Virtual lane line tracking rendering method, device, equipment and storage medium

Abstract

The present invention belongs to the field of autonomous driving technology, and discloses a method, device, equipment and storage medium for tracking and rendering a virtual lane line. The method includes: obtaining a target lane line, tracking and comparing the target lane line with a rendered lane line, and determining the association state between the target lane line and the rendered lane line; obtaining the attribute of the target lane line; when the attribute of the target lane line is a virtual lane line, determining the fixed endpoints in the target lane line according to the association state; dividing the target lane line according to the fixed endpoints to generate divided short solid line segments; and visually rendering the divided short solid line segments. In the above manner, the virtual lane line is divided into a number of short solid line segments, and the change of each short solid line segment in the continuous frames is minimized, which effectively solves the flow problem caused by the inconsistency of the virtual lane line generation points during rendering, can better serve visual rendering, reduce potential safety risks, and improve driving safety.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a virtual lane line tracking rendering method, device, equipment and storage medium. Background Art

[0002] In the autonomous driving system, lane lines are a very important perception element. They not only play an important role in behavioral decision-making, but also play a leading role in user interaction as the main display element. At present, when most perception systems identify and output lane lines, each lane line is represented by a series of points on the lane line. At the same time, the learned lane line attributes (such as dotted lines / solid lines, etc.) are sent to the downstream for use. There is no problem with directly rendering the real lane lines during visualization, but for the dotted lines, since the consistency of a series of points on the lane lines cannot be guaranteed each time they are sent to the downstream, it is easy for the virtual lane lines to flow during visualization rendering, which does not conform to the actual situation. Moreover, if the user stares at the flowing virtual lane lines, it is easy to get dizzy, which may cause safety accidents in serious cases.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a virtual lane line tracking rendering method, device, equipment and storage medium, aiming to solve the technical problem in the prior art that virtual lane lines are prone to flow during visual rendering, which can easily cause dizziness to users and affect driving safety.

[0005] To achieve the above object, the present invention provides a virtual lane line tracking and rendering method, the method comprising the following steps:

[0006] Acquire a target lane line, track and compare the target lane line with the rendered lane line, and determine the association state between the target lane line and the rendered lane line;

[0007] Obtaining the attributes of the target lane line;

[0008] When the attribute of the target lane line is a virtual lane line, determining a fixed endpoint in the target lane line according to the association state;

[0009] Segmenting the target lane line according to the fixed endpoints to generate segmented short solid line segments;

[0010] The segmented short solid line segments are visually rendered.

[0011] Optionally, determining a fixed endpoint in the target lane line according to the association state includes:

[0012] When the association state is no association, obtaining the endpoints at both ends of the target lane line and the endpoint positions corresponding to each of the endpoints;

[0013] According to the position of the endpoint, determining whether the endpoint is located in the front range and the rear range of the vehicle respectively;

[0014] When the endpoints are respectively located in the front range and the rear range of the vehicle, the endpoint located in the rear range of the vehicle is used as the fixed endpoint.

[0015] Optionally, the determining, based on the endpoint position, whether the endpoint is located behind the vehicle front range and the vehicle rear range, respectively, further includes:

[0016] When the endpoints are not located in the front range and the rear range of the vehicle respectively, the endpoints among the endpoints that meet the preset approach condition are used as the fixed endpoints.

[0017] Optionally, segmenting the target lane line according to the fixed endpoints to generate segmented short solid line segments includes:

[0018] Determine the current segmentation interval according to preset requirements;

[0019] The target lane line is segmented according to the fixed endpoint and the current segmentation interval to generate segmented short solid line segments.

[0020] Optionally, determining a fixed endpoint in the target lane line according to the association state includes:

[0021] When the association state is associated, obtaining a known segmented short solid line segment corresponding to the target lane line;

[0022] According to the endpoints of the known segmented short solid line segments, matching endpoints are determined in the target lane line as the fixed endpoints.

[0023] Optionally, segmenting the target lane line according to the fixed endpoints to generate segmented short solid line segments includes:

[0024] The target lane line is segmented according to the fixed endpoints to determine the interval between the first segmented short solid line segment and the current segmentation;

[0025] Determine the remaining lane lines according to the first segmented short solid line segment;

[0026] According to the current segmentation interval and the fixed endpoint, the remaining lane line is segmented and expanded to obtain a second segmented short solid line segment;

[0027] The first split short solid line segment and the second split short solid line segment are used as the split short solid line segment.

