation value.

[0038] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS

[0039] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, and are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation on the present disclosure. In the drawings:

[0040] Figure 1 It is a driving image schematic diagram in the prior art;

[0041] Figure 2 It is a flowchart of an auxiliary driving method provided by an embodiment of the present disclosure;

[0042] Figure 3 It is an expanded image schematic diagram of an auxiliary driving method provided by an embodiment of the present disclosure (the target vehicle drives along the lane center line);

[0043] Figure 4 It is an expanded image schematic diagram of an auxiliary driving method provided by an embodiment of the present disclosure (the target vehicle drives on the right side of the lane center line);

[0044] Figure 5 It is an expanded image schematic diagram of an auxiliary driving method provided by an embodiment of the present disclosure (the target vehicle drives on the left side of the lane center line);

[0045] Figure 6 It is a functional module schematic diagram of an auxiliary driving device provided by an embodiment of the present disclosure;

[0046] Figure 7 It is a structure schematic diagram of an electronic device related to an embodiment of the present disclosure.

[0047] Explanation of reference signs

[0048] 401, road area; 402, shielding area; 403, expansion area. DETAILED DESCRIPTION

[0049] The detailed description of the specific embodiments of the present disclosure is described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

[0050] In the present disclosure, the orientation words such as "left and right" are determined with the front of the vehicle traveling direction, unless otherwise stated.

[0051] With the popularity of automobiles, traffic accidents gradually increase, in order to reduce the occurrence of accidents, the application of auxiliary driving increases. Auxiliary driving refers to providing auxiliary support in the process of driving the vehicle by the driver, so that the driver can drive the vehicle more easily and safely on the road, and can avoid traffic accidents to a certain extent. Auxiliary driving is based on the relative position relationship between the vehicle and the lane line of the lane where the vehicle is located, but is affected by the installation position and angle of the image acquisition device installed on the vehicle, the accuracy of obtaining the position relationship in the prior art is poor, which affects the effect of auxiliary driving.

[0052] The inventors found that in the prior art, the relative position relationship between the vehicle and the lane line of the lane where the vehicle is located is usually obtained by inversely perspective transforming the lane line in the collected driving image, converting it from the image coordinate system to the world coordinate system, and obtaining the position relationship between the target vehicle and the lane line in the same coordinate system. However, this method is only effective when the road width is fixed or changes slowly, and has large errors when the road has a certain curvature or slope, making it difficult to accurately determine the relative position of the vehicle and the lane line. Further, as shown in Figure 1 Since the existing methods are all based on the driving image information collected by the image acquisition device installed on the front windshield to determine the relative position of the vehicle and the lane line, the actual position of the target vehicle cannot be captured due to the influence of the vehicle head part and the field of view angle of the image acquisition device. The existing method usually obtains the distance d 左 and d 右 However, in the case of driving on a curved road, continuous change of lane width, etc., the lane line distribution information near the target vehicle is blocked by the vehicle head in the driving image, and it is difficult to estimate the actual position of the lane line by extending the edge lines on both sides. Therefore, the distance information obtained is not accurate and cannot truly reflect the position of the target vehicle and the lane line, which affects the effect of auxiliary driving.

[0053] To this end, the present disclosure provides a solution that expands the current driving image, identifies the lane centerline of the target vehicle's lane, and obtains a deviation value. Based on this deviation value, the relative positional relationship between the target vehicle and the lane line can be determined, which can then be applied to assisted driving. By obtaining the lane centerline, the influence of vehicle head occlusion and the field of view of the image acquisition device are eliminated, improving the accuracy of the deviation value and truly reflecting the positional relationship between the target vehicle and the lane line. At the same time, the deviation value can be obtained without performing an inverse perspective transformation, avoiding the influence of road curvature and slope on the inverse perspective transformation matrix, thereby improving the accuracy of the deviation value. Furthermore, by identifying the lane line and obtaining the lane width, the system can adapt to roads of different widths, achieve automatic and accurate measurement of the lane width, and provide vehicle deviation warnings based on the lane width and deviation value.

[0054] Figure 2 This is a flow chart of an assisted driving method provided by an embodiment of the present disclosure. Figure 2 As shown, the method may include the following steps:

[0055] S101: Expand a current driving image of a target vehicle to obtain an expanded image; wherein the expanded image includes an expansion area, the expansion area includes a target point, and the target point is a position point corresponding to an image acquisition device in an image coordinate system, and the current driving image is captured by the image acquisition device.

