Travel path generation method and device, computer device, and storage medium

Abstract

The application relates to a driving path generation method and device, computer equipment and a storage medium, wherein the method comprises the following steps: determining a first lane line of a current lane where a vehicle is located, and determining a second lane line of a target lane where the vehicle is to be driven into; constructing a virtual lane line based on the first lane line and the second lane line; and generating a driving path of the vehicle based on the virtual lane line. By adopting the scheme of the application, the driving path of the vehicle meeting the lateral control requirements can be generated in the road condition with a large lateral displacement range before and after the lane line, and good intelligent driving experience can be provided for the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, and in particular to a driving path generation method and device, a computer device, and a storage medium. BACKGROUND

[0002] At present, an intelligent driving assistance system of a vehicle has a high-order lateral and longitudinal assistance control function. During vehicle driving, the intelligent driving assistance system detects lane lines on both sides of a lane of the vehicle in real time through a vehicle-mounted high-definition camera, and plans a driving path according to the lane lines, so that the vehicle is kept from driving in the middle and lateral assistance control of the vehicle is realized.

[0003] However, in the lateral assistance control of the vehicle, a too large lateral deviation amplitude may cause a risk of losing control of the vehicle, and has a large safety hazard. In related technologies, a driver usually manually drives the vehicle and the like to ensure the safety of the vehicle during lateral deviation, which greatly affects the driving experience of a user. SUMMARY

[0004] Embodiments of the present application provide a driving path generation method and device, a computer device, and a storage medium, which can plan a driving path under road conditions in which lane lines have a large misalignment amplitude, to at least partially solve the above technical problems.

[0005] To achieve the above object, according to a first aspect of the present application, a driving path generation method is provided, and the method comprises:

[0006] determining a first lane line of a current lane in which a vehicle is located, and determining a second lane line of a target lane into which the vehicle is to be driven;

[0007] constructing a virtual lane line based on the first lane line and the second lane line;

[0008] generating a driving path of the vehicle based on the virtual lane line.

[0009] According to a second aspect of the present application, a driving path generation device is provided, and the device comprises:

[0010] a determination module configured to determine a first lane line of a current lane in which a vehicle is located, and determine a second lane line of a target lane into which the vehicle is to be driven;

[0011] a construction module configured to construct a virtual lane line based on the first lane line and the second lane line;

[0012] a generation module configured to generate a driving path of the vehicle based on the virtual lane line.

[0013] According to a third aspect of the present application, a computer device is provided, comprising a processor and a memory, the memory storing a plurality of instructions; the processor loads the instructions from the memory to perform the steps of the driving path generation method according to the first aspect.

[0014] According to a fourth aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium storing a plurality of instructions, the instructions being adapted to be loaded by a processor to perform the steps of the driving path generation method according to the first aspect.

[0015] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program or instructions, the computer program or instructions being executed by a processor to implement the steps of the driving path generation method according to the first aspect.

[0016] The driving path generation method, device, computer device and storage medium according to the embodiments of the present application can determine the first lane line of the current lane where the vehicle is located and the second lane line of the target lane where the vehicle is going to enter, and thus determine the start position and end position of path planning of the vehicle in the road condition where the lane lines have a misalignment amplitude. Thus, based on the first lane line and the second lane line, a virtual lane line is constructed, which can maintain intelligent driving assistance or automatic driving of the vehicle in the case where the lane lines on both sides of the lane where the vehicle is located temporarily disappear or the front and rear lane lines have a large lateral misalignment amplitude, without the need for the user to take over the steering wheel and manually drive, thereby avoiding the safety hazard caused by the user not taking over the steering wheel in time. The driving path of the vehicle is generated based on the virtual lane line, which can timely perform path planning based on the virtual lane line, so as to correctly control the driving direction of the vehicle without exiting the lateral assistance function in the intelligent driving function, thereby achieving smooth transition of the vehicle from the current lane to the target lane in the road condition where the lane lines have a misalignment amplitude, and improving the user experience of intelligent driving.

[0017] Other features and advantages of the present application will be described in detail in the following detailed description. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0019] In order to more completely understand the present application and its beneficial effects, the following will be described in conjunction with the drawings, wherein the same reference numerals in the following description represent the same parts.

[0020] Figure 1is a top view schematic diagram of a traffic distribution provided by some embodiments of the present application;

[0021] Figure 2 is a schematic diagram of an application scenario of a driving path generation method provided by some embodiments of the present application;

[0022] Figure 3 is a flowchart of a driving path generation method provided by some embodiments of the present application;

[0023] Figure 4 is a schematic diagram of an image coordinate system provided by some embodiments of the present application;

[0024] Figure 5 is a schematic diagram of a virtual lane line provided by some embodiments of the present application;

[0025] Figure 6 is a schematic diagram of a virtual lane line and a driving path provided by some embodiments of the present application;

[0026] Figure 7 is a schematic diagram of a principle of constructing a virtual lane line provided by some embodiments of the present application;

[0027] Figure 8 is a schematic diagram of a principle of determining a segmentation point provided by some embodiments of the present application;

[0028] Figure 9 is a schematic diagram of a scenario of a driving area provided by some embodiments of the present application;

[0029] Figure 10 is a flowchart of steps performed by a lane line information extraction module and a vehicle driving path planning module respectively provided by some embodiments of the present application;

[0030] Figure 11 is a structural schematic diagram of a driving path generation apparatus provided by some embodiments of the present application;

[0031] Figure 12 is a structural schematic diagram of a computer device provided by some embodiments of the present application. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, any other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the protection scope of the present application.

[0033] In the description of the present application, the terms "first", "second" are only used for descriptive purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0034] At present, the intelligent driving assistance system of the automobile has been more and more widely applied. The intelligent driving assistance can detect the lane lines on both sides of the vehicle lane in real time through the vehicle-mounted high-definition camera during the vehicle driving process, and plan the driving path accordingly, so that the ego vehicle keeps driving in the middle, and realizes the lateral auxiliary control of the vehicle. During the vehicle driving process, the vehicle often encounters the split flow road conditions, such as Figure 1 As shown in the figure. Under this lane line split flow road condition, the lane lines on both sides will be temporarily lost, and the lane lines before and after the split flow have a large dislocation amplitude, which causes the intelligent driving assistance system to be unable to control the vehicle correctly. In this case, the prior art mostly adopts the same processing method as the intersection, that is, by exiting the intelligent driving lateral auxiliary function, using various alarm methods such as vision and sound to remind the user to take over the vehicle to solve the problem. Therefore, under the split flow road condition with a large dislocation amplitude of the lane line, the prior art does not consider planning the vehicle driving path according to the lane line information before and after the split flow, but directly exits the intelligent driving lateral auxiliary function, which easily causes the vehicle to deviate from the driving path when the user does not take over the steering wheel in time, thereby increasing the driving risk coefficient and affecting the driving safety. In addition, for the road with more lane line split flow road conditions, the frequent exit of the intelligent driving assistance function will greatly affect the continuity of the function operation, and cannot meet the intelligent driving needs of the user; at the same time of the frequent exit of the auxiliary function, the system reminding the user to take over the vehicle through various alarm methods also greatly affects the driving experience of the user.

[0035] In view of this, the embodiments of the present application provide a driving path generation method, device, system, equipment and storage medium, aiming at the road condition with a lateral displacement amplitude before and after the lane line, when the vehicle-mounted camera and other camera devices on the vehicle recognize the road condition, extracting the front and rear lane line information and further constructing a virtual lane line, so that the intelligent driving assistance system can timely plan the path based on the virtual lane line, thereby correctly controlling the driving direction of the vehicle without exiting the lateral assistance function, realizing the smooth transition of the vehicle under the road condition with the lateral displacement amplitude of the lane line, and improving the user's experience of intelligent driving. Compared with the prior art, the driving path generation method provided by the embodiments of the present application is proposed for the lane line road condition with a large lateral displacement amplitude before and after, which can effectively solve the problem of frequent exit of the intelligent driving assistance function under this kind of road condition, and is helpful to improve the intelligent driving experience of the driver; and the driving path generation method provided by the present application has small computing power requirement, simple process, high algorithm robustness and environmental adaptability, and can be applied to various types of lane line split road conditions and lane changing scenes.

[0036] Among them, the road condition with lane line having a lateral displacement amplitude at least includes two scenes: lane line split scene and lane changing scene. Under the above road condition, the front and rear lane lines have a certain degree of displacement amplitude in the lateral direction (with the vehicle driving direction as the vertical direction, and the lateral direction as the direction perpendicular to the vertical direction). In addition, under the above road condition, the front and rear lane lines can have a certain distance in the vertical direction.

[0037] In some embodiments, referring to Figure 2 , the embodiments of the present application can be applied to the application scenario as Figure 2 indicated. Figure 2 The application scenario as indicated can be a split road condition scene, or a lane changing scene. It should be noted that Figure 2 the number of front and rear lanes in the road scene as indicated in the above is only an example, and in the split scene and lane changing scene to which the embodiments of the present application are applied, the number of lanes before and after the split / lane changing can be the same or different, which is not limited by the present application.

[0038] Among them, the terminal device 202 can be a device including receiving and transmitting hardware, i.e. a device with receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. The terminal device 202 and the server 204 can perform bidirectional communication through a network. The terminal device 202 can also perform bidirectional communication with the vehicle through the network.

[0039] Exemplarily, the terminal device 202 can acquire an image captured by a camera of the vehicle, and obtain a road top view by processing. Alternatively, the terminal device 202 can also acquire a road top view and the like sent by the server 204. The terminal device 202 can determine a first lane line of a current lane where the vehicle is located, and determine a second lane line of a target lane where the vehicle is going to enter, and then construct a virtual lane line based on the first lane line and the second lane line, and finally generate a driving path of the vehicle based on the virtual lane line. Alternatively, the above steps can also be performed by the server 204, and the server 204 sends the driving path to the terminal device 202, and the terminal device 202 controls the vehicle to drive according to the driving path, and the like.