[0028] Optionally, after acquiring the attribute of the target lane line, the method further includes:

[0029] When the attribute of the target lane line is a mixed lane line, obtaining a real lane line and a virtual lane line in the target lane line;

[0030] Performing visual rendering on the actual lane line;

[0031] The virtual lane line is used as the target lane line, and the step of determining a fixed endpoint in the target lane line according to the association state is returned to be executed.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also proposes a virtual lane line tracking and rendering device, the virtual lane line tracking and rendering device comprising:

[0033] An acquisition module, used to acquire a target lane line, track and compare the target lane line with the rendered lane line, and determine the association state between the target lane line and the rendered lane line;

[0034] The acquisition module is further used to acquire the attributes of the target lane line;

[0035] A segmentation module, used for determining a fixed endpoint in the target lane line according to the association state when the attribute of the target lane line is a virtual lane line;

[0036] The segmentation module is further used to segment the target lane line according to the fixed endpoints to generate segmented short solid line segments;

[0037] A rendering module is used to perform visual rendering on the segmented short solid line segments.

[0038] In addition, to achieve the above-mentioned purpose, the present invention also proposes a virtual lane line tracking and rendering device, which includes: a memory, a processor, and a virtual lane line tracking and rendering program stored in the memory and executable on the processor, and the virtual lane line tracking and rendering program is configured to implement the steps of the virtual lane line tracking and rendering method described above.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a virtual lane line tracking rendering program is stored. When the virtual lane line tracking rendering program is executed by a processor, the steps of the virtual lane line tracking rendering method described above are implemented.

[0040] In the present invention, by acquiring the target lane line, the target lane line is tracked and compared with the rendered lane line, the association state between the target lane line and the rendered lane line is determined, and the attribute of the target lane line is acquired. When the attribute of the target lane line is a virtual lane line, the fixed endpoints in the target lane line are determined according to the association state, and the target lane line is segmented according to the fixed endpoints to generate segmented short solid line segments, and the segmented short solid line segments are visually rendered. Compared with directly visually rendering the virtual lane line, which is prone to flow phenomenon, the present invention divides the virtual lane line into segments of short solid line segments, and sets fixed endpoints to ensure that the change of each short solid line segment in continuous frames is minimized, which can effectively solve the flow problem caused by inconsistent virtual lane line generation points during rendering, can better serve visual rendering, reduce potential safety risks, and improve driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural schematic diagram of a virtual lane line tracking and rendering device in a hardware operating environment involved in an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of the flow chart of the first embodiment of the virtual lane line tracking and rendering method of the present invention;

[0043] Figure 3 It is a schematic diagram of the overall process of an embodiment of a virtual lane line tracking and rendering method of the present invention;

[0044] Figure 4 A schematic diagram of a flow chart of a second embodiment of a method for tracking and rendering virtual lane lines according to the present invention;

[0045] Figure 5 A schematic diagram of a flow chart of a third embodiment of a method for tracking and rendering virtual lane lines according to the present invention;

[0046] Figure 6 A schematic diagram of a flow chart of a fourth embodiment of a method for tracking and rendering virtual lane lines according to the present invention;

[0047] Figure 7 It is a structural block diagram of the first embodiment of the virtual lane line tracking and rendering device of the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0050] Reference Figure 1 , Figure 1It is a schematic diagram of the structure of a virtual lane line tracking and rendering device in the hardware operating environment involved in the embodiment of the present invention.

[0051] like Figure 1 As shown, the virtual lane line tracking rendering device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or it may be a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0052] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the virtual lane line tracking and rendering device, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0053] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a virtual lane line tracking and rendering program.

[0054] exist Figure 1 In the virtual lane line tracking and rendering device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the virtual lane line tracking and rendering device of the present invention can be set in the virtual lane line tracking and rendering device, and the virtual lane line tracking and rendering device calls the virtual lane line tracking and rendering program stored in the memory 1005 through the processor 1001, and executes the virtual lane line tracking and rendering method provided by the embodiment of the present invention.

[0055] The embodiment of the present invention provides a virtual lane line tracking and rendering method, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a method for tracking and rendering virtual lane lines according to the present invention.

[0056] In this embodiment, the virtual lane line tracking and rendering method includes the following steps:

[0057] Step S10: Acquire a target lane line, track and compare the target lane line with the rendered lane line, and determine the association state between the target lane line and the rendered lane line.

