Method and device for recognizing an autonomous lane change

Abstract

The application relates to a lane changing recognition method and device for automatic driving. The method comprises the following steps: fitting a continuous road picture to obtain lane line expression in a target time period; obtaining an initial road picture, and establishing a corresponding relationship between actual lane lines in the initial road picture and lane line expressions; recognizing actual lane lines in the Nth picture according to the corresponding relationship between the actual lane lines in the initial road picture and the lane line expressions; selecting at least one actual lane line, obtaining a first lane line corresponding to the at least one actual lane line in the initial road picture, obtaining an Nth lane line corresponding to the at least one actual lane line in the Nth picture, calculating a displacement difference value between the first actual lane line and the Nth lane line in the same image coordinate system, and judging that lane changing of a vehicle occurs in the case that the displacement difference value meets a preset displacement difference value. The scheme provided by the application can accurately recognize lane changing behavior of an automatic driving vehicle during driving.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a method and device for identifying automatic driving lane change. BACKGROUND

[0002] In the related art, in many advanced auxiliary driving and automatic driving applications such as lane departure warning (LDW) and lane keeping assist (LKA), it is crucial to detect the change of lane lines at all times. Therefore, many camera lane line data are needed to determine whether the automatic driving vehicle changes lanes.

[0003] However, the automatic driving vehicle needs to be equipped with a map required for automatic driving in the process of identifying lane change, and whether the vehicle changes lanes is determined according to real-time road conditions combined with received lane line data. If the map data of the current road conditions is missing in the process of automatic driving, it is not possible to accurately determine whether the vehicle changes lanes, and it is also not possible to determine the direction of the lane change of the vehicle, thereby easily affecting the motion path planning and leading to the failure to achieve the driving assistance function.

[0004] Therefore, the present application provides a method and device for identifying automatic driving lane change, which do not need to rely on map information for automatic driving, and can accurately identify the lane change behavior of the automatic driving vehicle in the process of automatic driving only according to the continuous road pictures received by the automatic driving vehicle. SUMMARY

[0005] To solve or partially solve the problems in the related art, the present application provides a method and device for identifying automatic driving lane change, which can accurately identify the lane change behavior of the automatic driving vehicle in the process of driving.

[0006] The first aspect of the present application provides a method for identifying automatic driving lane change, comprising:

[0007] receiving at least two continuous road pictures in a target time period, the continuous road pictures including an Nth picture currently received, calculating a lane line expression according to the continuous road pictures, the lane line expression being used to represent the actual lane line on the lane in the continuous road pictures;

[0008] obtaining an initialization road picture, identifying the actual lane line in the initialization road picture, and establishing a corresponding relationship between the actual lane line in the initialization road picture and the lane line expression, the initialization road picture being the first road picture in the target time period that meets a preset standard among the continuous road pictures;

[0009] identifying the actual lane line in the Nth picture according to the corresponding relationship between the actual lane line in the initialization road picture and the lane line expression;

[0010] selecting at least one actual lane line, obtaining a first lane line corresponding to the at least one actual lane line of an initial road picture, obtaining an Nth lane line corresponding to the at least one actual lane line of an Nth picture, calculating a displacement difference between the first actual lane line and the Nth lane line under the same image coordinate system, and determining that the vehicle has changed lanes in a case where the displacement difference meets a preset displacement difference.

[0011] Optionally, at least two continuous road pictures are received within a target time period, the continuous road pictures include an Nth picture currently received, and a lane line expression is calculated according to the continuous road pictures, including:

[0012] The continuous road pictures are preprocessed to identify lane lines of the continuous road pictures.

[0013] Anvanish point of intersection of lane lines in each road picture is identified, and the lane lines of the road picture are deleted in a case where a distance between the vanish point of intersection of the lane lines and the lane lines exceeds a first preset range.

[0014] The identified lane lines are fitted to obtain a fitted lane line expression.

[0015] Optionally, an initial road picture is obtained, and actual lane lines in the initial road picture are identified, including:

[0016] A vanish point of intersection of lane lines in the initial road picture is obtained.

[0017] The actual lane lines in the initial road picture are identified according to the lane line expression and the vanish point of intersection of the lane lines, and the actual lane lines in the initial road picture are divided into left lane lines and right lane lines.

[0018] Optionally, a corresponding relationship between the actual lane lines in the initial road picture and the lane line expression is established, including:

[0019] A slope value of the lane line corresponding to the actual lane line in the initial road picture is determined.