[0040] The terminal device includes but is not limited to one or more of a mobile phone, a computer, an Internet of Things device, a vehicle-mounted terminal, and a portable wearable device, and the like. The Internet of Things device can be a smart vehicle-mounted device, and the like. The portable wearable device can be one or more of a smart watch, a smart bracelet, smart glasses, a head-mounted device, and the like.

[0041] The server can be a stand-alone server, or a server network, a server cluster, or a distributed system composed of multiple servers. The server includes but is not limited to a computer, a network host, a single network server, a plurality of network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0042] The vehicle can be a fuel automobile, a plug-in hybrid electric vehicle, or a new energy vehicle, and the like, which are not limited in the present application.

[0043] The following will be described in detail with reference to the accompanying drawings. It should be noted that the sequence of the following embodiments is not limited as the preferred sequence of the embodiments. Although a logical sequence is shown in the flowchart, in some cases, the steps shown or described can be performed in an order different from that shown in the accompanying drawings.

[0044] Referring to Figure 3 , a driving path generation method is provided, which is applied to a computer device. The computer device can be a terminal device or a server. The method includes:

[0045] In step S301, a first lane line of a current lane where the vehicle is located is determined, and a second lane line of a target lane where the vehicle is going to enter is determined.

[0046] As mentioned above, the embodiments of the present application can be applied in split-flow road conditions and lane-changing scenarios. Taking the split-flow road condition as an example, in some embodiments, the computer device determines a first lane line of a current lane where the vehicle is located before splitting, and determines a second lane line of a target lane where the vehicle will enter after splitting. Specifically, the computer device determines whether it belongs to a split-flow road condition. One of the characteristics of the split-flow road condition is that the lane line is disconnected in the longitudinal direction and has a misalignment in the transverse direction. In the split-flow road condition, the computer device determines the lane where the vehicle is located before splitting, i.e., the current lane, and the lane where the vehicle will enter after splitting, i.e., the target lane. Further, the computer device extracts the lane line of the current lane as the first lane line, and extracts the second lane line of the target lane as the second lane line.

[0047] In some embodiments, the computer device can extract the first lane line and the second lane line according to the image collected by the vehicle or the road facility device. In some embodiments, the computer device further performs image processing such as size adjustment, noise reduction filtering, binarization processing, coordinate system mapping, etc. on the image to highlight the lane line information.

[0048] For example, the computer device can extract the lane line from the road surface monitoring image collected by the vehicle or the road facility device, and further distinguish the first lane line and the second lane line. Illustratively, the computer device obtains a road surface top view and determines the first lane line and the second lane line in the road surface top view. The road surface top view is a road surface image in a top-down perspective, for example, as shown in FIG. 6. Figure 1 Illustratively, the computer device can obtain the road surface image collected by the vehicle and generate the road surface top view through inverse perspective mapping, etc.

[0049] In some embodiments, the computer device can obtain the road surface top view by: obtaining a driving monitoring image collected by a shooting device of the vehicle; and converting the driving monitoring image into the road surface top view based on a preset coordinate system mapping relationship. The preset coordinate system mapping relationship may, for example, be a mapping relationship between a coordinate system of a real physical world and an image coordinate system, etc.

[0050] In other embodiments, the computer device can further obtain point cloud data and determine the first lane line and the second lane line according to the point cloud data. For example, the point cloud data belonging to the lane line is extracted from the point cloud data, and the first lane line and the second lane line are further extracted, etc.

[0051] For the sake of simplicity and ease of understanding, the following will be described by taking image processing as an example.

[0052] Road surface plan view It should be noted that, for the sake of description simplicity, the longitudinal direction referred to in the embodiments of the present application refers to the Y-axis direction of the image coordinate system, and the transverse direction refers to the X-axis direction of the image coordinate system. Exemplarily, the X-axis and Y-axis directions of the image coordinate system are as shown in FIG. 8, and the upper left corner of the image is taken as the coordinate axis origin. Figure 4

[0053] Therefore, the computer device can extract all lane lines in the image, and determine whether the vehicle is currently in a split road condition according to the distance characteristics between the lane lines in the image.

[0054] If yes, the computer device determines a first lane line of a current lane where the vehicle is located before splitting, and a second lane line of a target lane where the vehicle is going to enter after splitting. The current lane where the vehicle is located before splitting can be the lane lines located on both sides of the vehicle in the image. The target lane where the vehicle is going to enter after splitting can be determined automatically by the computer device or manually set by the user.

[0055] In some embodiments, the computer device determines the lane line with the minimum transverse distance, i.e., the distance in the X-axis direction, between the lane line after splitting and the lane line of the current lane, as the lane line of the target lane.

[0056] The computer device can construct a virtual lane line through the lane lines located on the same side of the lane, for example, the computer device can take the left lane line of the current lane as the first lane line, and take the left lane line of the target lane as the second lane line; or the computer device takes the right lane line of the current lane as the first lane line, and takes the right lane line of the target lane as the second lane line.

[0057] In other embodiments, the computer device can take the left lane line and the right lane line of the current lane as the first lane line, and take the left lane line and the right lane line of the target lane as the second lane line. It is easy to understand that when the determined lane line includes the left lane line and the right lane line, the first left lane line corresponds to the second left lane line, and the first right lane line corresponds to the second right lane line, thereby generating smooth virtual lane lines on both sides.

[0058] In step S302, a virtual lane line is constructed based on the first lane line and the second lane line.

[0059] Specifically, the computer device constructs a virtual lane line based on the first lane line of the current lane and the second lane line of the target lane, so that the computer device can timely plan a path based on the virtual lane line, thereby correctly controlling the driving direction of the vehicle and realizing smooth transition of the vehicle in the split road condition.

[0060] ​When the first lane line and the second lane line are both lane lines on the left side of the lane, the constructed virtual lane line is also a left side lane line of the virtual lane, as shown in Fig. (a) of Figure 5 When the first lane line and the second lane line are both lane lines on the right side of the lane, the constructed virtual lane line is also a right side lane line of the virtual lane, as shown in Fig. (b) of Figure 5 When the first lane line and the second lane line both include left and right lane lines, the constructed virtual lane line also includes left and right side lane lines of the virtual lane, as shown in Fig. (c) of Figure 5

[0061] Step S303: generating a driving path of the vehicle based on the virtual lane line.

[0062] Specifically, the computer device plans a driving path based on the generated virtual lane line, so that the vehicle drives along the driving path, thereby achieving smooth transition from the current lane to the target lane under the split road condition, avoiding the situation that the vehicle exits the intelligent driving function due to excessive lateral deviation, and the resulting safety hazards.

[0063] In some embodiments, the computer device can generate a virtual lane line along the virtual lane line and at a preset distance from the virtual lane line. When the virtual lane line includes left and right side lane lines, i.e., two virtual lane lines as shown in Fig. (c) of Figure 5 The computer device can generate a driving path in the middle of the two virtual lane lines, as shown in Fig. (c) of Figure 6 The vehicle drives along the driving path represented by the arrowed solid line, and the distance between the driving path and the left and right virtual lane lines in the X-axis direction is equal, thereby ensuring that the vehicle is inside the virtual lane line and ensuring the safe driving distance of the vehicle from other lanes and other vehicles.

[0064] ​The driving path generation method of the embodiment of the present application can determine the starting position and the end position of the path planning of the vehicle under the split flow road condition by determining the first lane line of the current lane where the vehicle is located before the split flow and determining the second lane line of the target lane where the vehicle will enter after the split flow. Thus, based on the first lane line and the second lane line, the virtual lane line is constructed, which can keep the intelligent driving assistance or automatic driving of the vehicle under the condition that the lane lines on both sides of the lane where the vehicle is located temporarily disappear or the front and rear lane lines have a large dislocation range in the split flow road condition, without the need for the user to take over the steering wheel and manually drive, and the driving path of the vehicle is generated based on the virtual lane line, which can timely plan the path based on the virtual lane line, so as to correctly control the driving direction of the vehicle without exiting the lateral assistance function in the intelligent driving function, realize the smooth transition of the vehicle from the lane before the split flow to the lane after the split flow under the split flow road condition, effectively solve the problem of frequent exit of the intelligent driving assistance function on the road with many lane line split flow road conditions, and improve the experience of the user in intelligent driving. Moreover, the driving path generation method of the embodiment of the present application has small computing power requirement, simple process, high algorithm robustness and environmental adaptability, and can be applied to various types of lane line split flow road conditions.

[0065] Since the lane lines of the lanes before and after the split flow have dislocation under the split flow road condition, if the virtual lane line is directly connected to the lanes before and after the split flow, it will cause the lateral deviation of the vehicle in the driving process to be too large, which exists serious safety hazards. Therefore, in some embodiments, based on the first lane line and the second lane line, the virtual lane line is constructed, including: determining a first tangent point on the first lane line and a second tangent point on the second lane line; wherein the first lane line belongs to the current lane where the vehicle is located before the split flow, and the second lane line belongs to the target lane where the vehicle will enter after the split flow; constructing a first virtual lane line based on the first tangent point and constructing a second virtual lane line based on the second tangent point; and constructing the virtual lane line based on the first virtual lane line and the second virtual lane line.

[0066] Specifically, the computer device determines a first tangent point on the first lane line and a second tangent point on the second lane line. The first tangent point is at least a certain distance away from the end point of the first lane line, and the second tangent point is at least a certain distance away from the start point of the second lane line, and the distances can be equal or not equal.

[0067] Thus, the computer device can construct a first virtual lane line based on the first tangent point and construct a second virtual lane line based on the second tangent point. The computer device can connect the first virtual lane line and the second virtual lane line to construct the virtual lane line.

[0068] In the above embodiment, the two-segment fitting method is used to construct the virtual lane line in the flow splitting process, so that the generated virtual lane line can ensure smooth driving of the vehicle, meet the lateral control requirements of the vehicle, and avoid safety hazards caused by excessive lateral deviation of the vehicle during driving.

[0069] In some embodiments, the first lane line includes a first left lane line and a first right lane line, and the second lane line includes a second left lane line and a second right lane line, the first intersection point includes a first left intersection point on the first left lane line and a first right intersection point on the first right lane line, and the second intersection point includes a second left intersection point on the second left lane line and a second right intersection point on the second right lane line.