[0058] It should be noted that the executor of this embodiment is a vehicle, which includes at least a vehicle computer, a perception module and an interaction module. The perception module in this embodiment is a camera perception module, which can perceive lane lines. The interaction module in this embodiment is a human-robot interaction system (HRI, Human-Robot Interaction), that is, a large display screen, which can realize visual rendering.

[0059] It can be understood that the target lane line refers to the lane line that currently needs to be processed, and obtaining the target lane line includes: obtaining a road surface image within a preset range, sensing the road surface image, and obtaining the target lane line.

[0060] It should be understood that the road surface image is the image of the road surface, and the preset range refers to the range for collecting the road surface image, which is usually 100 meters around the vehicle body, and can be adjusted according to actual needs. This embodiment does not limit this.

[0061] In a specific implementation, this embodiment obtains the target lane line through a perception module. The perception module obtains a road surface image within a preset range through a camera, and the road surface image is perceived by a BEV transformer to obtain the target lane line.

[0062] It should be noted that the rendered lane line refers to the result that already exists in the local map, that is, the lane line that has been visually rendered using the method of this embodiment. The association state refers to the association between lane lines, which is divided into two states: associated and unassociated. If the target lane line can track and compare a certain lane line in the rendered lane line, it is considered that the target lane line has been visually rendered using the method of this embodiment (it may be fully rendered or partially rendered). At this time, the target lane line is associated with the rendered lane line, and the two lane lines can be associated together. If the target lane line cannot track and compare all the lane lines in the rendered lane line, it is considered that the target lane line has not been visually rendered using the method of this embodiment, and the target lane line is unassociated with the rendered lane line.

[0063] In a specific implementation, the target lane line is sensed by the perception module, the vehicle computer receives the target lane line, tracks and compares the target lane line with the rendered lane line, determines the association status between the target lane line and the rendered lane line, and associates the associated target lane line with the rendered lane line.

[0064] Step S20: Acquire the attributes of the target lane line.

[0065] It can be understood that the attribute of the target lane line refers to the category of the lane line that currently needs to be processed. The attributes in this embodiment may be a virtual lane line and a real lane line. Since a lane line may change from real to virtual starting from somewhere or from virtual to real starting from somewhere, the attributes in this embodiment may also be a mixed lane line.

[0066] It should be understood that the attributes of the target lane line are sensed by the perception module.

[0067] In a specific implementation, the vehicle will obtain the attributes perceived by the perception module in order to determine how to implement the next step.

[0068] Step S30: When the attribute of the target lane line is a virtual lane line, a fixed endpoint in the target lane line is determined according to the association state.

[0069] It should be noted that the fixed endpoints are the endpoints fixed during segmentation in this embodiment, which can be considered as the key points of segmentation. Different association states correspond to different fixed endpoint determination methods. Therefore, the number of fixed endpoints needs to be determined according to actual conditions.

[0070] It is understandable that when rendering a virtual lane line, flow phenomena caused by inconsistent generation points are prone to occur. When this embodiment determines that the target lane line is a virtual lane line, it will first perform corresponding processing and then perform visual rendering.

[0071] In the specific implementation, when the vehicle computer determines that the target lane line is a virtual lane line, it finds the corresponding fixed endpoint determination method according to the association state, determines the fixed endpoint in the target lane line, and reduces the change of each short solid line segment endpoint in continuous frames by setting the fixed endpoint.

[0072] Furthermore, after step S20, the method further includes: when the attribute of the target lane line is a real lane line, visually rendering the target lane line.

[0073] It should be understood that since direct rendering of the real lane line will not cause flow problems, this embodiment does not perform additional processing on the target lane line when it is determined that the target lane line is a real lane line, and directly performs visual rendering.

[0074] Step S40: segmenting the target lane line according to the fixed endpoints to generate segmented short solid line segments.

[0075] It should be noted that the divided short solid line segments refer to the short solid line segments obtained by dividing. Since the virtual lane line is essentially a combination of short solid line segments, this embodiment divides a virtual lane line into short solid line segments and ensures that the change of each short solid line segment in continuous frames is minimized.

[0076] It is understandable that since different association states have different fixed endpoint determination methods, and segmentation needs to be performed based on the fixed endpoints, different association states also correspond to different segmentation methods, and the association state, fixed endpoint determination method and segmentation method are corresponding.