[0020] The slope value of the lane line expression corresponding to the actual lane line is obtained.

[0021] The slope value of the lane line in the initial road picture and the slope value of the lane line expression are compared to determine that there is a corresponding relationship between the lane line in the initial road picture and the actual lane line with the smallest slope difference.

[0022] Optionally, the actual lane lines in the Nth picture are identified according to the corresponding relationship between the actual lane lines in the initial road picture and the lane line expression, including:

[0023] Obtaining a slope value difference of lane lines in adjacent road pictures in continuous road pictures, determining a corresponding relationship of the same lane lines in the adjacent road pictures according to the slope value difference of the lane lines in the adjacent road pictures;

[0024] According to the corresponding relationship between the actual lane lines and the lane line expressions in the initialization road pictures and the corresponding relationship of the same lane lines in the adjacent road pictures, a corresponding lane line of the actual lane line in the road pictures is determined, so as to realize tracking the lane line of the same lane line in the road pictures in the continuous road pictures;

[0025] According to the lane line of the actual lane line in the road pictures, the actual lane line in the Nth picture is recognized.

[0026] Optionally, after judging that the vehicle has changed lanes in the case that the displacement difference meets the preset displacement difference, the method further comprises:

[0027] If the coordinate difference is a positive value, a first preset prompt is output, and the first preset prompt is used to indicate that the autonomous vehicle changes lanes to a first direction;

[0028] If the coordinate difference is a negative value, a second preset prompt is output, and the second preset prompt is used to indicate that the autonomous vehicle changes lanes to a second direction.

[0029] Optionally, after judging that the vehicle has changed lanes in the case that the displacement difference meets the preset displacement difference, the method further comprises:

[0030] Obtaining a lane line corresponding to a road fitting equation in the N-1th picture;

[0031] Calculating slopes of the same lane line in the N-1th picture and the Nth picture, and if the slope difference is within a preset difference range, it is judged that the lane changing is ended.

[0032] The second aspect of the present application provides an automatic driving lane changing recognition device, comprising:

[0033] The obtaining module is configured to receive at least two continuous road pictures in a target time period, the continuous road pictures comprising an Nth picture currently received, and calculate a lane line expression according to the continuous road pictures, the lane line expression being used to represent actual lane lines on a lane in the continuous road pictures;

[0034] The first detection module is configured to obtain an initialization road picture, recognize actual lane lines in the initialization road picture, and establish a corresponding relationship between the actual lane lines and the lane line expression in the initialization road picture, the initialization road picture being a first road picture meeting a preset standard in the target time period in the continuous road pictures;

[0035] The second detection module is configured to identify the actual lane line in the Nth picture according to the correspondence between the actual lane line in the initial road picture and the lane line expression.

[0036] The judgment module is configured to select at least one actual lane line, obtain a first lane line corresponding to the at least one actual lane line in the initial road picture, obtain an Nth lane line corresponding to the at least one actual lane line in the Nth picture, calculate a displacement difference between the first actual lane line and the Nth lane line in the same image coordinate system, and determine that the vehicle has changed lanes when the displacement difference meets a preset displacement difference.

[0037] The third aspect of the present application provides an electronic device, comprising:

[0038] a processor; and

[0039] a memory having executable code stored thereon, the executable code, when executed by the processor, causing the processor to perform the method as described above.

[0040] The fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon, the executable code, when executed by a processor of an electronic device, causing the processor to perform the method as described above.

[0041] The technical solution provided by the present application can include the following beneficial effects: The present application does not need to obtain the vehicle condition information of the autonomous vehicle during the driving process, but can analyze the driving road condition of the autonomous vehicle in the target time period by only receiving the continuous road pictures taken by the camera, specifically including: receiving at least two continuous road pictures in the target time period, the continuous road pictures including an Nth picture currently received, and calculating a lane line expression according to the continuous road pictures. That is, the actual lane line is effectively identified by the camera picture.

[0042] The technical solution of the present application can also: determine the lane line position in the initial road picture, compare the positions of the same lane line in the continuous adjacent pictures, thereby obtaining the positions of the same lane line in different pictures, and compare the positions of the same lane line in the current picture and the initial road picture to obtain the lane changing condition of the vehicle, thereby accurately identifying the lane changing behavior of the autonomous vehicle during the driving process. That is, the lane changing condition of the vehicle can be tracked and identified by the camera picture.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0044] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which like reference characters refer to like parts throughout the figures, and in which:

[0045] Figure 1 is a flowchart of a method for identifying automatic driving lane change according to an embodiment of the present application;

[0046] Figure 2 is a flowchart of a method for calculating lane line expression according to an embodiment of the present application;

[0047] Figure 3 is a structural diagram of an apparatus for identifying automatic driving lane change according to an embodiment of the present application;

[0048] Figure 4 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] Embodiments of the present application will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the application are shown. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.