[0070] Therefore, the first virtual lane line includes a first virtual left lane line constructed based on the first left intersection point and a first virtual right lane line constructed based on the first right intersection point, and the second virtual lane line includes a second virtual left lane line constructed based on the second left intersection point and a second virtual right lane line constructed based on the second right intersection point. Further, based on the first virtual lane line and the second virtual lane line, the virtual lane line is constructed, including connecting the first virtual left lane line and the second virtual left lane line to generate a virtual left lane line, connecting the first virtual right lane line and the second virtual right lane line to generate a virtual right lane line, and constructing the virtual lane line based on the virtual left lane line and the virtual right lane line.

[0071] In the above embodiment, the two-segment fitting method is used to construct the virtual lane line in the flow splitting process, and the virtual lane lines on the left and right sides of the lane are constructed respectively. The virtual lane lines on the left and right sides can form a complete virtual lane, and the driving path can be planned in the virtual lane, which can make the driving path more accurate, ensure smooth driving of the vehicle, meet the lateral control requirements of the vehicle, and avoid safety hazards caused by excessive lateral deviation of the vehicle during driving.

[0072] In some embodiments, the first intersection point on the first lane line and the second intersection point on the second lane line are determined, including determining a termination point of the first lane line and a starting point of the second lane line, and determining, on the first lane line, a point at a first preset distance from the termination point as the first intersection point, and determining, on the second lane line, a point at a second preset distance from the starting point as the second intersection point.

[0073] Specifically, the computer device takes the end point of the first lane line at the flow splitting point as the termination point, which represents the disconnection of the lane line before the flow splitting, and takes the starting point of the second lane line at the flow splitting point as the starting point, which represents the start of the lane line after the flow splitting.

[0074] Thus, the computer device determines a point on the first lane line, which is a distance interval of a first preset value from the end point, as a first tangent point; and determines a point on the second lane line, which is a distance interval of a second preset value from the start point, as a second tangent point. The first preset value and the second preset value can be equal or different.

[0075] In the above embodiments, by selecting the points at a distance interval from the breakpoints of the lane lines before and after the split as the tangent points, the generated virtual lane line can have a certain extension in the longitudinal direction, and the offset amplitude of the driving path generated based on the virtual lane line in the transverse direction can meet the lateral control requirements of the vehicle, thereby avoiding safety hazards caused by excessive lateral offset.

[0076] In some embodiments, constructing the first virtual lane line based on the first tangent point includes: determining a first virtual auxiliary line based on the first tangent point and a lane line equation corresponding to the first lane line; determining a split point, and determining a second virtual auxiliary line based on the split point and the first tangent point; and constructing the first virtual lane line based on the first virtual auxiliary line and the second virtual auxiliary line.

[0077] Specifically, the computer device determines a lane line equation corresponding to the first lane line when determining the first lane line. For example, the computer device can generate the lane line equation corresponding to the first lane line by a lane line fitting method. The lane line fitting method includes but is not limited to a least square method based on a hyperbolic model, an image processing method based on edge detection and transformation, a lane line fitting based on a fitting function and a residual function, etc., which are not limited in the present application.

[0078] In addition, the computer device also determines a split point. Since the driving path of the vehicle is usually in an "S" shape when changing lanes, the curve turning point in the middle of the "S" shape is the split point of the virtual lane line. The computer device can determine the split point when extracting the lane line.

[0079] The computer device generates a first virtual auxiliary line according to the first tangent point and the lane line equation corresponding to the first lane line, and generates a second virtual auxiliary line according to the determined split point of the virtual lane point. Thus, according to the first virtual auxiliary line and the second virtual auxiliary line, a virtual circle tangent to the first tangent point can be determined, and the line segment between the first tangent point and the split point on the virtual circle is the first virtual lane line.

[0080] For example, as shown in FIG. 4, the computer device determines a first tangent point A on the first lane line, and a second tangent point B on the second lane line. The computer device determines a first virtual auxiliary line A1 passing through the first tangent point A and a second virtual auxiliary line B1 passing through the second tangent point B. Figure 7As shown, the computer device determines the equation of the tangent line of the first lane arc on the left at the tangent point based on the first tangent point of the first lane line and its lane line equation, thereby obtaining the perpendicular line L1 passing through the center O, which is the first virtual auxiliary line; and, based on the dividing point and the first tangent point, the computer device can obtain the perpendicular bisector L2 of the line connecting the dividing point and the first tangent point, which is the second virtual auxiliary line. Thus, the intersection of L1 and L2 is the center O of the first virtual lane arc on the left. The arc segment of the circle with the center O and the distance between the center O and the first tangent point as its radius between the first tangent point and the dividing point is the first virtual lane line on the left, which is the first virtual lane line.

[0081] It is easy to understand that, similar to the above embodiments, constructing a second virtual lane line based on the second tangent point includes: determining a third virtual auxiliary line based on the second tangent point and the lane line equation corresponding to the second lane line; determining a split point, and determining a fourth virtual auxiliary line based on the split point and the second tangent point; and constructing the second virtual lane line based on the third and fourth virtual auxiliary lines. Specific steps can be found in the above embodiments and will not be repeated here. Therefore, connecting the first virtual lane line before the traffic split with the second virtual lane line after the traffic split generates an "S"-shaped virtual lane line.

[0082] In the above embodiments, by constructing virtual auxiliary lines and virtual lane lines before or after traffic diversion, the first virtual lane line and the second virtual lane line are constructed in a two-segment manner. Then, the first virtual lane line before traffic diversion is connected to the second virtual lane line after traffic diversion to generate a smooth "S"-shaped virtual lane line. This allows the generated virtual lane line to transition smoothly at the traffic diversion point, and vehicles will not have a large lateral deviation when driving, thus ensuring driving safety.

[0083] In some embodiments, determining the split point of the virtual lane line includes: determining the first coordinates of the end point of the first lane line and the second coordinates of the start point of the second lane line; and determining the split point of the virtual lane line based on the first coordinates and the second coordinates.

[0084] Specifically, the computer device obtains the coordinates of the end point of the first lane line, i.e., the first coordinates, and the coordinates of the start point of the second lane line, i.e., the second coordinates. Based on the first and second coordinates, the computer device can then determine the point located midway between the first and second coordinates on both the X and Y axes; this point is the dividing point of the virtual lane line.

[0085] For example, such as Figure 8 As shown, the computer device calculates the mean of the horizontal and vertical coordinates based on the first coordinate (x1, y1) and the second coordinate (x2, y2) to obtain the dividing point. The coordinates of the dividing point are ((x1+x2) / 2, (y1+y2) / 2).

[0086] In the above embodiments, the split point is determined by calculating the breakpoint of the lane line before and after the split, so that the generated virtual lane line can transition at the split in a relatively smooth "S" shape, and there is no large lateral deviation when the vehicle is driving, thereby ensuring driving safety.

[0087] After the virtual lane line is constructed, the computer device can generate a driving path for the vehicle according to the virtual lane line. To this end, in some embodiments, the driving path of the vehicle is generated based on the virtual lane line, including: determining a driving area composed of the virtual left lane line and the virtual right lane line; and generating the driving path of the vehicle in the driving area.

[0088] Specifically, in the case where the virtual lane line includes the virtual left lane line and the virtual right lane line, the computer device can determine a driving area composed of the virtual left lane line and the virtual right lane line. The driving area can be the entire area composed of the virtual left lane line and the virtual right lane line, or a driving area slightly smaller than the entire area, etc., as shown in the figure. Thus, the computer device can generate the driving path of the vehicle in the driving area. Figure 9

[0089] It should be noted that when the virtual lane line includes only one virtual lane line, such as the virtual left lane line or the virtual right lane line, the right side of the virtual left lane line is the driving area, and the left side of the virtual right lane line is the driving area.

[0090] In the above embodiments, by determining the driving area composed of the virtual left lane line and the virtual right lane line, and planning the driving path in the driving area, the driving safety of the vehicle is further ensured.

[0091] To further ensure the lateral deviation of the vehicle before and after the split, in some embodiments, the above method further includes: determining the lane line curvature of the virtual lane line; when the lane line curvature does not satisfy the curvature condition, adjusting the position of the first tangent point and / or the second tangent point, and returning to the step of constructing the virtual lane line based on the first lane line and the second lane line until the curvature of the generated virtual lane line satisfies the curvature condition.

[0092] Specifically, after the virtual lane line is generated, the computer device further calculates the lane line curvature of the virtual lane line. The way to calculate the lane line curvature may, for example, be to calculate the curvature based on the arc length of the parameter curve, and the specific way is not limited by the present application.

[0093] ​The computer device can acquire a preset curvature threshold, and determine whether the calculated lane line curvature is less than the curvature threshold, so as to determine whether the lane line curvature satisfies the curvature condition. When the lane line curvature exceeds the curvature threshold, it indicates that the lane line curvature does not satisfy the curvature condition, and the computer device returns to step S302 to re-execute and re-determine the positions of the first and second tangent points, so as to re-generate a new virtual lane line.

[0094] When the computer device re-generates the virtual lane line, the first tangent point is farther from the end point of the first lane line than when the virtual lane line was last generated, and / or the second tangent point is farther from the start point of the second lane line than when the virtual lane line was last generated. For example, when re-generating, the computer device increases the first preset value and / or increases the second preset value, so as to re-determine the first and / or second tangent points.

[0095] In the above embodiments, the lane line curvature of the generated virtual lane line is controlled by the curvature condition, so as to ensure that the driving path of the vehicle can satisfy the lateral control requirements of the vehicle, guarantee the safety of driving, and ensure the continuous operation of the intelligent driving function in the split flow situation without the user taking over the steering wheel for manual driving. When the lane line curvature does not satisfy the curvature condition, the positions of the two-section lane line tangent points can also be adjusted in an adaptive manner, so as to construct a virtual lane line that satisfies the curvature requirement, and further generate a driving path that meets the lateral control requirements.

[0096] In the case where the virtual lane line is constructed based on the first virtual lane line and the second virtual lane line, the lane line curvature of the virtual lane line is determined, including: determining a first curvature of the first virtual lane line and a second curvature of the second virtual lane line, respectively; and wherein the lane line curvature does not satisfy the curvature condition includes that the first curvature does not satisfy a first curvature condition and the second curvature does not satisfy a second curvature condition.