[0077] In the specific implementation, the car will use the fixed endpoints as a reference to divide the target lane line into short solid line segments for the final visualization rendering.

[0078] Step S50: Visually render the segmented short solid line segments.

[0079] It should be understood that the visual rendering is completed by the interactive module. The vehicle computer sends the obtained segmented short solid line segments to the interactive module, and the interactive module performs visual rendering according to actual needs.

[0080] like Figure 3 The overall process diagram shown in the figure first receives the lane line from the camera perception module, tracks and compares it with the previous results, and then determines the attributes of the lane line. If the lane line is a virtual lane line, it needs to be divided into short solid line segments and then sent to HRI for visualization rendering. If the lane line is a real lane line, it is directly sent to HRI for visualization rendering.

[0081] In this embodiment, by acquiring the target lane line, the target lane line is tracked and compared with the rendered lane line, the association state between the target lane line and the rendered lane line is determined, and the attribute of the target lane line is acquired. When the attribute of the target lane line is a virtual lane line, the fixed endpoints in the target lane line are determined according to the association state, and the target lane line is segmented according to the fixed endpoints to generate segmented short solid line segments, and the segmented short solid line segments are visually rendered. Compared with directly visually rendering the virtual lane line, which is prone to flow phenomenon, this embodiment divides the virtual lane line into segments of short solid line segments, and sets fixed endpoints to ensure that the change of each short solid line segment in continuous frames is minimized, which can effectively solve the flow problem caused by inconsistent virtual lane line generation points during rendering, can better serve visual rendering, reduce potential safety risks, and improve driving safety.

[0082] Reference Figure 4 , Figure 4 The figure is a flow chart of a second embodiment of a method for tracking and rendering virtual lane lines according to the present invention.

[0083] Based on the above embodiment, step S30 includes:

[0084] Step S301: when the association state is no association, the endpoints at both ends of the target lane line and the endpoint positions corresponding to the endpoints are obtained.

[0085] It should be noted that the lane line is a line with two endpoints (the starting endpoint and the ending endpoint). The endpoints at both ends of the target lane line refer to the starting endpoint and the ending endpoint of the target lane line, and the endpoint positions refer to the positions of the two endpoints relative to the vehicle body.

[0086] It can be understood that when the association state is unassociated, it can be considered that the target lane line has not been segmented before, and the target lane line needs to be completely segmented. At this time, the fixed endpoint needs to be selected from the two endpoints of the target lane line, and one of them is selected.

[0087] Step S302: Determine, based on the endpoint positions, whether the endpoints are located in the front range and the rear range of the vehicle, respectively.

[0088] It should be understood that the vehicle front range refers to the range in front of the vehicle body and the range under the vehicle body, and the vehicle rear range refers to the range behind the vehicle body. The endpoint located in the vehicle front range means that the endpoint is in front of the vehicle body or under the vehicle body, and the endpoint located in the vehicle rear range means that the endpoint is behind the vehicle body. The vehicle front range and vehicle rear range respectively refer to that one of the two endpoints is in the vehicle rear range and the other is in the vehicle front range, that is, one of the two endpoints is behind the vehicle body and the other is below or in front of the vehicle body, and in this case, only one endpoint is behind the vehicle body.

[0089] In a specific implementation, it is determined whether one of the two endpoints is behind the vehicle body according to the positions of the two endpoints of the target lane line.

[0090] Step S303: When the endpoints are located in the front range and the rear range of the vehicle respectively, the endpoint located in the rear range of the vehicle is used as the fixed endpoint.

[0091] In a specific implementation, if one of the endpoints at both ends of the target lane line is behind the vehicle body, the endpoint behind the vehicle body is selected and fixed as the fixed endpoint. At this time, the number of fixed endpoints is 1.

[0092] Furthermore, after step S302, the method further includes: when the endpoints are not respectively located in the front range and the rear range of the vehicle, taking the endpoints among the endpoints that meet the preset approach condition as the fixed endpoint.

[0093] It should be noted that the endpoints are not located in the front range and rear range of the vehicle respectively, which means that the two endpoints are located in the front range of the vehicle at the same time or the two endpoints are located in the rear range of the vehicle at the same time, that is, both endpoints are behind the vehicle body or both endpoints are in front of / below the vehicle body.

[0094] It can be understood that the preset approach condition refers to approaching the vehicle body, and the endpoint that meets the preset approach condition is the endpoint that is closer to the vehicle body.