[0050] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0051] It is to be understood that the singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. It is to be further understood that the terms "comprise", "comprising", "comprises", "including", "includes" or "contain" or "containing" when used in this specification, specify the presence of stated features, integers, steps, operations, elements, or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or groups thereof.

[0052] In the related art, in lane departure warning (LDW), lane keeping assist (LKA), and many other advanced auxiliary driving and automatic driving applications, it is crucial to detect the change of lane lines at all times. Therefore, many cameras are needed to capture lane line data to determine whether an autonomous vehicle changes lanes.

[0053] However, an autonomous vehicle needs to be equipped with a map required for autonomous driving in the process of identifying lane changes, and whether the vehicle changes lanes is determined according to real-time road conditions combined with received lane line data. If map data of the current road conditions is missing during autonomous driving, it is not possible to accurately determine whether the vehicle changes lanes, and it is also not possible to determine the direction of the lane change of the vehicle, thereby easily affecting the motion path planning and leading to the failure to achieve the driving assistance function.

[0054] To solve the above problems, the embodiments of the present application provide an identification method for automatic driving lane change, which does not need to rely on map information for autonomous driving, but can accurately identify the lane change behavior of an autonomous vehicle during autonomous driving only according to continuous road pictures received by the autonomous vehicle.

[0055] The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0056] Figure 1 is a flowchart of the identification method for automatic driving lane change shown in the embodiments of the present application.

[0057] Referring to Figure 1 , steps S101 to S104.

[0058] In step S101, at least two continuous road pictures are received within a target time period, the continuous road pictures include an Nth picture currently received, a lane line expression is calculated according to the continuous road pictures, and the lane line expression is used to represent the actual lane line on the lane in the continuous road pictures.

[0059] In step S101, the continuous road pictures can come from video images obtained by a video acquisition device. The video acquisition device installed inside / outside the vehicle can capture video images in front of and behind the vehicle road through a lens at a fixed frame rate, and save the pixel data of the video images in a storage device, so as to facilitate subsequent extraction of data for image detection. The continuous road pictures correspond to corresponding time stamps, and there is a sequence between the continuous road pictures on the time axis.

[0060] As Figure 2 indicated, the lane line expression is calculated according to the continuous road pictures, including:

[0061] Step S201, pre-process the continuous road pictures to identify lane lines of the continuous road pictures.

[0062] In the embodiment, the pre-processing of the Nth picture includes gray processing of the Nth picture, and Gaussian filter denoising of the gray processed picture. Canny edge detection algorithm and Hough line detection algorithm are used to detect the denoised road picture to obtain all the straight lines after denoising.

[0063] The Canny edge detection algorithm identifies lane line edges in the road picture through gradient algorithm. The Hough line detection algorithm further judges the lane lines by performing edge detection on the obtained image and then performing straight line detection on the edge detection by Hough transform. The Hough line detection algorithm is simple and less affected by the gap in the straight line and noise.

[0064] Step S202, identify the vanishing point of intersection of lane lines in each road picture, and if the distance between the vanishing point of intersection of lane lines and the lane lines exceeds a first preset range, delete the lane lines of the road picture.

[0065] In the embodiment, step S202 is mainly used to delete pictures that do not meet the preset conditions to prevent subsequent calculation errors from being too large. Specifically, the step includes: calculating the intersection points between two straight lines; finding the point with the maximum intersection point density within a certain range by performing two clustering algorithms, and defining the point with the maximum intersection point density as the vanishing point of all straight lines. The distance from the vanishing point to each straight line is calculated, and if the distance is higher than a certain threshold, it indicates that the straight line deviates greatly and is removed.

[0066] Step S203, fit the identified lane lines to obtain the fitted lane line expression.

[0067] In the embodiment, fitting the identified lane lines to obtain the fitted lane line expression includes: grouping the straight lines that meet the preset conditions, and grouping the straight lines with similar slopes into a group to determine the actual number of lane lines. The straight lines in each group are averaged to obtain one straight line. The number of groups represents the number of lane lines in the current road picture, and the last fitted straight line in each group represents the lane line expression of the actual lane line. However, the obtained lane line expression can only determine the slope of the actual lane line and the number of actual lane lines. At this time, the lane line expression has not been associated with the specific actual lane line, so the corresponding relationship between the actual lane line and the lane line expression needs to be established in the subsequent process.