[0056] In one embodiment of the present disclosure, an image acquisition device is installed on the target vehicle, and the image acquisition device can be a camera or other device for acquiring driving images of the target vehicle. Figures 3 to 5 As shown, according to the content in the driving image, it can be divided into a road area 401 (mainly the road part where the target vehicle is located) and a blocked area 402 (mainly the target vehicle part captured by the image acquisition device, that is, the blocked part of the vehicle head). The target point is the corresponding point of the image acquisition device in the image coordinate system. Figures 3 to 5 In the example, the target point is point O.

[0057] The collected current driving image is expanded to obtain an expanded image, where the expanded portion is an expansion area 403 , and the expansion area 403 includes the target point.

[0058] S102: Identify the center line of the lane where the target vehicle is located in the current driving image based on the expanded image.

[0059] In an embodiment of the present disclosure, the lane center line refers to the central axis of the lane in which the target vehicle is located. The lane line in the expanded image is identified by using an image processing method, and the identified result is processed to obtain the lane center line of the lane line in which the target vehicle is located in the current driving image. Compared with the prior art which needs to obtain the left and right edge lines of the lane line, the lane center line only needs to obtain one line, which is more accurate and can avoid visual errors caused by the installation position of the image acquisition device. In the case of a curved road, the position relationship between the target vehicle and the lane line can be truly reflected, and the accuracy of the auxiliary driving is improved.

[0060] S103: determining the deviation value of the target vehicle from the extension line according to the extension line of the lane center line and the target point.

[0061] In an embodiment of the present disclosure, the lane center line is the dashed line part in Figures 3 to 5 According to the position relationship between the extension line of the lane center line and the target point, the deviation value (distance between the target vehicle and the lane center line) of the target vehicle from the lane center line can be determined, that is, the driving state of the target vehicle. As shown in Figure 3 The extension line (dashed line part) of the lane center line can intersect with the target point O, indicating that the vehicle in the expanded image is driving along the lane center line; as shown in Figure 4 The extension line (dashed line part) of the lane center line is on the left side of the target point O, indicating that the vehicle in the expanded image is driving on the right side of the lane center line; as shown in Figure 5 The extension line (dashed line part) of the lane center line is on the right side of the target point O, indicating that the vehicle in the expanded image is driving on the left side of the lane center line.

[0062] As an optional implementation, S101 can further include: expanding the current driving image downward by a preset width to obtain an expanded image, wherein the blank area is the expansion area.

[0063] In an embodiment of the present disclosure, the downward image expansion is performed on the forward driving image to obtain an expanded image as shown in Figures 3 to 5 The expanded blank area is the expansion area 403, and the expansion width is determined according to the position of the target point, so that the expansion area 403 contains the target point.

[0064] As an optional implementation, the deviation value is the corresponding intercept of the extension line in the target coordinate system; wherein the target coordinate system is a plane rectangular coordinate system with the target point as the origin, or a plane rectangular coordinate system with a point obtained by calibrating the target point according to the installation position of the image acquisition device as the origin.

[0065] In an embodiment of the present disclosure, the point of the image acquisition device in the image coordinate system is a target point. When the image acquisition device is installed in the middle of the vehicle (usually the middle of the bottom edge of the front windshield), as shown in the figure, the target coordinate system is a plane rectangular coordinate system with the target point O as the origin. When the image acquisition device is not installed in the middle of the vehicle, it is calibrated so that the corresponding position after calibration is in the middle of the vehicle, and the point of the corresponding position in the image coordinate system after calibration is the point obtained after calibration of the target point. The target coordinate system is a plane rectangular coordinate system with the point as the origin. Figures 3 to 5

[0066] The deviation value refers to the distance of the target vehicle from the center line of the lane, which is represented in the target coordinate system as the intercept of the extension line of the center line of the lane and the x-axis. In an embodiment, the image acquisition device is installed in the middle of the vehicle, and the target point O is the origin of the target coordinate system. As shown in the figure, in the extended image, the intersection of the extension line and the x-axis is A1, and the intercept is A1O. Since A1 coincides with the origin, the deviation value of the vehicle is 0. As shown in the figure, in the extended image, the intersection of the extension line and the x-axis is A2, and the intercept is A2O. The deviation value of the vehicle is A2O. As shown in the figure, in the extended image, the intersection of the extension line and the x-axis is A3, and the intercept is A3O. The deviation value of the vehicle is A3O. In another embodiment, the image acquisition device is not installed in the middle of the vehicle, and the origin of the target coordinate system is the point obtained after calibration of the target point according to the actual installation position. The deviation value of the vehicle is the intercept of the extension line in the target coordinate system, i.e. the distance between the intersection of the extension line and the x-axis and the origin. Figure 3 Figure 4 Figure 5