[0097] Specifically, the computer device calculates the first curvature of the first virtual lane line and the second curvature of the second virtual lane line, respectively, and determines whether the first curvature satisfies the first curvature condition and whether the second curvature satisfies the second curvature condition, respectively. For example, the computer device can determine whether the first curvature is less than a first curvature threshold and whether the second curvature is less than a second curvature threshold, respectively. Only when the first curvature and the second curvature both satisfy the corresponding curvature conditions, the computer device determines that the lane line curvature of the virtual lane line meets the curvature condition, and further generates a driving path that can satisfy the lateral control requirements of the vehicle.

[0098] In the above embodiments, by constructing a two-section virtual lane line and controlling the lane line curvatures of the virtual lane lines before and after the split, the generated "S" type virtual lane line can be made smoother, so as to effectively ensure that the generated driving path meets the lateral control requirements.

[0099] In any of the above embodiments or combinations thereof, the construction of the virtual lane line is described in detail. However, in practical scenarios, one of the keys to constructing the virtual lane line is to judge the lane line split flow condition, and accurately detect the breakpoints of the lane lines before and after the split, that is, to judge where the lane line of the current lane ends and where the lane line of the target lane starts. Moreover, due to the possible problems such as color fading and partial loss of the lane line in actual scenarios, it will affect the accurate extraction of the lane line, and further affect the accurate construction of the virtual lane line. Therefore, the accurate extraction of the lane line before and after the split is particularly important. Therefore, in some embodiments, the first lane line of the current lane where the vehicle is located before the split is determined, and the second lane line of the target lane where the vehicle will enter after the split is determined, comprising: extracting a plurality of lane lines in the image, and dividing the plurality of lane lines into lane lines before the split and lane lines after the split; in the lane lines before the split, determining the first lane line of the current lane where the vehicle is located; in the lane lines after the split, screening out the second lane line of the target lane where the vehicle will enter after the split.

[0100] Specifically, the computer device first extracts a plurality of lane lines included in the image, and divides each lane line extracted to be divided into lane lines before the split or lane lines after the split. Therefore, the computer device can determine the first lane line of the current lane where the vehicle is located in the lane lines before the split. For example, the computer device obtains the current position of the vehicle, and calculates the lateral distance between each lane line before the split and the current position, and the lane line before the split with the smallest lateral distance is taken as the first lane line of the current lane where the vehicle is located.

[0101] Moreover, the computer device can screen out the second lane line of the target lane where the vehicle will enter after the split in the lane lines after the split. For example, the computer device can calculate the lateral distance between each lane line after the split and the current position, and the lane line after the split with the smallest lateral distance is taken as the second lane line of the target lane. For another example, the computer device can calculate the lateral distance between each lane line after the split and the first lane line based on the determined first lane line, and the lane line after the split with the smallest lateral distance is taken as the second lane line of the target lane.

[0102] In the above embodiments, by dividing each detected lane line to distinguish whether the lane line belongs to the lane line before the split or the lane line after the split under the split flow condition, and further determining the first lane line of the current lane and the second lane line of the target lane, the computational complexity is reduced, the computing power requirement is low, the generation efficiency of the driving path can be improved, and it is suitable for actual needs under various split flow conditions.

[0103] The extracting the plurality of lane lines in the image comprises: performing peak value searching on the image to determine a plurality of peak points; for any peak point, taking the peak point as a starting point, searching through a plurality of sliding windows to determine effective pixels in each sliding window; and performing lane line fitting based on the effective pixels in each sliding window to obtain a lane line corresponding to the peak point.

[0104] Specifically, the computer device can determine the center point of each lane line through peak value searching. For example, the computer device can use a histogram statistical method to perform peak value searching on the image to preliminarily locate the center position of each lane line in the horizontal direction, and the pixel point of the center position is the peak point.

[0105] Then, the computer device takes the peak point as a starting point to search through a sliding window to obtain all pixels and coordinate information of each lane line. For example, the computer device defines the height of the sliding window as h, the width of the lane marking as w, and the correspondence between the image X-axis direction and Y-axis direction pixels and the real world coordinate system as f(x) and f(y), and the width of the sliding window can be set to 2*w / f(x) to more completely search the effective pixel information of the lane line. The effective pixel refers to the pixel belonging to the lane line. The effective pixel information is, for example, the number, coordinates and other information of the effective pixel.

[0106] Thus, for each peak point, the computer device starts from the position of the peak point, searches through a plurality of sliding windows to determine the effective pixels in each sliding window, and performs lane line fitting based on the effective pixels in each sliding window to obtain the lane line corresponding to the peak point.

[0107] In the above embodiment, the center position of the lane line is preliminarily located through peak value searching, and the sliding search is performed based on the center position, so that the lane line is fitted according to the effective pixels in the sliding search, which can quickly extract the lane line information in the image, has low computing power requirement and high efficiency in extracting the lane line.

[0108] In the process of sliding search, the computer device can also determine whether each lane line belongs to a pre-split lane line or a post-split lane line. That is, in some embodiments, dividing the plurality of lane lines into a pre-split lane line and a post-split lane line comprises: determining a preset interval length of the lane line; under the condition that the number of effective pixels in a continuous preset number of sliding windows is less than a first threshold, when a interval condition is met based on the preset number and the preset interval length, determining the lane line as the post-split lane line; and when the interval condition is not met based on the first number and the preset interval length, determining the lane line as the pre-split lane line.

[0109] Specifically, the computer device determines a preset interval length Line_gap of the lane line in the Y-axis direction. When the computer device performs a sliding search in the Y-axis direction through a sliding window, if the number of valid pixels in the current window is less than a first threshold value, it indicates that the window does not contain valid lane line information.

[0110] If the number of valid pixels in the N consecutive sliding windows is less than the first threshold value, and the interval condition N*h*f(y)>Line_gap is met, i.e., the interval between the lane lines on the image is greater than the preset interval length when the lane lines are mapped to reality, the computer device determines the lane line as a post-split lane line. Otherwise, if the interval condition N*h*f(y)>Line_gap is not met, the computer device determines the lane line as a pre-split lane line.

[0111] In the above embodiments, by judging whether the lane line is a pre-split lane line or a post-split lane line according to the valid pixel information in the consecutive sliding windows, the extracted lane line is more accurate. Moreover, the above method does not need to perform complex image processing, and has small computing power requirement, simple process, high algorithm robustness and environmental adaptability, and can be applied to various types of lane line split road conditions.

[0112] To more accurately extract each lane line, the computer device also updates the center position of the lane line in the X-axis direction, i.e., the peak point, in real time during the sliding search. Therefore, in some embodiments, when the number of valid pixels in any sliding window exceeds a second threshold value, a new peak point is determined based on the coordinates of each valid pixel in the sliding window. Specifically, when the number of valid pixels in the current sliding window exceeds the second threshold value, the computer device obtains the horizontal coordinates of all valid pixels in the current sliding window, and calculates the mean value of the horizontal coordinates of all valid pixels. The pixel at the horizontal coordinate position represented by the mean value is taken as the new peak point of the current lane line. In this way, by updating the center position of the lane line, the accuracy of lane line extraction and fitting is improved, and the accuracy of the virtual lane line and the driving path is also improved.

[0113] In the above embodiment, the valid pixels in each sliding window are determined by: obtaining pixel values of pixels in each sliding window; and for any pixel, the pixel is determined as a valid pixel when the pixel value of the pixel exceeds a third threshold. Specifically, the computer device obtains pixel values of pixels in each sliding window, and for each pixel, it is determined whether the pixel value of the pixel exceeds a third threshold. If yes, the computer device determines the pixel as a valid pixel. Thus, lane line fitting is performed based on the valid pixel information in the sliding window, and the obtained lane line is more accurate; and the judgment of the lane lines before and after the split is performed based on the valid pixel information in the continuous multiple sliding windows, so that the current lane and the target lane can be quickly determined, and the generation efficiency of the driving path is improved.

[0114] It should be understood that, although each step in the flowchart involved in the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0115] As described above, the embodiments of the present application can also be applied in a lane changing scene. In an ideal state, the lane lines before and after lane changing in the lane changing scene are continuous in the vertical direction, but in actual road conditions, the lane lines before and after lane changing in the lane changing scene may also have a certain degree of misalignment in the horizontal direction.

[0116] The embodiments of the present application can also be applied to this kind of scene, that is, the driving path generation method provided by the embodiments of the present application further comprises: determining a first lane line of a current lane where the vehicle is located before lane changing, and determining a second lane line of a target lane where the vehicle will enter after lane changing; constructing a virtual lane line based on the first lane line and the second lane line; and generating a driving path of the vehicle based on the virtual lane line. In the lane changing scene, the computer device determines the lane where the vehicle is located before lane changing (i.e. the current lane), and the lane where the vehicle will enter after lane changing, i.e. the target lane. Further, the computer device extracts the lane line of the current lane as the first lane line, and extracts the second lane line of the target lane as the second lane line.

[0117] The computer device can extract the first lane line and the second lane line according to the image collected by the vehicle or the road facility device. In some embodiments, the computer device further performs image processing such as size adjustment, noise reduction filtering, binarization processing, coordinate system mapping, etc. on the image to highlight the lane line information. For example, the computer device can extract the lane line from the road surface monitoring image collected by the vehicle or the road facility device, and then distinguish the first lane line and the second lane line. For example, the computer device obtains a road surface top view, and determines the first lane line and the second lane line in the road surface top view. The road surface top view is a road surface image in a top-down perspective, as shown in FIG. 8A, for example. For example, the computer device can obtain the road surface image collected by the vehicle, and generate the road surface top view through inverse perspective mapping or the like. Figure 1

[0118] In some embodiments, the computer device can obtain the road surface top view by: obtaining a driving monitoring image collected by a shooting device of the vehicle; and converting the driving monitoring image into the road surface top view based on a preset coordinate system mapping relationship. The preset coordinate system mapping relationship can be a mapping relationship between a coordinate system of a real physical world and an image coordinate system, for example. In other embodiments, the computer device can further obtain point cloud data, and determine the first lane line and the second lane line according to the point cloud data. For example, the computer device extracts the point cloud data belonging to the lane line from the point cloud data, and then extracts the first lane line and the second lane line, etc. Therefore, the computer device can extract all the lane lines in the image, and determine whether the vehicle is currently in the lane changing scene according to the distance characteristics between the lane lines in the image. Alternatively, the computer device can determine that the current is in the lane changing scene according to the driving instruction of the vehicle (such as the instruction of the driver to the vehicle to change lanes through buttons, touch, voice, etc.), that is, the vehicle will change lanes.