[0068] Step S101 obtains lane lines with better image quality by preprocessing the road picture, and the lane line expression obtained by grouping and fitting the lane lines can as accurately as possible represent the number and distribution of actual lane lines, facilitating the establishment of a connection between the lane lines and the lane lines of continuous road pictures. At the same time, the lane line expression in the target time period is obtained, so that the detected lane lines and the actual lane lines can be corresponded in real time and continuously. Alternatively, it can be understood that lane line tracking is a process of continuously obtaining a lane line model. The lane line expression is generally expressed by a linear equation, which can be regarded as an example of the lane line model of the embodiments of the application.

[0069] Step S102 obtains an initialization road picture, identifies actual lane lines in the initialization road picture, and establishes a corresponding relationship between the actual lane lines in the initialization road picture and the lane line expression. The initialization road picture is the first road picture in the target time period that meets the preset standard.

[0070] Step S102 obtains actual lane lines of the initialization road picture without judging the actual lane lines by the lane line expression, and mainly directly obtains the actual lane lines of the initialization road picture by using an image recognition method, so as to establish a corresponding relationship between the actual lane lines and the lane lines of the initialization road picture. Specifically, it includes: obtaining vanishing points of intersection of lane lines in the initialization road picture; identifying actual lane lines in the initialization road picture according to the lane line expression and the vanishing points of intersection of the lane lines, and dividing the actual lane lines in the initialization road picture into left lane lines and right lane lines.

[0071] In an embodiment, when the image recognition method is used to directly obtain the lane lines of the initialization road picture, the lane lines of the initialization road picture can also be judged according to the lane line expression. For example, the number of actual lane lines is judged according to the lane line expression, the left lane lines and the right lane lines are obtained according to the vanishing points of the lane lines and the number of the actual lane lines, and the left lane lines and the right lane lines are numbered.

[0072] In an embodiment, establishing a corresponding relationship between the actual lane lines in the initialization road picture and the lane line expression includes: determining a slope value of the lane line corresponding to the actual lane line in the initialization road picture; obtaining a slope value of the lane line expression corresponding to the actual lane line; and comparing the slope value of the lane line in the initialization road picture and the slope value of the lane line expression to determine that there is a corresponding relationship between the lane line in the initialization road picture and the actual lane line with the smallest slope difference.

[0073] In step S102, the correspondence between the actual lane line expression and the actual lane line in the initialization road picture is established, which helps to associate the obtained actual lane line expression with the actual lane line. For example, in a certain scenario, the obtained lane line expression has six groups, indicating that there are six actual lane lines, and the six lane lines correspond to different slopes. The identified initialization road picture has six lane lines, but the direct identification of the initialization road picture can only simply determine the left lane line and the right lane line. According to the lane line expression and the lane line slope of the initialization road picture, the lane lines in the initialization road picture can be corresponded to the specific actual lane lines, for example, the identified initialization lane lines can include a left first lane line, a left second lane line, a left third lane line, a right first lane line, a right second lane line, and a right third lane line. By establishing the correspondence between the lane line expression and the lane line in the initialization road picture, the specific actual lane line corresponding to the lane line expression is determined, which helps to continuously track the lane line subsequently.

[0074] The lane line expression is generally expressed by a linear equation, which can be regarded as an example of the lane line model of the embodiment of the application. That is, in this lane line tracking method, the lane line tracking is realized by obtaining the lane line expression in the vehicle coordinate system. The above two lane line tracking result output methods can be regarded as a process in which the detected lane line is corresponded to the actual lane line in real time and continuously. Alternatively, it can be understood that the lane line tracking is a process of continuously obtaining the lane line model.

[0075] In step S103, the actual lane line in the Nth picture is identified according to the correspondence between the actual lane line in the initialization road picture and the lane line expression.

[0076] Specifically, in step S103, the slope value difference of the lane line in the adjacent road picture is obtained in the continuous road picture, the correspondence of the same lane line in the adjacent road picture is determined according to the slope value difference of the lane line in the adjacent road, the corresponding lane line of the actual lane line in the road picture is determined according to the correspondence between the actual lane line in the initialization road picture and the lane line expression and the correspondence of the same lane line in the adjacent road picture, so as to realize the tracking of the same lane line in the road picture in the continuous road picture, and the actual lane line in the Nth picture is identified according to the lane line of the actual lane line in the road picture.