[0095] In a specific implementation, when the two endpoints are simultaneously located in the front range of the vehicle or the two endpoints are simultaneously located in the rear range of the vehicle, the endpoint closer to the vehicle body of the two endpoints is used as a fixed endpoint.

[0096] The step S40 comprises:

[0097] Step S401: Determine the current segmentation interval according to preset requirements.

[0098] It should be understood that the preset requirements refer to visualization requirements, that is, to restore the real scene as much as possible, and the endpoints of each frame cannot change too much so that the lines look like they are flowing. The current segmentation interval is equivalent to the length of each short solid line segment during the current segmentation. The specific value needs to be determined according to the actual situation, and this embodiment does not limit this.

[0099] Step S402: segmenting the target lane line according to the fixed endpoints and the current segmentation interval to generate segmented short solid line segments.

[0100] In the specific implementation, according to the visualization requirements, the target lane line is divided into several short solid line segments at equal intervals according to the current segmentation interval.

[0101] In this embodiment, when the association state is unassociated, the endpoints at both ends of the target lane line and the endpoint positions corresponding to each of the endpoints are obtained, and according to the endpoint positions, it is determined whether the endpoints are respectively located in the front range and the rear range of the vehicle. When the endpoints are respectively located in the front range and the rear range of the vehicle, the endpoints located in the rear range of the vehicle are used as the fixed endpoints. According to preset requirements, the current segmentation interval is determined, and the target lane line is segmented according to the fixed endpoint and the current segmentation interval to generate segmented short solid line segments. This embodiment divides the virtual lane line into segments of short solid line segments, and by setting fixed endpoints, it ensures that the change of each short solid line segment in continuous frames is minimized, which can effectively solve the flow problem caused by inconsistent virtual lane line generation points during rendering, and can better serve visual rendering, reduce potential safety risks, and improve driving safety.

[0102] Reference Figure 5 , Figure 5 The figure is a flow chart of a third embodiment of a method for tracking and rendering virtual lane lines according to the present invention.

[0103] Based on the first embodiment above, step S30 includes:

[0104] Step S301 ′: when the association state is associated, obtaining a known segmented short solid line segment corresponding to the target lane line.

[0105] It should be noted that if the association status is associated, it can be considered that the target lane line has been segmented before, and the target lane line does not need to be segmented completely, but only the part that has not been processed before needs to be segmented. The target lane line has been segmented before, which means that the result of the previous segmentation is known information, and the known segmented short solid line segment refers to the short solid line segment obtained by the previous segmentation process.

[0106] Step S302': According to the endpoints of the known segmented short solid line segments, a matching endpoint is determined in the target lane line as the fixed endpoint.

[0107] It is understandable that the matching endpoint refers to a point in the target lane line that can match the endpoint of the known segmented short solid line segment. Since the known segmented short solid line segment is a known segmentation result, the endpoint of each corresponding short solid line segment is also known.

[0108] In a specific implementation, when the association state is associated, points that can match these short solid line segments are determined in the target lane line according to the several short solid line segments obtained by the previous segmentation process, and these matching points are fixed as fixed endpoints.

[0109] The step S40 comprises:

[0110] Step S401 ′: segmenting the target lane line according to the fixed endpoints, and determining the interval between the first segmented short solid line segment and the current segmentation.

[0111] It should be understood that the first segmented short solid line segments refer to the target lane line obtained according to the previous segmentation results, that is, the target lane line is segmented according to the fixed endpoints to obtain the short solid line segments. The fixed endpoints are actually the endpoints at both ends of these short solid line segments. The current segmentation interval is equivalent to the length of each short solid line segment during the current segmentation. The current segmentation interval in this embodiment is determined according to the previous segmentation results to ensure that the lane line is segmented at equal intervals.

[0112] Step S402': determining the remaining lane lines according to the first segmented short solid line segments, and segmenting and extending the remaining lane lines according to the current segmentation interval and the fixed endpoints to obtain second segmented short solid line segments.

[0113] It should be noted that the remaining lane line refers to the portion of the target lane line that has not been segmented before. The second segmented short solid line segment refers to a number of short solid line segments obtained by segmenting the remaining lane line, and the remaining lane line is segmented at equal intervals according to the current segmentation interval to generate a number of short solid line segments.

[0114] In the specific implementation, for the target lane line to be processed currently, first find the corresponding points in the target lane line according to the previous segmentation results, and fix these points as fixed endpoints for segmentation, and then continue to segment and expand the remaining parts until the entire target lane line is covered.