[0119] In some embodiments, the computer device determines the lane line with the minimum distance between the lane line after the lane changing and the lane line of the current lane, that is, the distance in the X-axis direction, as the lane line of the target lane. The computer device can construct a virtual lane line through the lane lines on the same side of the lane, for example, the computer device can take the left lane line of the current lane as the first lane line, and take the left lane line of the target lane as the second lane line. Alternatively, the computer device can take the right lane line of the current lane as the first lane line, and take the right lane line of the target lane as the second lane line. In other embodiments, the computer device can take the left lane line and the right lane line of the current lane as the first lane line, and take the left lane line and the right lane line of the target lane as the second lane line. It is easy to understand that when the determined lane line includes the left lane line and the right lane line, the first left lane line corresponds to the second left lane line, and the first right lane line corresponds to the second right lane line, thereby generating smooth virtual lane lines on both sides.​

[0120] To make the process of lane changing smoother, in some embodiments, based on the first lane line and the second lane line, a virtual lane line is constructed, including: determining a first cut point on the first lane line, and a second cut point on the second lane line; wherein the first lane line belongs to the current lane where the vehicle is before lane changing, and the second lane line belongs to the target lane where the vehicle will enter after lane changing; based on the first cut point, a first virtual lane line is constructed, and based on the second cut point, a second virtual lane line is constructed; based on the first virtual lane line and the second virtual lane line, a virtual lane line is constructed. Specifically, the computer device determines a first cut point on the first lane line, and a second cut point on the second lane line, respectively. The first cut point is at least a certain distance away from the end point of the first lane line, and the second cut point is at least a certain distance away from the starting point of the second lane line, and the two distances can be equal or not equal. Thus, the computer device can construct a first virtual lane line based on the first cut point, and a second virtual lane line based on the second cut point. The computer device can connect the first virtual lane line and the second virtual lane line to construct a virtual lane line.

[0121] In the above embodiments, by constructing a two-segment fitting method to construct a virtual lane line during lane changing, the generated virtual lane line can ensure smooth driving of the vehicle, meet the lateral control requirements of the vehicle, and avoid safety hazards caused by excessive lateral deviation during driving.

[0122] In some embodiments, the first lane line includes a first left lane line and a first right lane line, and the second lane line includes a second left lane line and a second right lane line, then the first cut point includes: a first left cut point on the first left lane line, and a first right cut point on the first right lane line; the second cut point includes: a second left cut point on the second left lane line, and a second right cut point on the second right lane line. Thus, the first virtual lane line constructed includes: a first virtual left lane line constructed based on the first left cut point, and a first virtual right lane line constructed based on the first right cut point; the second virtual lane line includes: a second virtual left lane line constructed based on the second left cut point, and a second virtual right lane line constructed based on the second right cut point. Further, based on the first virtual lane line and the second virtual lane line, a virtual lane line is constructed, including: connecting the first virtual left lane line and the second virtual left lane line to generate a virtual left lane line; connecting the first virtual right lane line and the second virtual right lane line to generate a virtual right lane line; based on the virtual left lane line and the virtual right lane line, a virtual lane line is constructed.

[0123] In the above embodiment, the two-section fitting method is used to construct the virtual lane line in the lane changing process, and the virtual lane lines on the left and right sides of the lane are constructed respectively. The virtual lane lines on the left and right sides can form a complete virtual lane, and the driving path is planned in the virtual lane, so that the driving path is more accurate, the smooth driving of the vehicle is ensured, the lateral control requirements of the vehicle are met, and the safety hazards caused by excessive lateral deviation of the vehicle during driving are avoided.

[0124] In some embodiments, determining the first tangent point on the first lane line and the second tangent point on the second lane line comprises: determining a terminal point of the first lane line and a starting point of the second lane line; on the first lane line, a point at a first preset distance from the terminal point is taken as the first tangent point; and on the second lane line, a point at a second preset distance from the starting point is taken as the second tangent point. Specifically, the computer device takes the end point of the first lane line at the lane changing position as the terminal point, which represents the disconnection of the lane line before lane changing; and takes the starting point of the second lane line at the lane changing position as the starting point, which represents the start of the lane line after lane changing.

[0125] Therefore, the computer device determines a point on the first lane line that is at a distance interval of the first preset value from the terminal point as the first tangent point, and determines a point on the second lane line that is at a distance interval of the second preset value from the starting point as the second tangent point. The first preset value and the second preset value can be equal or unequal.

[0126] In the above embodiment, by selecting a point at a certain distance from the breakpoint of the lane line before and after lane changing as a tangent point, the generated virtual lane line has a certain extension in the longitudinal direction, and the lateral deviation of the driving path generated based on the virtual lane line meets the lateral control requirements of the vehicle, avoiding safety hazards caused by excessive lateral deviation.

[0127] In some embodiments, constructing the first virtual lane line based on the first tangent point comprises: determining a first virtual auxiliary line based on the first tangent point and a lane line equation corresponding to the first lane line; determining a segmentation point and determining a second virtual auxiliary line based on the segmentation point and the first tangent point; and constructing the first virtual lane line based on the first virtual auxiliary line and the second virtual auxiliary line. Specifically, the computer device determines a lane line equation corresponding to the first lane line when determining the first lane line. For example, the computer device can generate a lane line equation corresponding to the first lane line by a lane line fitting method. The lane line fitting method includes but is not limited to a least square method based on a hyperbolic model, an image processing method based on edge detection and transformation, a lane line fitting based on a fitting function and a residual function, etc., which are not limited in the present application.

[0128] Further, the computer device also determines the split point. Since the vehicle usually travels in an "S" shape when changing lanes, the curve turning point in the middle of the "S" shape is the split point of the virtual lane line. The computer device can determine the split point when extracting the lane line.

[0129] The computer device generates a first virtual auxiliary line according to the first tangent point and the lane line equation corresponding to the first lane line, and generates a second virtual auxiliary line according to the split point of the determined virtual lane point. Thus, according to the first virtual auxiliary line and the second virtual auxiliary line, a virtual circle tangent to the first tangent point can be determined, and the line segment between the first tangent point and the split point on the virtual circle is the first virtual lane line.

[0130] In some embodiments, determining the split point of the virtual lane line includes: respectively determining a first coordinate of a termination point of the first lane line and a second coordinate of a starting point of the second lane line; and determining the split point of the virtual lane line based on the first coordinate and the second coordinate.

[0131] Specifically, the computer device obtains a coordinate of a termination point of the first lane line, i.e., a first coordinate, and a coordinate of a starting point of the second lane line, i.e., a second coordinate. The computer device can determine a point located in the middle of the first coordinate and the second coordinate on the X-axis and the Y-axis according to the first coordinate and the second coordinate, and the point is the split point of the virtual lane line.

[0132] Thus, the split point is determined by the breakpoint of the lane line before and after the lane change, so that the generated virtual lane line can transition at the lane change in a relatively smooth "S" shape, and the vehicle does not have a large lateral deviation when traveling, thereby ensuring driving safety.

[0133] In some embodiments, generating a driving path of the vehicle based on the virtual lane line includes: determining a driving area constituted by the virtual left lane line and the virtual right lane line; and generating the driving path of the vehicle in the driving area. Specifically, in the case where the virtual lane line includes the virtual left lane line and the virtual right lane line, the computer device can determine a driving area constituted by the virtual left lane line and the virtual right lane line, which can be the entire area constituted by the virtual left lane line and the virtual right lane line, or a driving area slightly smaller than the entire area, etc.

[0134] Thus, by determining the driving area constituted by the virtual left lane line and the virtual right lane line, and planning the driving path in the driving area, the driving safety of the vehicle is further ensured.

[0135] In some embodiments, the method further comprises: determining a lane line curvature of the virtual lane line; when the lane line curvature does not satisfy the curvature condition, adjusting the position of the first cut point and / or the second cut point, returning to the step of constructing the virtual lane line based on the first lane line and the second lane line, until the curvature of the generated virtual lane line satisfies the curvature condition.

[0136] In the case where the virtual lane line is constructed based on the first virtual lane line and the second virtual lane line, the determination of the lane line curvature of the virtual lane line comprises: determining a first curvature of the first virtual lane line and a second curvature of the second virtual lane line respectively; and the lane line curvature not satisfying the curvature condition comprises: the first curvature not satisfying a first curvature condition and the second curvature not satisfying a second curvature condition.

[0137] Thus, the lane line curvature of the generated virtual lane line is controlled by the curvature condition, thereby ensuring that the driving path of the vehicle can satisfy the lateral control requirements of the vehicle, ensuring driving safety, and ensuring the continuous operation of the intelligent driving function under variable road conditions without the user taking over the steering wheel for manual driving. When the lane line curvature does not satisfy the curvature condition, the position of the two-section virtual lane line cut point can be adjusted in an adaptive manner to construct a virtual lane line that satisfies the curvature requirement, thereby generating a driving path that meets the lateral control requirements.

[0138] In some embodiments, the determination of the first lane line of the current lane where the vehicle is located before changing lanes and the determination of the second lane line of the target lane where the vehicle will enter after changing lanes comprise: extracting a plurality of lane lines in the image, and dividing the plurality of lane lines into lane lines before changing lanes and lane lines after changing lanes; in the lane lines before changing lanes, determining the first lane line of the current lane where the vehicle is located; and in the lane lines after changing lanes, screening out the second lane line of the target lane where the vehicle will enter after changing lanes.