[0077] In this embodiment, the left and right lane lines obtained by the initialization are compared with the lane lines in the next picture, the left and right lane lines in the next picture are found out, then the left and right lane lines in the next picture are compared with the lane lines in the picture after the next picture, and the left and right lane lines in the picture after the next picture are found out, and so on.

[0078] In an embodiment scenario, for obtaining a first slope value of an actual lane line in an initialization road picture, a second slope value of a lane line in a next picture of the initialization lane line is obtained, the second slope value is compared with the first slope value, and a corresponding relationship between the next picture and the actual lane line is determined. Similarly, the slope of the next picture of the next picture is compared with the slope of the next picture, and the actual lane line in the initialization road picture is determined. In this way, according to the slope difference between the lane lines of adjacent pictures, the same actual lane line in different pictures can be tracked.

[0079] Lane line tracking is a method for processing obtained lane lines, which can reduce the influence of missed detection and false detection. Lane line detection is equivalent to detecting lane lines in each frame of image, and then corresponding detection results are continuously generated when the vehicle continuously drives forward. However, in actual situations, there may be a situation that a frame or multiple frames of images are not detected or detection errors occur (for example, other lines are detected as lane lines), which may cause the lane lines detected in front and the lane lines detected behind to be unable to correspond or correspond incorrectly. Lane line tracking can be used to correct these errors. The principle of lane line tracking is to abstract lane lines into a mathematical model or a geometric model (for example, the lane line expression in the above), and match the real historical data (for example, the actual lane line in the initialization road picture in the above) with the lane line detected in the current image. If the matching rule is met, it is considered to be the same lane line. In short, lane line tracking can be regarded as a process of continuously identifying the actual lane line of the current road picture, and the actual lane line of the current road picture obtained can be used to correct the errors in lane line detection.

[0080] In step S104, at least one actual lane line is selected, a first lane line corresponding to the at least one actual lane line in an initialization road picture is obtained, an Nth lane line corresponding to the at least one actual lane line in an Nth picture is obtained, a displacement difference between the first actual lane line and the Nth lane line is calculated under the same image coordinate system, and in a case where the displacement difference meets a preset displacement difference, it is determined that the vehicle has changed lanes.

[0081] Step S104, the left and right lane lines found in each picture (possibly only left lane line or right lane line) are compared with the left and right lane lines in the initialization picture respectively, and whether the lane change occurs is judged by the deviation degree of the lane line. The difference between the intersection points of the lane line and the straight line where the lower edge of the picture is located is used as the index to make the judgment. Taking a selected actual lane line as an example, the first lane line of the actual lane line in the initialization road picture is obtained, and the Nth lane line of the actual lane line in the Nth picture is obtained; the same image coordinate system is established, the first intersection point of the first lane line and the bottom edge of the initialization road picture is obtained, and the Nth intersection point of the Nth lane line and the bottom edge of the Nth picture is obtained; the horizontal coordinates of the first intersection point and the Nth intersection point are compared to obtain the displacement difference value between the first intersection point and the Nth intersection point, wherein the displacement difference value is used to represent the deviation difference value of the first lane line and the Nth lane line in the same coordinate system.

[0082] In the case where the displacement difference value meets the preset displacement difference value, it is judged that the vehicle has changed lanes, and the left and right lane lines found in each picture (possibly only left lane line or right lane line) are compared with the left and right lane lines in the initialization road picture respectively, and the lane change direction is judged by the deviation direction of the lane line. The index for judging the deviation direction of the lane line is determined according to the positive and negative values of the displacement difference value.

[0083] In an embodiment, the positive and negative signs of the difference value can be used to judge whether the vehicle is changing lanes to the left or to the right, which specifically includes: if the coordinate difference value is positive, outputting a first preset prompt, the first preset prompt being used to indicate that the autonomous vehicle is changing lanes to a first direction; and if the coordinate difference value is negative, outputting a second preset prompt, the second preset prompt being used to indicate that the autonomous vehicle is changing lanes to a second direction.

[0084] In the present embodiment, the first direction can be the left lane line direction or the right lane line direction, and the second direction is opposite to the first direction along the horizontal straight line direction.

[0085] In an embodiment, in the case where the displacement difference value meets the preset displacement difference value, it is judged that the vehicle has changed lanes, which includes: obtaining the lane line corresponding to the road fitting equation in the N-1th picture; calculating the slope of the same lane line in the N-1th picture and the Nth picture, and if the slope difference value is within the preset difference value range, it is judged that the lane change is over.