[0067] As an optional implementation, S102 can further include: identifying the extended image to determine lane line feature points of the lane where the target vehicle is located; determining a lane center position point according to the lane line feature points; and fitting the lane center position point to obtain a lane center line equation.

[0068] In an embodiment of the present disclosure, a deep learning model is used to identify the features of the lane line of the lane where the target vehicle is located in the extended image to obtain lane line feature points. The deep learning model can improve the accuracy of feature identification and provide an accurate data basis. After obtaining the lane line feature points, the lane center position point can be determined, and the lane center line equation of the lane line can be obtained by fitting the lane center position point.

[0069] For example, the coordinates of the lane center line points can be calculated by the coordinates of the lane line feature points in the image coordinate system, and linear fitting is performed to obtain the lane center line equation in the image coordinate system.

[0070] ​​​​At this time, S103 can further include: determining a horizontal distance of the target point relative to the lane center line equation to obtain the deviation value.

[0071] It can be understood that the deviation value of the target vehicle can be determined according to the horizontal distance of the target point relative to the lane center line equation, that is, the relative position relationship between the target vehicle and the lane line of the lane where the target vehicle is located is determined. Compared with identifying the left and right edge lines of the lane line, obtaining the lane center line only needs to fit a line, which is less affected by environmental factors such as weather and vegetation obstruction, has higher fitting accuracy, and can avoid visual errors caused by head obstruction and installation position of the image acquisition device, especially in the case of turning on a curve, the position relationship between the target vehicle and the lane line where the target vehicle is located can be more truly reflected, and the accuracy of subsequent assisted driving is improved.

[0072] The existing assisted driving system mainly includes a lane keeping assistance system, an automatic parking assistance system, a brake assistance system, a reversing assistance system, and a driving assistance system, wherein the lane keeping assistance system is also called a lane departure warning system. The main function of the lane departure warning system is a safety system that actively issues a warning alarm to the driver when the vehicle is about to or has deviated from the lane line where the vehicle is located, which can greatly reduce the accident rate. Because the accuracy of obtaining the relative position relationship between the vehicle and the lane line of the lane where the vehicle is located in the prior art is poor, the effect of assisted driving is affected, which also affects the accuracy of lane departure warning.

[0073] As an optional implementation, the assisted driving method further includes: identifying a lane width value of the lane according to the expanded image; and determining whether the target vehicle deviates from the lane line of the lane where the target vehicle is located according to the deviation value and the lane width value.

[0074] In an embodiment of the present disclosure, the lane width value is obtained based on the lane line identification result, which can adapt to the width of different roads, realize automatic measurement of the lane width, and improve the accuracy of subsequent deviation warning. For example, a deep learning model is used to identify the features of the lane line of the lane where the target vehicle is located in the expanded image to obtain lane line feature points, and the width of the lane where the target vehicle is located (i.e., the lane width value) is obtained based on the identified lane line feature points.

[0075] The deviation warning value is set according to the lane width value, and when the distance between the target vehicle and the extension line of the lane center line (i.e., the deviation value) exceeds the deviation warning value, it is determined that the target vehicle deviates from the lane line where the target vehicle is located.

[0076] As an optional implementation, the judging whether the target vehicle deviates from the lane line of the lane according to the deviation value and the lane width value comprises: obtaining a vehicle width value of the target vehicle; and judging that the target vehicle deviates from the lane line if the deviation value is greater than a deviation threshold value, wherein the deviation threshold value is half of a difference between the lane width value and the vehicle width value.

[0077] In an embodiment of the present disclosure, the vehicle width of the target vehicle can be obtained by means of vehicle factory information, direct measurement, etc., and the deviation threshold value of the vehicle is set according to the vehicle width value and the lane width value, and the deviation threshold value is half of a difference between the lane width value and the vehicle width value, that is, the deviation threshold value is a deviation value when a left edge line of a lane where a left tire pressure line of the target vehicle is located or a right edge line of a lane where a right tire pressure line of the target vehicle is located, and the target vehicle is judged to deviate from the lane line of the lane when the deviation value is greater than the deviation threshold value.