[0139] Specifically, the computer device calculates a first curvature of the first virtual lane line and a second curvature of the second virtual lane line respectively, and determines whether the first curvature satisfies a first curvature condition and whether the second curvature satisfies a second curvature condition respectively. For example, the computer device can determine whether the first curvature is less than a first curvature threshold and whether the second curvature is less than a second curvature threshold respectively. Only when the first curvature and the second curvature both satisfy the corresponding curvature conditions, the computer device determines that the lane line curvature of the virtual lane line meets the curvature condition, and the generated driving path can satisfy the lateral control requirements of the vehicle.

[0140] In the above embodiments, by constructing a two-section virtual lane line and controlling the lane line curvature of the virtual lane line before and after changing lanes, the generated "S" type virtual lane line can be smoother, thereby effectively ensuring that the generated driving path meets the lateral control requirements.

[0141] In the method, the multiple lane lines in the image are extracted, including: performing peak value searching on the image to determine multiple peak points; for any peak point, taking the peak point as a starting point, searching through multiple sliding windows to determine valid pixels in each sliding window; and performing lane line fitting based on the valid pixels in each sliding window to obtain a lane line corresponding to the peak point. In the process of sliding searching, the computer device can also determine whether each lane line belongs to a lane line before lane changing or a lane line after lane changing. That is, in some embodiments, the multiple lane lines are divided into lane lines before lane changing and lane lines after lane changing, including: determining a preset interval length of the lane lines; under the condition that the number of valid pixels in a continuous preset number of sliding windows is less than a first threshold, when an interval condition is met based on the preset number and the preset interval length, the lane line concerned is determined as a lane line after lane changing; and when the interval condition is not met based on the first number and the preset interval length, the lane line concerned is determined as a lane line before lane changing. In the process of determining the valid pixels in each sliding window, the pixel values of the pixels in each sliding window are obtained, and for any pixel, when the pixel value of the pixel concerned exceeds a third threshold, the pixel concerned is determined as a valid pixel.

[0142] The specific implementation manners and beneficial effects of the lane changing scene in the above embodiments can refer to the description of the lane changing scene in the foregoing embodiments, which will not be described herein.

[0143] In one specific example, the embodiments of the present application also provide a driving path generation system, which can include a lane line information extraction module and a vehicle driving path planning module.

[0144] The lane line information extraction module is a key module for subsequent vehicle path planning at a split (or lane changing) point. The content of lane line information extraction includes pixel information of all lane lines in a road surface top view, judgment information of lane line categories (i.e., judgment of whether each lane line belongs to a lane line before split (or lane changing) or a lane line after split (or lane changing)), position information of lane line starting points or ending points (i.e., breakpoint) at a split (or lane changing) point, and lane line matching information at a split (or lane changing) point. The lane line detection process includes four types of lane lines: white solid line, white dashed line, yellow solid line, and yellow dashed line. The lane line information extraction module converts a driving view (usually a front view) into a road surface top view based on the conversion relationship between the driving view and the internal and external parameters of the camera, and based on the coordinate conversion relationship determined by the internal and external parameters, for subsequent detection and planning. Thus, as shown in FIG. 1 (taking a split scene as an example), the lane line information extraction module can perform the following steps: Figure 10

[0145] ​Step one, image pre-processing. In order to reduce the influence of lane line color, ground light and ground texture characteristics change and other factors in complex environment, the lane line information extraction module can first adopt the way of edge detection combined with multiple color space threshold to extract the lane line feature information of the input image. Specifically, the lane line information extraction module can adopt Sobel operator to detect the lane line pixels in horizontal and vertical directions respectively, and carry out threshold detection in RGB, HSV, Lab and LUV four color spaces, and combine the detection results of the two to obtain the binary image containing lane line features more robustly and clearly.

[0146] In the detection process, the lane line information extraction module selects a lane line detection method based on histogram statistics to analyze the binary image. However, this method cannot directly obtain the category and breakpoint position information of multiple lane lines before and after the split (or lane change) section, so it cannot plan the target lane and driving path to be merged after the split (or lane change). Therefore, the lane line information extraction module first screens the pixel information related to the lane line in the current frame image; on this basis, the pixel position information corresponding to each lane line is extracted based on histogram and sliding window, and the lane line category is judged synchronously; in addition, the lane line fitting is carried out according to the pixel information corresponding to each lane line, so as to further determine the lane line breakpoint position information by using the fitting result, and finally obtain the matching information of the lane lines before and after the split (or lane change).

[0147] Step two: pre- and post-split (or lane change) lane line detection. The lane line information extraction module performs peak finding on the binary image based on a histogram statistical method to preliminarily locate the center position x_current of each lane line in the X-axis direction of the image; and takes the center position as the starting point, searches for all pixel position information constituting each lane line through a sliding window. Among them, the sliding window height is defined as w_h, the lane marking width is defined as l_w, and the correspondence between the image X-axis direction and Y-axis direction pixels and the real world coordinate system is represented as xm_per_pix and ym_per_pix. The width of the sliding window can be set to 2*l_w / xm_per_pix, so that the effective pixel information of the lane line can be more completely searched. At the same time, in the search process, the lane line information extraction module synchronously judges the category of each lane line. Specifically, the gap length between the dashed lane lines is defined as line_gap, and considering the noise interference problem, for each sliding window, if the number of effective pixels in the current window is less than the threshold T1, it is considered that the window does not contain effective lane line information; if the number of effective pixels in the continuous N sliding windows is less than the threshold T1, and N*w_h*ym_per_pix>line_gap is satisfied, it can be determined that the lane line is a post-split (or lane change) lane line (i.e. the opposite lane line that may merge into), otherwise the lane line is a pre-split (or lane change) lane line (i.e. the current lane line). In addition, in the detection process, the lane line information extraction module also updates the center position x_current of the lane line in the X-axis direction of the image in real time, so as to more accurately detect the lane line. Specifically, if the number of effective pixels in the current window is greater than the threshold T2, the lane line information extraction module takes the mean value of the X coordinates of all effective pixel points in the window as the new center position x_current. After the search is completed, the lane line information extraction module performs lane line fitting according to the effective pixel information of each lane line to obtain the parameters of all lane lines before and after the split (or lane change).

[0148] Step three, split (or lane change) lane line breakpoint detection. The lane line information extraction module determines the position coordinates of the breakpoints of all lane lines in the Y-axis direction of the image based on the effective pixel information and lane line category information of the lane lines obtained in step two, and then calculates the position coordinates of the breakpoints in the X-axis direction of the image according to the lane line fitting equation, to finally obtain the breakpoint position information of all lane lines before and after the split (or lane change).

[0149] Step four: lane line matching at the split (or lane change) location. Taking the center position of the image in the X-axis direction as the center of the ego vehicle, the lane line information extraction module calculates the center positions between each two lane lines before the split (or lane change), so as to determine the lane in which the ego vehicle is located before the split (or lane change) and the left and right lane lines line now left and line now right that constitute the lane; the lane line information extraction module calculates the center positions between each two lane lines after the split (or lane change), selects the lane that is closest to the ego vehicle in the lateral direction (i.e., has the smallest lateral turning angle) as the opposite target lane into which the ego vehicle is about to merge, so as to determine the left and right lane lines line coming left and line coming right of the lane into which the ego vehicle is about to merge after the split (or lane change), and complete the lane line matching.

[0150] For the extraction results of the lane line information extraction module, the vehicle driving path planning module can determine the lane line breakpoint position information of the lane in which the ego vehicle is located before the split (or lane change), and the lane line breakpoint position information of the opposite target lane into which the ego vehicle is about to merge after the split (or lane change). The vehicle driving path planning module aims to design a virtual lane path according to these information, so that the ego vehicle can smoothly transition to the opposite target lane along the virtual lane during the split (or lane change), thereby reducing the exit probability of the intelligent auxiliary driving function under the lane line split (or lane change) condition and improving the continuity of the intelligent auxiliary driving function. The key to vehicle driving path planning is to construct a suitable virtual lane line on the split (or lane change) section, which not only can smoothly connect the lane lines before and after the split (or lane change), but more importantly, the curvature thereof can conform to the lateral control requirements (i.e., less than a preset curvature) as much as possible. However, the current one-segment lane line fitting method cannot meet the above conditions. Therefore, the driving path generation method provided in the embodiments of the present application constructs a virtual lane line by a two-segment fitting method, which is still shown in FIG. 4, and the specific implementation steps can be described as follows: Figure 10

[0151] Step one: determining the split point and the tangent point of the two-segment virtual lane line at the split (or lane change) location. The vehicle driving path planning module takes the left and right lane line breakpoint coordinates corner now left and corner now right of the lane in which the ego vehicle is located before the split (or lane change), and the left and right lane line breakpoint coordinates corner coming left and corner coming right of the opposite target lane into which the ego vehicle is about to merge after the split (or lane change), and takes the midpoint thereof as the split point of the two-segment lane arc, i.e.,

[0152] corner mid left = 1 / 2 * (corner now left + corner coming left) ​

[0153] corner_mid_right = 1 / 2 * (corner_now_right + corner_coming_right)

[0154] wherein corner_mid_left and corner_mid_right represent the split points of the two-segment lane arc, respectively.

[0155] In addition to the split points, another tangent point of the circular arc needs to be determined for constructing the lane arc. Therefore, the vehicle driving path planning module defines that the path planning starts at D1 meters before the split (or lane change) and ends at D2 meters after the split (or lane change), i.e., the virtual two-segment lane lines are tangent to the lane lines before and after the split (or lane change) at this point. For example, D1 = D2. According to the correspondence between the X-axis and Y-axis pixels in the image and the real-world coordinate system, the vehicle driving path planning module can determine the Y-axis coordinates of the tangent points of the left and right lane lines before and after the split (or lane change) as follows:

[0156] cut_now_left_y = corner_now_left_y + D1 / ym_per_pix

[0157] cut_coming_left_y = corner_coming_left_y - D2 / ym_per_pix

[0158] cut_now_right_y = corner_now_right_y + D1 / ym_per_pix

[0159] cut_coming_right_y = corner_coming_right_y - D2 / ym_per_pix

[0160] wherein cut_now_left, cut_coming_left, cut_now_right, and cut_coming_right represent the four tangent points of the left and right lane lines before and after the split (or lane change) and the virtual lane arc, respectively, and the suffix “_y” represents the Y-axis coordinate. Based on the Y-axis coordinates of the tangent points and the lane line equations obtained in the above steps, the vehicle driving path planning module can further calculate the X-axis coordinates of the tangent points to determine the positions of the tangent points.