[0086] In the present embodiment, whether the lane change is over is judged by judging the positive and negative value changes of the slope of the current left lane or right lane and the slope of the original left lane and right lane, and combining the absolute value of the slope of the current picture left lane or right lane.

[0087] The technical scheme provided in the application can have the following beneficial effects: the application does not need to acquire vehicle condition information of an autonomous vehicle in a driving process, but can analyze driving road conditions of the autonomous vehicle in a target time period by only receiving continuous road pictures shot by a camera, specifically including: receiving at least two continuous road pictures in the target time period, the continuous road pictures including an Nth picture currently received, and calculating lane line expressions according to the continuous road pictures. That is, the actual lane line is effectively identified by the camera pictures.

[0088] The technical scheme of the application can also: determine lane line positions in an initial road picture, compare positions of the same lane line in continuous adjacent pictures, thereby obtaining positions of the same lane line in different pictures, and compare the positions of the same lane line in the current picture and the initial road picture to obtain lane changing conditions of the vehicle, thereby accurately identifying lane changing behaviors of the autonomous vehicle in the driving process. That is, the lane changing conditions of the vehicle can be tracked and identified by the pictures of the camera.

[0089] Corresponding to the foregoing application function implementation method embodiments, the application further provides an automatic driving lane changing identification device, an electronic device, and corresponding embodiments.

[0090] Figure 3 FIG. 1 is a structural schematic diagram of an automatic driving lane changing identification device according to an embodiment of the application.

[0091] Referring to Figure 3 The device includes:

[0092] The obtaining module 301 is configured to receive at least two continuous road pictures in a target time period, the continuous road pictures including an Nth picture currently received, and calculate lane line expressions according to the continuous road pictures, the lane line expressions being used to represent actual lane lines on a lane in the continuous road pictures.

[0093] In an embodiment, the receiving at least two continuous road pictures in the target time period, the continuous road pictures including the Nth picture currently received, and calculating the lane line expressions according to the continuous road pictures include: pre-processing the continuous road pictures to identify lane lines of the continuous road pictures; identifying vanishing points at which lane lines intersect in each road picture, and deleting the lane lines of the road picture if a distance between the vanishing points at which the lane lines intersect and the lane lines exceeds a first preset range; and fitting the identified lane lines to obtain a lane line expression after fitting.

[0094] The first detection module 302 is configured to acquire an initial road picture, identify actual lane lines in the initial road picture, and establish a corresponding relationship between the actual lane lines in the initial road picture and lane line expressions.

[0095] In an embodiment, the acquiring of the initial road picture and the identifying of the actual lane lines in the initial road picture include: acquiring vanishing points of intersection of lane lines in the initial road picture; identifying the actual lane lines in the initial road picture according to the lane line expressions and the vanishing points of intersection of lane lines, and dividing the actual lane lines in the initial road picture into left lane lines and right lane lines.

[0096] In an embodiment, the establishing of the corresponding relationship between the actual lane lines in the initial road picture and the lane line expressions includes: determining slope values of lane lines corresponding to the actual lane lines in the initial road picture; acquiring slope values of the lane line expressions corresponding to the actual lane lines; and comparing the slope values of the lane lines in the initial road picture and the slope values of the lane line expressions to determine that there is a corresponding relationship between the lane line with the minimum slope difference and the actual lane line.

[0097] The second detection module 303 is configured to identify actual lane lines in the Nth picture according to the corresponding relationship between the actual lane lines in the initial road picture and the lane line expressions.

[0098] In an embodiment, the identifying of the actual lane lines in the Nth picture according to the corresponding relationship between the actual lane lines in the initial road picture and the lane line expressions includes: acquiring slope difference values of lane lines in adjacent road pictures in the continuous road pictures, determining corresponding relationships of the same lane lines in the adjacent road pictures according to the slope difference values of the lane lines in the adjacent road pictures; determining lane lines corresponding to the actual lane lines in the road pictures according to the corresponding relationship between the actual lane lines in the initial road picture and the lane line expressions and the corresponding relationships of the same lane lines in the adjacent road pictures, so as to track the lane lines of the same lane lines in the road pictures in the continuous road pictures; and identifying the actual lane lines in the Nth picture according to the lane lines of the actual lane lines in the road pictures.

[0099] The judgment module 304 is configured to select at least one actual lane line, acquire a first lane line corresponding to the at least one actual lane line in the initial road picture, acquire an Nth lane line corresponding to the at least one actual lane line in the Nth picture, calculate a displacement difference value between the first actual lane line and the Nth lane line in the same image coordinate system, and determine that the vehicle has changed lanes when the displacement difference value meets a preset displacement difference value.