[0078] In a feasible implementation, the left and right deviation warning lines can be set in combination with the actual situation of the road section where the target vehicle is located, and the deviation threshold value is half of a difference between a width value of the left and right deviation warning lines and the vehicle width value, and the target vehicle is judged to deviate from the lane line of the lane when the deviation value is greater than the deviation threshold value.

[0079] As an optional implementation, the judging whether the target vehicle deviates from the lane line of the lane according to the deviation value and the lane width value comprises: obtaining a vehicle width value of the target vehicle; determining deviation speed information corresponding to a plurality of time points of the target vehicle according to the deviation value corresponding to the current driving image and the deviation value corresponding to each of a plurality of continuous historical driving images before the current driving image; determining time information of the target vehicle deviating from the lane line according to a first distance value and the deviation speed information, wherein the first distance value is a difference between half of the lane width value and a second distance value, and the second distance value is a sum of half of the vehicle width value and the deviation value corresponding to the current driving image; and judging that the target vehicle deviates from the lane line if the time information is less than a preset safety warning time threshold value.

[0080] In an embodiment of the present disclosure, the lateral moving speed of the target vehicle (i.e., the deviation rate information) can be obtained according to the deviation value corresponding to the continuous multiple lane images, and the time (i.e., the time information) required for the target vehicle to deviate from the lane line of the lane in which the target vehicle is located can be obtained according to the lateral moving speed of the target vehicle and the first distance value. In the present embodiment, the first distance value is the difference between half of the lane width value and the second distance value, and the second distance value is the sum of half of the vehicle width value and the deviation value corresponding to the current lane image, i.e., the first distance value is the distance between the left tire of the target vehicle and the left edge line of the lane in which the target vehicle is located or the distance between the right tire of the target vehicle and the right edge line of the lane in which the target vehicle is located, and at this time, the time information is the quotient of the first distance value and the deviation rate information.

[0081] In a feasible implementation, the left and right deviation warning lines can be set according to the actual situation of the road segment in which the target vehicle is located, and at this time, the first distance value is the difference between half of the width value of the two deviation warning lines and the second distance value, and the second distance value is the sum of half of the vehicle width value and the deviation value corresponding to the current lane image, i.e., the first distance value is the distance between the left tire of the target vehicle and the left deviation warning line or the distance between the right tire of the target vehicle and the right deviation warning line of the lane in which the target vehicle is located, and at this time, the time information is the quotient of the first distance value and the deviation rate information.

[0082] According to historical experience data, the earlier the warning time, the more time left for the driver to correct the wrong driving behavior, which can better reduce and prevent the occurrence of traffic accidents, but if the warning time is too early, the vehicle will trigger an alarm when slightly deviating from the middle of the lane, which may cause the deviation warning system to generate false alarms or even interfere with the normal driving of the driver, and therefore the safety warning time threshold should be reasonably set. In the present embodiment, the safety warning time threshold is set to 1.5 seconds according to the earliest warning time required in GB / T 26773-2011, and when the time (i.e., the time information) required for the target vehicle to deviate from the lane line of the lane in which the target vehicle is located is less than 1.5 seconds, it is determined that the target vehicle deviates from the lane line of the lane in which the target vehicle is located.

[0083] Figure 6 A functional module schematic diagram of an auxiliary driving device provided in an embodiment of the present disclosure is shown in FIG. 2. Figure 6 As shown in FIG. 2, the auxiliary driving device 200 can include an image extension module 201, a lane center line recognition module 202, and a deviation value determination module 203.

[0084] The image extension module 201 is configured to extend the current lane image of the target vehicle to obtain an extended image, wherein the extended image includes an extension area, the extension area includes a target point, the target point is a position point corresponding to an image acquisition device in an image coordinate system, and the current lane image is captured by the image acquisition device.

[0085] The lane center line recognition module 202 is configured to recognize, according to the expanded image, a lane center line of a lane in which the target vehicle is located in the current driving image.

[0086] The deviation value determination module 203 is configured to determine, according to the extension line of the lane center line and the target point, a deviation value of the target vehicle from the extension line.

[0087] Optionally, the image expansion module 201 comprises:

[0088] An expansion sub-module, configured to expand the current driving image downward by a preset width to obtain an expanded image, wherein the blank area is used as the expansion area.