[0161] Step two: constructing two-segment virtual lane line at the split (or lane change) point. Take the left lane line as an example, according to the cut point cut now left and the lane line equation of the left lane line before the split (or lane change), the vehicle driving path planning module can determine the tangent equation of the first segment of the left lane arc at the cut point, thereby obtaining the perpendicular line L1 passing through the center of the circle; according to the split point corner mid left and the cut point cut now left of the left lane line before the split (or lane change), the vehicle driving path planning module can obtain the middle perpendicular line L2 of the connecting line; the intersection of L1 and L2 is the position of the center of the first segment of the left virtual lane arc center now left.

[0162] Similarly, the vehicle driving path planning module can locate the position of the center of the second segment of the left virtual lane arc center coming left according to the split point corner mid left, the cut point cut coming left and the lane line equation of the left lane line after the split (or lane change), thereby determining the two-segment lane line on the left side at the split (or lane change) point. Similarly, the two-segment virtual lane line on the right side is also obtained by the same method.

[0163] Step three: calculating the curvature C of the virtual lane line. As mentioned above, the two-segment lane line constructed not only needs to smoothly connect the lane lines before and after the split (or lane change), but also needs to have a curvature that meets the lateral control requirements (i.e. less than the preset curvature threshold C Set) as much as possible, so that the intelligent auxiliary driving function can operate normally under the lane line split (or lane change) condition. Therefore, it is necessary to calculate the curvature of the constructed lane arc, and when the curvature exceeds the preset value, the position of the cut point (i.e. the value of D1 and D2) is adjusted to plan the virtual lane line that meets the curvature requirement.

[0164] Step four, judging whether the curvature C of the lane line virtual lane line is less than the preset curvature threshold C Set. If yes, continue to step five, otherwise return to step two to re-execute.

[0165] Step five: generating the vehicle driving path at the split (or lane change) point according to the virtual lane line. The vehicle driving path planning module can generate the driving path of the ego vehicle during the split (or lane change) process according to the two-segment lane arc constructed above, so that the vehicle can smoothly move forward according to the preset path under the action of the intelligent auxiliary driving function.

[0166] Thus, the final driving path generation system outputs the two-segment virtual lane line and the driving path of the vehicle.

[0167] Based on the same inventive concept, the embodiments of the present application also provide a driving path generation device for implementing the driving path generation method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more driving path generation device embodiments provided below can refer to the limitations of the driving path generation method described above, which will not be repeated here.

[0168] Please refer to Figure 11 , provides a driving path generation device, which can be integrated in a computer device, comprising a determination module 1101, a construction module 1102 and a generation module 1103, wherein:

[0169] The determination module 1101 is configured to determine a first lane line of a current lane where the vehicle is located, and determine a second lane line of a target lane where the vehicle is to enter;

[0170] The construction module 1102 is configured to construct a virtual lane line based on the first lane line and the second lane line;

[0171] The generation module 1103 is configured to generate a driving path of the vehicle based on the virtual lane line.

[0172] In some embodiments, the construction module is further configured to determine a first cut point on the first lane line, and a second cut point on the second lane line; wherein the first lane line belongs to a current lane where the vehicle is located before the split, and the second lane line belongs to a target lane where the vehicle is to enter after the split; construct a first virtual lane line based on the first cut point, and construct a second virtual lane line based on the second cut point; and construct the virtual lane line based on the first virtual lane line and the second virtual lane line.

[0173] In some embodiments, the construction module is further configured to determine a first cut point on the first lane line, and a second cut point on the second lane line; wherein the first lane line belongs to a current lane where the vehicle is located before the lane change, and the second lane line belongs to a target lane where the vehicle is to enter after the lane change; construct a first virtual lane line based on the first cut point, and construct a second virtual lane line based on the second cut point; and construct the virtual lane line based on the first virtual lane line and the second virtual lane line.

[0174] In some embodiments, the construction module is further configured to determine a termination point of the first lane line and a starting point of the second lane line; on the first lane line, a point with a first preset value from the termination point is taken as the first cut point; and on the second lane line, a point with a second preset value from the starting point is taken as the second cut point.

[0175] In some embodiments, the constructing module is further configured to determine a first virtual auxiliary line based on the first cut point and a lane line equation corresponding to the first lane line; determine a split point, and determine a second virtual auxiliary line based on the split point and the first cut point; and construct the first virtual lane line based on the first virtual auxiliary line and the second virtual auxiliary line.

[0176] In some embodiments, the constructing module is further configured to determine a first coordinate of a termination point of the first lane line, and a second coordinate of a starting point of the second lane line, respectively; and determine a split point of the virtual lane line based on the first coordinate and the second coordinate.

[0177] In some embodiments, the first virtual lane line comprises a first virtual left lane line and a first virtual right lane line, and the second virtual lane line comprises a second virtual left lane line and a second virtual right lane line; the constructing module is further configured to connect the first virtual left lane line with the second virtual left lane line to generate a virtual left lane line; connect the first virtual right lane line with the second virtual right lane line to generate a virtual right lane line; and construct the virtual lane line based on the virtual left lane line and the virtual right lane line.

[0178] In some embodiments, the constructing module is further configured to determine a driving area formed by the virtual left lane line and the virtual right lane line; and generate a driving path of the vehicle within the driving area.

[0179] In some embodiments, the apparatus further comprises a verifying module configured to determine a lane line curvature of the virtual lane line; and when the lane line curvature does not satisfy a curvature condition, adjust a position of the first cut point and / or the second cut point, and return to the step of constructing the virtual lane line based on the first lane line and the second lane line until a curvature of the generated virtual lane line satisfies the curvature condition.

[0180] In some embodiments, when the virtual lane line is constructed based on the first virtual lane line and the second virtual lane line, the verifying module is further configured to determine a first curvature of the first virtual lane line, and a second curvature of the second virtual lane line, respectively; and wherein the lane line curvature does not satisfy the curvature condition comprises that the first curvature does not satisfy a first curvature condition, and the second curvature does not satisfy a second curvature condition.

[0181] In some embodiments, the determining module is further configured to extract a plurality of lane lines in the image, and divide the plurality of lane lines into a pre-split lane line and a post-split lane line; in the pre-split lane line, determine a first lane line of a current lane in which the vehicle is located; and in the post-split lane line, screen out a second lane line of a target lane into which the vehicle will drive after the split.

[0182] In some embodiments, the determining module is further configured to extract a plurality of lane lines in the image, and divide the plurality of lane lines into lane lines before the lane change and lane lines after the lane change; in the lane lines before the lane change, determine a first lane line of a current lane in which the vehicle is located; and in the lane lines after the lane change, screen a second lane line of a target lane into which the vehicle will drive after the lane change.

[0183] In some embodiments, the determining module is further configured to perform peak finding on the image to determine a plurality of peak points; for any peak point, perform searching through a plurality of sliding windows with the peak point as a starting point, and determine effective pixels in each sliding window; and based on the effective pixels in each sliding window, perform lane line fitting to obtain a lane line corresponding to the peak point.

[0184] In some embodiments, the determining module is further configured to determine a preset interval length of the lane line; and when a number of effective pixels in a continuous preset number of sliding windows is less than a first threshold, and when an interval condition is met based on the preset number and the preset interval length, determine the lane line as a lane line after the lane split; and when the interval condition is not met based on the first number and the preset interval length, determine the lane line as a lane line before the lane split.

[0185] In some embodiments, the determining module is further configured to, when a number of effective pixels in any sliding window exceeds a second threshold, determine a new peak point based on coordinates of the effective pixels in the sliding window.

[0186] In some embodiments, the determining module is further configured to obtain pixel values of pixels in each sliding window; and for any pixel, when a pixel value of the pixel exceeds a third threshold, determine the pixel as an effective pixel.

[0187] Each module in the above apparatuses can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in the control apparatus in hardware form, or stored in a memory in a computer device in software form, so as to be called and executed by the processor to perform operations corresponding to the above modules.

[0188] In some embodiments, a computer device is provided, and an internal structure diagram of the computer device can be as shown in Figure 12The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize a driving path generation method.

[0189] Optionally, the computer device further includes a display unit. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, trackball or touchpad arranged on the shell of the computer device, or can be an external keyboard, touchpad or mouse, etc.

[0190] Those skilled in the art can understand that, Figure 12 The skilled in the art can understand that,

[0191] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited thereto.

[0192] Accordingly, embodiments of this application also provide a computer device, which may be a terminal device or a server.

[0193] like Figure 12 As shown, Figure 12 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. The computer device 1200 includes a processor 1201 with one or more processing cores, a memory 1202 with one or more computer-readable storage media, and a computer program stored on the memory 1202 and executable on the processor. The processor 1201 and the memory 1202 are electrically connected. Those skilled in the art will understand that the computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0194] The processor 1201 is a control center of the computer device 1200, connects all parts of the computer device 1200 by various interfaces and lines, executes various functions and processes data of the computer device 1200 by running or loading software programs and / or units stored in the memory 1202 and calling data stored in the memory 1202, and thus monitors the computer device 1200 as a whole. The processor 1201 can be a central processing unit CPU, a graphics processing unit GPU, a network processor NP, etc., and can implement or execute various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0195] In the embodiments of the present application, the processor 1201 in the computer device 1200 loads the instructions corresponding to the processes of one or more application programs into the memory 1202, and runs the application programs stored in the memory 1202 by the processor 1201, so as to implement various functions, for example: determining a first lane line of a current lane where a vehicle is located, and determining a second lane line of a target lane where the vehicle is going to enter; constructing a virtual lane line based on the first lane line and the second lane line; generating a driving path of the vehicle based on the virtual lane line. The specific implementation of each operation above can refer to the previous embodiments, which will not be repeated here.