[0115] Step S403 ′: taking the first segmented short solid line segment and the second segmented short solid line segment as the segmented short solid line segment.

[0116] In a specific implementation, the interaction module can directly visualize the first segmented short solid line segment according to the previous segmentation processing result. At the same time, the vehicle will send the obtained second segmented short solid line segment to the interaction module, and the interaction module will then visualize and render the second segmented short solid line segment.

[0117] In this embodiment, when the association state is associated, the known split short solid line segment corresponding to the target lane line is obtained, and according to the endpoints of the known split short solid line segment, a matching endpoint is determined in the target lane line as the fixed endpoint, and the target lane line is split according to the fixed endpoint to determine the first split short solid line segment and the current split interval, and the remaining lane lines are determined according to the first split short solid line segment, and the remaining lane lines are split and extended according to the current split interval and the fixed endpoint to obtain the second split short solid line segment, and the first split short solid line segment and the second split short solid line segment are used as the split short solid line segment. This embodiment splits the virtual lane line into segments of short solid line segments, and by setting fixed endpoints, ensures that the change of each short solid line segment in consecutive frames is minimized, which can effectively solve the flow problem caused by inconsistent virtual lane line generation points during rendering, can better serve visual rendering, reduce potential safety risks, and improve driving safety.

[0118] Reference Figure 6 , Figure 6 The figure is a flow chart of a fourth embodiment of a method for tracking and rendering virtual lane lines according to the present invention.

[0119] Based on the first embodiment above, step S30 includes:

[0120] Step S301": when the attribute of the target lane line is a mixed lane line, a real lane line and a virtual lane line in the target lane line are obtained.

[0121] It should be noted that when the attribute is a mixed lane line, it means that the target lane line contains both real lane lines and virtual lane lines, which need to be rendered separately.

[0122] Step S302": Visually render the actual lane line.

[0123] Step S303": taking the virtual lane line as the target lane line, and determining a fixed endpoint in the target lane line according to the association state.

[0124] In a specific implementation, the real lane line in the target lane line is directly visualized and rendered, and the virtual lane line in the target lane line is used as the current target lane line, and the process returns to step S30. For the specific content, please refer to the above embodiment, which will not be described in detail in this embodiment.

[0125] In this embodiment, when the attribute of the target lane line is a mixed lane line, the real lane line and the virtual lane line in the target lane line are obtained, the real lane line is visually rendered, the virtual lane line is used as the target lane line, and the fixed endpoints in the target lane line are determined according to the association state, the target lane line is segmented according to the fixed endpoints, and the segmented short solid line segments are generated, and the segmented short solid line segments are visually rendered. This embodiment divides the virtual lane line into segments of short solid line segments, and ensures that the change of each short solid line segment in consecutive frames is minimal, which can effectively solve the flow problem caused by the inconsistency of the virtual lane line generation points during rendering, can better serve visual rendering, reduce potential safety risks, and improve driving safety.

[0126] In addition, an embodiment of the present invention further proposes a storage medium, on which a virtual lane line tracking and rendering program is stored. When the virtual lane line tracking and rendering program is executed by a processor, the steps of the virtual lane line tracking and rendering method described above are implemented.

[0127] Reference Figure 7 , Figure 7 It is a structural block diagram of the first embodiment of the virtual lane line tracking and rendering device of the present invention.

[0128] like Figure 7 As shown, the virtual lane line tracking and rendering device proposed in the embodiment of the present invention includes:

[0129] The acquisition module 10 is used to acquire a target lane line, track and compare the target lane line with the rendered lane line, and determine the association state between the target lane line and the rendered lane line.

[0130] The acquisition module 10 is further used to acquire the attributes of the target lane line.

[0131] The segmentation module 20 is used to determine the fixed endpoints in the target lane line according to the association state when the attribute of the target lane line is a virtual lane line.

[0132] The segmentation module 20 is further configured to segment the target lane line according to the fixed endpoints to generate segmented short solid line segments.

[0133] The rendering module 30 is used to perform visual rendering on the segmented short solid line segments.