[0089] Optionally, the auxiliary driving device 200 further comprises:

[0090] A lane width value recognition module, configured to recognize, according to the expanded image, a lane width value of the lane.

[0091] A deviation judgment module, configured to judge, according to the deviation value and the lane width value, whether the target vehicle deviates from the lane line.

[0092] Optionally, the deviation judgment module comprises:

[0093] A first width value acquisition sub-module, configured to acquire a vehicle width value of the target vehicle.

[0094] A first deviation judgment sub-module, configured to judge that the target vehicle deviates from the lane line if the deviation value is greater than a deviation threshold value, wherein the deviation threshold value is half of a difference between the lane width value and the vehicle width value.

[0095] Optionally, the deviation judgment module further comprises:

[0096] A second width value acquisition sub-module, configured to acquire a vehicle width value of the target vehicle.

[0097] A deviation rate information acquisition sub-module, configured to determine deviation rate information of the target vehicle at multiple time points according to the deviation value corresponding to the current driving image and the deviation value corresponding to each of a plurality of continuous historical driving images before the current driving image.

[0098] A time information acquisition sub-module, configured to determine time information of the target vehicle deviating from the lane line according to a first distance value and the deviation rate information, wherein the first distance value is a difference between half of the lane width value and a second distance value, and the second distance value is a sum of half of the vehicle width value and the deviation value corresponding to the current driving image.

[0099] a second deviation judgment sub-module, configured to judge that the target vehicle deviates from the lane line if the time information is less than a preset safety warning time threshold.

[0100] Optionally, the lane center line identification module 202 comprises:

[0101] a lane line feature point acquisition sub-module, configured to identify the expanded image to determine lane line feature points of a lane in which the target vehicle is located;

[0102] a lane center position point determination sub-module, configured to determine a lane center position point according to the lane line feature points;

[0103] a lane center line acquisition sub-module, configured to fit the lane center position point to obtain a lane center line equation;

[0104] the deviation value determination module 203 comprises:

[0105] a deviation value determination sub-module, configured to determine a horizontal distance of the target point relative to the lane center line equation to obtain the deviation value.

[0106] As to the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

[0107] As can be seen from the above description, the present embodiment can determine the relative position relationship between the target vehicle and the lane line according to the deviation value by expanding the current driving image, identifying the lane center line of the lane in which the target vehicle is located and obtaining the deviation value, and then applying it to assist driving. By obtaining the lane center line, the influence of the head shielding and the field of view angle of the image acquisition device is eliminated, the accuracy of the deviation value is improved, and the position relationship between the target vehicle and the lane line is truly reflected. At the same time, the deviation value can be obtained without inverse perspective transformation, avoiding the influence of road curvature and slope on the inverse perspective transformation matrix, and improving the accuracy of the deviation value. Further, by identifying the lane line to obtain the lane width, the present embodiment can adapt to roads of different widths, realize automatic and accurate measurement of the lane width, and perform vehicle deviation warning according to the lane width and the deviation value.

[0108] Figure 7 A structural schematic diagram of an electronic device related to the embodiments of the present disclosure is shown in FIG. 3. As shown in FIG. 3, the electronic device 300 can include a processor 301 and a memory 302. The electronic device 300 can also include one or more of a multimedia component 303, an input / output (I / O) interface 304, and a communication component 305. For example, the electronic device can be a vehicle. Figure 7

[0109] ​The processor 301 is configured to control overall operations of the electronic device 300 to complete all or part of the steps of the above-mentioned assisted driving method. The memory 302 is configured to store various types of data to support operations of the electronic device 300, which can include, for example, instructions for any application or method operating on the electronic device 300, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 303 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 302 or transmitted through the communication component 305. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 305 is configured to perform wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, and the like, or a combination of one or more of them, is not limited herein. Therefore, the corresponding communication component 305 can include a Wi-Fi module, a Bluetooth module, an NFC module, and the like.

[0110] In some embodiments, the electronic device 300 can be implemented by one or more Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor or other electronic elements for executing the above-mentioned assisted driving method.

[0111] In addition, in an embodiment, the embodiments of the present disclosure also provide a computer-readable storage medium including program instructions, which, when executed by a processor, implement the steps of the above-mentioned assisted driving method. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, and the above-mentioned program instructions can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned assisted driving method.