[0100] In an embodiment, the device for identifying automatic driving lane change further comprises a first prompting module and a second prompting module, the first prompting module is configured to provide a lane change reminder to the automatic driving vehicle, and the second prompting module is configured to provide a lane change duration to the automatic driving vehicle.

[0101] The first prompting module is configured to determine a lane change direction after the vehicle changes lane when the displacement difference meets a preset displacement difference, and output a first preset prompt if the coordinate difference is positive, and output a second preset prompt if the coordinate difference is negative, wherein the first preset prompt is configured to indicate that the automatic driving vehicle changes lane in a first direction, and the second preset prompt is configured to indicate that the automatic driving vehicle changes lane in a second direction.

[0102] The second prompting module is configured to determine whether the vehicle changes lane after determining the lane change direction of the vehicle, obtain a lane line corresponding to a road fitting equation in the N-1th picture, calculate a slope of the same lane line in the N-1th picture and the Nth picture, and determine that the lane change is ended if a slope difference is within a preset difference range.

[0103] As to the device in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the method, and will not be described in detail here.

[0104] Figure 4 FIG. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application.

[0105] Referring to FIG. 4, Figure 4 The electronic device 400 includes a memory 410 and a processor 420.

[0106] The processor 420 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0107] The memory 410 can include various types of storage units, such as a system memory, a read-only memory (ROM), and a permanent storage device. Among them, the ROM can store static data or instructions required by the processor 420 or other modules of the computer. The permanent storage device can be a read-write storage device. The permanent storage device can be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a mass storage device (such as a magnetic or optical disk, a flash memory) as a permanent storage device. In some other embodiments, the permanent storage device can be a removable storage device (such as a floppy disk, an optical drive). The system memory can be a read-write storage device or a volatile read-write storage device, such as a dynamic random access memory. The system memory can store some or all of the instructions and data required by the processor during runtime. In addition, the memory 410 can include a combination of any computer readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic disks and / or optical disks. In some embodiments, the memory 410 can include a read and / or write removable storage device, such as a compact disc (CD), a read-only digital versatile disc (such as DVD-ROM, double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a min SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer readable storage medium does not include a carrier wave and an instantaneous electronic signal transmitted by wireless or wired transmission.

[0108] The executable code stored on the memory 410 can cause the processor 420 to perform part or all of the above-mentioned methods when the executable code is processed by the processor 420.

[0109] In addition, the method according to the present application can also be implemented as a computer program or computer program product, which includes computer program code instructions for executing part or all of the steps of the above-mentioned methods of the present application.

[0110] Alternatively, the present application can also be implemented as a computer readable storage medium (or non-transitory machine readable storage medium or machine readable storage medium) having executable code (or computer program or computer instruction code) stored thereon, which when executed by a processor of an electronic device (or server, etc.) causes the processor to perform part or all of the steps of the above-mentioned methods according to the present application.

[0111] Having described various embodiments of the application, it is to be understood that the above description is meant not to limit and not to encompass all of the possible embodiments. Many modifications and variations of this application can be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. It is intended that the scope of the application be defined by the scope of the patent and by the claims as allowed by the patent office, which can include adaptations based on the description, equivalents, and / or substitutions of elements individually or collectively to the entire disclosure.