[0196] Optionally, as shown in Figure 12 The computer device 1200 further includes a touch display screen 1203, a radio frequency circuit 1204, an audio circuit 1205, an input unit 1206 and a power supply 1207. The processor 1201 is electrically connected with the touch display screen 1203, the radio frequency circuit 1204, the audio circuit 1205, the input unit 1206 and the power supply 1207 respectively. Those skilled in the art can understand that the computer device structure shown in the Figure 12 The computer device structure shown in the

[0197] The touch display screen 1203 can be used to display a graphical user interface and receive operation instructions generated by user acting on the graphical user interface. The touch display screen 1203 can include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the computer device, which can be composed of graphics, text, icons, video and any combination thereof. Alternatively, the display panel can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED) or the like. The touch panel can be used to collect touch operations (such as user operations on or near the touch panel using a finger, a stylus or any suitable object or accessory) of the user thereon or therearound, and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Alternatively, the touch panel can include two parts of a touch detection device and a touch controller. The touch detection device detects the touch position of the user and detects signals generated by the touch operation, and transmits the signals to the touch controller; the touch controller receives the touch information from the touch detection device, and converts it into touch coordinates, and then sends it to the processor 1201, and can receive commands from the processor 1201 and execute them. The touch panel can cover the display panel, and when the touch panel detects a touch operation thereon or therearound, it transmits to the processor 1201 to determine the type of touch event, and then the processor 1201 provides corresponding visual output on the display panel according to the type of touch event. In the embodiments of the present application, the touch panel and the display panel can be integrated into the touch display screen 1203 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can realize the input and output functions as two independent components. That is, the touch display screen 1203 can also realize the input function as part of the input unit 1206.

[0198] The radio frequency circuit 1204 can be used to transceive radio frequency signals to establish wireless communication with network devices or other computer devices, and transceive signals between network devices or other computer devices.

[0199] The audio circuit 1205 can be used to provide an audio interface between a user and the computer device through a speaker and a microphone. The audio circuit 1205 can convert received audio data into an electrical signal and transmit the electrical signal to the speaker for conversion into an audible signal output by the speaker. On the other hand, the microphone can collect a sound signal and convert the sound signal into an electrical signal, which is received by the audio circuit 1205 and converted into audio data. The audio data can be output to the processor 1201 for processing, transmitted to another computer device through the radio frequency circuit 1204, or output to the memory 1202 for further processing. The audio circuit 1205 can also include a jack for a headset to provide communication between the headset and the computer device.

[0200] The input unit 1206 can be used to receive inputted digital, character information or user feature information (e.g., fingerprint, iris, face information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0201] The power supply 1207 is used to supply power to various components of the computer device 1200. Optionally, the power supply 1207 can be logically connected to the processor 1201 through a power management system, so that the power management system can be used to manage charging, discharging, power consumption management, etc. The power supply 1207 can also include one or more direct current or alternating current power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, etc.

[0202] Although Figure 12 The computer device 1200 can also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which are not shown in the figure, and will not be described here.

[0203] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0204] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by an instruction, or by an instruction controlling relevant hardware. The instruction can be stored in a computer readable storage medium and loaded and executed by a processor.

[0205] To this end, the embodiment of the present application provides a computer readable storage medium, wherein a plurality of computer programs are stored, the computer programs can be loaded by a processor to execute any one of the driving path generation methods provided by the embodiment of the present application. The computer program can execute the steps of the following driving path generation method: determining a first lane line of a current lane where the vehicle is located, and determining a second lane line of a target lane where the vehicle is going to enter; constructing a virtual lane line based on the first lane line and the second lane line; and generating a driving path of the vehicle based on the virtual lane line. The specific implementation of each operation can be referred to the foregoing embodiments, which will not be described here.

[0206] The computer readable storage medium can include a read only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0207] Since the computer programs stored in the computer readable storage medium can execute any one of the driving path generation methods provided by the embodiment of the present application, the beneficial effects that can be achieved by any one of the driving path generation methods provided by the embodiment of the present application can be achieved, which will be described in detail in the foregoing embodiments, and will not be described here.

[0208] According to an aspect of the present application, a computer program product or a computer program is also provided, the computer program product or the computer program includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional implementation manners in the foregoing embodiments.

[0209] In the above driving path generation device, computer readable storage medium, computer device, and computer program product embodiments, the description of each embodiment has its own focus, and the parts not described in detail in an embodiment can be referred to the related description of other embodiments. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the driving path generation device, computer readable storage medium, computer program product, computer device and its corresponding units described above and the beneficial effects brought by them can be referred to the description of the driving path generation method in the above embodiments, and will not be described here.

[0210] The technical features of the above embodiments can be combined arbitrarily, and for the sake of concise description, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0211] The above merely describes preferred embodiments of the present application, and is not intended to limit the present application in any form. Although the description of each embodiment in the present application has its own emphasis, the parts not described in detail in one embodiment can be referred to the relevant embodiments of other embodiments. Any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the technical solution content of the present application still falls within the scope of the technical solution of the present application.

Claims

1. A travel path generating method characterized by comprising: The method comprises: extracting a plurality of lane lines in an image, and determining a preset interval length of the lane lines; under the condition that the number of valid pixels in a continuous preset number of sliding windows is less than a first threshold value, determining a lane line as a post-split lane line when an interval condition is met based on the preset number and the preset interval length; determining the lane line as a pre-split lane line when the interval condition is not met based on the preset number and the preset interval length; in the pre-split lane line, determining a first lane line of a current lane in which a vehicle is located; in the post-split lane line, screening out a second lane line of a target lane into which the vehicle will drive after splitting; based on the first lane line and the second lane line, constructing a virtual lane line; based on the virtual lane line, generating a driving path of the vehicle.

2. The method of claim 1, wherein, The method comprises: determining a first tangent point on the first lane line and a second tangent point on the second lane line; wherein the first lane line belongs to a current lane in which the vehicle is located before splitting, and the second lane line belongs to a target lane into which the vehicle will drive after splitting; based on the first tangent point, constructing a first virtual lane line, and based on the second tangent point, constructing a second virtual lane line; based on the first virtual lane line and the second virtual lane line, constructing a virtual lane line.

3. The method of claim 2, wherein, The method comprises: determining a termination point of the first lane line and a starting point of the second lane line; on the first lane line, taking a point with a first preset value from the termination point as a first tangent point; on the second lane line, taking a point with a second preset value from the starting point as a second tangent point.

4. The method of claim 2, wherein, The method comprises: based on the first tangent point and a lane line equation corresponding to the first lane line, determining a first virtual auxiliary line; determining a split point, and based on the split point and the first tangent point, determining a second virtual auxiliary line; based on the first virtual auxiliary line and the second virtual auxiliary line, constructing a first virtual lane line.

5. The method of claim 4, wherein, The method comprises: respectively determining a first coordinate of the termination point of the first lane line and a second coordinate of the starting point of the second lane line; based on the first coordinate and the second coordinate, determining a split point of a virtual lane line.

6. The method of claim 2, wherein, The first virtual lane line comprises a first virtual left lane line and a first virtual right lane line, and the second virtual lane line comprises a second virtual left lane line and a second virtual right lane line; the method comprises: connecting the first virtual left lane line and the second virtual left lane line to generate a virtual left lane line; connecting the first virtual right lane line and the second virtual right lane line to generate a virtual right lane line; based on the virtual left lane line and the virtual right lane line, constructing a virtual lane line.

7. The method of claim 6, wherein, The method comprises: determine a driving area composed of the virtual left lane line and the virtual right lane line; generate a driving path of the vehicle in the driving area.

8. The method of claim 2, wherein, The method further comprises: determining a lane line curvature of the virtual lane line; when the lane line curvature does not satisfy a curvature condition, adjusting a position of the first and / or second tangent point, returning to the step of constructing the virtual lane line based on the first and second lane lines until the curvature of the generated virtual lane line satisfies the curvature condition.

9. The method of claim 8, wherein, when the virtual lane line is constructed based on the first and second virtual lane lines, the determining the lane line curvature of the virtual lane line comprises: determining a first curvature of the first virtual lane line and a second curvature of the second virtual lane line respectively; wherein the lane line curvature does not satisfy the curvature condition comprises that the first curvature does not satisfy a first curvature condition and the second curvature does not satisfy a second curvature condition.

10. The method of claim 1, wherein, The extracting the plurality of lane lines in the image comprises: performing peak searching on the image to determine a plurality of peak points; for any peak point, taking the peak point as a starting point, searching through a plurality of sliding windows to determine effective pixels in each sliding window; performing lane line fitting based on the effective pixels in each sliding window to obtain a lane line corresponding to the peak point.

11. The method of claim 10, wherein, The method further comprises: when the number of effective pixels in any sliding window exceeds a second threshold, determining a new peak point based on coordinates of the effective pixels in the sliding window.

12. The method of any one of claims 10-11, wherein, The determining the effective pixels in each sliding window comprises: obtaining pixel values of pixels in each sliding window; for any pixel, when the pixel value of the pixel exceeds a third threshold, determining the pixel as an effective pixel.

13. A travel path generating device characterized by comprising: The apparatus comprises: a determining module configured to extract a plurality of lane lines in an image, and determine a preset interval length of the lane lines, under a condition that the number of effective pixels in a continuous preset number of sliding windows is less than a first threshold, when a interval condition is satisfied based on the preset number and the preset interval length, determine a lane line after splitting as a lane line after splitting, when the interval condition is not satisfied based on the preset number and the preset interval length, determine a lane line before splitting as a lane line before splitting, in the lane line before splitting, determine a first lane line of a current lane in which a vehicle is located, in the lane line after splitting, filter out a second lane line of a target lane into which the vehicle will drive after splitting; a constructing module configured to construct a virtual lane line based on the first and second lane lines; a generating module configured to generate a driving path of the vehicle based on the virtual lane line.

14. A computer device, comprising: The apparatus comprises a processor and a memory, the memory stores a plurality of instructions; the processor loads the instructions from the memory to execute steps of the driving path generation method according to any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a plurality of instructions, the instructions are suitable for being loaded by a processor to execute steps of the driving path generation method according to any one of claims 1 to 12.

16. A computer program product, characterised in that, The computer program is executed by a processor to perform the steps of the travel path generation method according to any one of claims 1 to 12.

Images