[0112] In addition, in an embodiment, the embodiments of the present disclosure also provide a computer program product, which can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned assisted driving method when executed by the programmable device.

[0113] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Within the technical concept range of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all belong to the protection range of the present disclosure.

[0114] In addition, it should be noted that each specific technical feature described in the above-described specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0115] In addition, any combination of various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, and it should also be considered as the disclosed content of the present disclosure.

Claims

1. A driving assistance method, characterized in that: include: Expanding a current driving image of the target vehicle to obtain an expanded image; wherein the expanded image includes an expansion area, the expansion area includes a target point, and the target point is a position point corresponding to the image acquisition device in an image coordinate system, and the current driving image is captured by the image acquisition device; identifying, based on the expanded image, a lane centerline of a lane where the target vehicle is located in the current driving image; Determining a deviation value between the target vehicle and the extension line based on the extension line of the lane centerline and the target point; identifying a lane width value of the lane according to the expanded image; Obtaining a vehicle width value of the target vehicle; Determining deviation rate information corresponding to the target vehicle at multiple moments based on the deviation value corresponding to the current driving image and the deviation value corresponding to each frame of a plurality of consecutive frames of historical driving images preceding the current driving image; Determining the time information of the target vehicle deviating from the lane line based on a first distance value and the deviation rate information; wherein the first distance value is the difference between half the lane width value and a second distance value, and the second distance value is the sum of half the vehicle width value and the deviation value corresponding to the current driving image; If the time information is less than a preset safety warning time threshold, it is determined that the target vehicle has deviated from the lane line.

2. The assisted driving method according to claim 1, characterized in that: The step of expanding the current driving image of the target vehicle to obtain the expanded image includes: The current driving image is expanded downward to obtain a blank area of ​​a preset width to obtain an expanded image, wherein the blank area serves as the expanded area.

3. The assisted driving method according to claim 1, characterized in that: The deviation value is the corresponding transverse intercept of the extension line in the target coordinate system; wherein, the target coordinate system is a plane rectangular coordinate system with the target point as the origin, or a plane rectangular coordinate system with the point obtained after calibrating the target point according to the installation position of the image acquisition device as the origin.

4. The assisted driving method according to claim 1, characterized in that: The determining, based on the deviation value and the lane width value, whether the target vehicle deviates from the lane line of the lane in which the target vehicle is located includes: Obtaining a vehicle width value of the target vehicle; If the deviation value is greater than a deviation threshold, it is determined that the target vehicle has deviated from the lane line; wherein the deviation threshold is half of the difference between the lane width value and the vehicle width value.

5. The assisted driving method according to claim 1, characterized in that: The step of identifying, based on the expanded image, a lane centerline of a lane where the target vehicle is located in the current driving image includes: Recognizing the expanded image to determine lane line feature points of the lane where the target vehicle is located; Determine the lane center point based on the lane line feature points; Fitting the lane center position point to obtain a lane centerline equation; Determining a deviation value between the target vehicle and the extension line according to the extension line of the lane center line and the target point includes: The horizontal distance of the target point relative to the lane centerline equation is determined to obtain the deviation value.

6. A driving assistance device, characterized in that: include: an image expansion module, configured to expand a current driving image of a target vehicle to obtain an expanded image; wherein the expanded image includes an expansion area, the expansion area includes a target point, and the target point is a position point corresponding to the image acquisition device in the image coordinate system, and the current driving image is captured by the image acquisition device; a lane centerline recognition module, configured to recognize, based on the expanded image, a lane centerline of the lane where the target vehicle is located in the current driving image; a deviation value determining module, configured to determine a deviation value between the target vehicle and the extension line based on the extension line of the lane center line and the target point; a lane width value recognition module, configured to recognize a lane width value of the lane according to the expanded image; A deviation judgment module is used to obtain the vehicle width value of the target vehicle; determine the deviation rate information corresponding to the target vehicle at multiple moments based on the deviation value corresponding to the current driving image and the deviation value corresponding to each frame of the multiple consecutive frames of historical driving images before the current driving image; determine the time information of the target vehicle deviating from the lane line based on the first distance value and the deviation rate information; wherein the first distance value is the difference between half of the lane width value and the second distance value, and the second distance value is the sum of half of the vehicle width value and the deviation value corresponding to the current driving image; if the time information is less than a preset safety warning time threshold, it is determined that the target vehicle has deviated from the lane line.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.

Images