Claims

1. A method for recognizing an automatic driving lane change, characterized by, The application relates to a method for detecting lane changing of a vehicle. The method comprises the following steps: receiving at least two continuous road pictures in a target time period, the continuous road pictures comprising an Nth picture currently received, calculating lane line expressions according to the continuous road pictures, the lane line expressions being used for representing actual lane lines on a lane in the continuous road pictures; obtaining an initialization road picture, identifying actual lane lines in the initialization road picture, and establishing a corresponding relationship between the actual lane lines in the initialization road picture and the lane line expressions, the initialization road picture being a first road picture in the target time period which meets a preset standard among the continuous road pictures; identifying actual lane lines in the Nth picture according to the corresponding relationship between the actual lane lines in the initialization road picture and the lane line expressions; selecting at least one actual lane line, obtaining a first lane line corresponding to the at least one actual lane line in the initialization road picture, obtaining an Nth lane line corresponding to the at least one actual lane line in the Nth picture, calculating a displacement difference value between the first lane line and the Nth lane line in a same image coordinate system, and judging that the vehicle has changed lanes in the case that the displacement difference value meets a preset displacement difference value. The method for receiving at least two continuous road pictures in a target time period, the continuous road pictures comprising an Nth picture currently received, and calculating lane line expressions according to the continuous road pictures comprises the following steps: pre-processing the continuous road pictures, identifying lane lines of the continuous road pictures; identifying vanishing points at which lane lines intersect in each road picture, and deleting the lane lines of the road picture in the case that the distance between the vanishing points at which the lane lines intersect and the lane lines exceeds a first preset range; fitting the identified lane lines, and obtaining fitted lane line expressions. The method for obtaining an initialization road picture and identifying actual lane lines in the initialization road picture comprises the following steps: obtaining vanishing points at which lane lines intersect in the initialization road picture; identifying actual lane lines in the initialization road picture according to the lane line expressions and the vanishing points at which the lane lines intersect, and dividing the actual lane lines in the initialization road picture into left lane lines and right lane lines. The method for establishing a corresponding relationship between actual lane lines in the initialization road picture and the lane line expressions comprises the following steps: determining slope values of lane lines corresponding to the actual lane lines in the initialization road picture; obtaining slope values of the lane line expressions; comparing the slope values of the lane lines in the initialization road picture and the slope values of the lane line expressions, and judging that there is a corresponding relationship between the lane lines in the initialization road picture and the actual lane lines with the smallest slope difference value.

2. The method of claim 1, wherein, The method for identifying actual lane lines in the Nth picture according to the corresponding relationship between the actual lane lines in the initialization road picture and the lane line expressions comprises the following steps: obtaining slope difference values of lane lines in adjacent road pictures in the continuous road pictures, and determining corresponding relationships of the same lane lines in the adjacent road pictures according to the slope difference values of the lane lines in the adjacent road pictures. ​ ​ ​ 3. The method of claim 1, wherein, ​ ​ ​ 4. The method of claim 1, wherein, ​ ​ ​ ​ 5. The method of claim 1, wherein, ​ ​ determine a corresponding lane line of the actual lane line in the road picture according to a corresponding relationship between the actual lane line in the initialization road picture and the lane line expression and a corresponding relationship of the same lane line in adjacent road pictures, so that the same lane line in the continuous road pictures corresponds to a corresponding lane line in the continuous road pictures; determine the actual lane line in the Nth picture according to the lane line of the actual lane line in the continuous road pictures.

6. The method of claim 1, wherein, In a case where the displacement difference value meets a preset displacement difference value, it is determined that the vehicle has changed lanes, and the method further includes: if the coordinate difference value is positive, output a first preset prompt, and the first preset prompt is used to indicate that the vehicle has changed lanes in a first direction; if the coordinate difference value is negative, output a second preset prompt, and the second preset prompt is used to indicate that the vehicle has changed lanes in a second direction.

7. The method of claim 1, wherein, In a case where the displacement difference value meets a preset displacement difference value, it is determined that the vehicle has changed lanes, and the method further includes: obtain a lane line corresponding to a road fitting equation in the (N-1)th picture; calculate a slope of the same lane line in the (N-1)th picture and the Nth picture, and if the slope difference value is within a preset difference value range, it is determined that the lane change is completed.

8. A recognition device for lane changing in autonomous driving, characterized in that, The method further includes: a obtaining module, configured to receive at least two continuous road pictures in a target time period, the continuous road pictures including an Nth picture currently received, and calculate a lane line expression according to the continuous road pictures, the lane line expression being used to represent actual lane lines on lanes in the continuous road pictures; a first detecting module, configured to obtain an initialization road picture, identify actual lane lines in the initialization road picture, and establish a corresponding relationship between the actual lane lines in the initialization road picture and the lane line expression, the initialization road picture being a first road picture meeting a preset standard in the target time period among the continuous road pictures; a second detecting module, configured to identify actual lane lines in the Nth picture according to the corresponding relationship between the actual lane lines in the initialization road picture and the lane line expression; a judging module, configured to select at least one actual lane line, obtain a first lane line corresponding to the at least one actual lane line in the initialization road picture, obtain an Nth lane line corresponding to the at least one actual lane line in the Nth picture, calculate a displacement difference value between the first lane line and the Nth lane line in a same image coordinate system, and determine that the vehicle has changed lanes in a case where the displacement difference value meets a preset displacement difference value.

9. An electronic device, comprising: The method further includes: a processor; and a memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the method of any one of claims 1-7.

10. A computer-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-7.

Images