[0134] In this embodiment, by acquiring the target lane line, the target lane line is tracked and compared with the rendered lane line, the association state between the target lane line and the rendered lane line is determined, and the attribute of the target lane line is acquired. When the attribute of the target lane line is a virtual lane line, the fixed endpoints in the target lane line are determined according to the association state, and the target lane line is segmented according to the fixed endpoints to generate segmented short solid line segments, and the segmented short solid line segments are visually rendered. Compared with directly visually rendering the virtual lane line, which is prone to flow phenomenon, this embodiment divides the virtual lane line into segments of short solid line segments, and sets fixed endpoints to ensure that the change of each short solid line segment in continuous frames is minimized, which can effectively solve the flow problem caused by inconsistent virtual lane line generation points during rendering, can better serve visual rendering, reduce potential safety risks, and improve driving safety.

[0135] In one embodiment, the segmentation module 20 is further configured to obtain the endpoints at both ends of the target lane line and the endpoint positions corresponding to each of the endpoints when the association state is unassociated;

[0136] According to the position of the endpoint, determining whether the endpoint is located in the front range and the rear range of the vehicle respectively;

[0137] When the endpoints are respectively located in the front range and the rear range of the vehicle, the endpoint located in the rear range of the vehicle is used as the fixed endpoint.

[0138] In one embodiment, the segmentation module 20 is further configured to use an endpoint among the endpoints that meets a preset approach condition as the fixed endpoint when the endpoints are not respectively located in the front range and the rear range of the vehicle.

[0139] In one embodiment, the segmentation module 20 is further used to determine the current segmentation interval according to a preset requirement;

[0140] The target lane line is segmented according to the fixed endpoint and the current segmentation interval to generate segmented short solid line segments.

[0141] In one embodiment, the segmentation module 20 is further configured to obtain a known segmented short solid line segment corresponding to the target lane line when the association state is associated;

[0142] According to the endpoints of the known segmented short solid line segments, matching endpoints are determined in the target lane line as the fixed endpoints.

[0143] In one embodiment, the segmentation module 20 is further used to segment the target lane line according to the fixed endpoints, and determine the interval between the first segmentation short solid line segment and the current segmentation;

[0144] Determine the remaining lane lines according to the first segmented short solid line segment;

[0145] According to the current segmentation interval and the fixed endpoint, the remaining lane line is segmented and expanded to obtain a second segmented short solid line segment;

[0146] The first split short solid line segment and the second split short solid line segment are used as the split short solid line segment.

[0147] In one embodiment, the segmentation module 20 is further configured to obtain a real lane line and a virtual lane line in the target lane line when the attribute of the target lane line is a mixed lane line;

[0148] Performing visual rendering on the actual lane line;

[0149] The virtual lane line is used as the target lane line, and the step of determining a fixed endpoint in the target lane line according to the association state is returned to be executed.

[0150] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0151] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0152] In addition, for technical details not fully described in this embodiment, reference may be made to the virtual lane line tracking and rendering method provided in any embodiment of the present invention, which will not be described in detail here.

[0153] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0154] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0155] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0156] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A virtual lane line tracking and rendering method, characterized in that: The virtual lane line tracking and rendering method comprises: Acquire a target lane line, track and compare the target lane line with the rendered lane line, and determine the association state between the target lane line and the rendered lane line; Obtaining the attributes of the target lane line; When the attribute of the target lane line is a virtual lane line, determining a fixed endpoint in the target lane line according to the association state; Segmenting the target lane line according to the fixed endpoints to generate segmented short solid line segments; Performing visual rendering on the segmented short solid line segments; Determining the fixed endpoint in the target lane line according to the association state includes: When the association state is unassociated, the endpoints at both ends of the target lane line and the endpoint positions corresponding to the endpoints are obtained, and according to the endpoint positions, whether the endpoints are respectively located in the front range and the rear range of the vehicle, when the endpoints are respectively located in the front range and the rear range of the vehicle, the endpoint located in the rear range of the vehicle is used as the fixed endpoint; When the association state is associated, a known segmented short solid line segment corresponding to the target lane line is obtained, and a matching endpoint is determined in the target lane line as the fixed endpoint according to an endpoint of the known segmented short solid line segment.

2. The method according to claim 1, characterized in that The step of determining whether the endpoint is located in the front range of the vehicle and behind the rear range of the vehicle according to the endpoint position, further includes: When the endpoints are not located in the front range and the rear range of the vehicle respectively, the endpoints among the endpoints that meet the preset approach condition are used as the fixed endpoints.

3. The method according to claim 2, characterized in that The step of segmenting the target lane line according to the fixed endpoints to generate segmented short solid line segments includes: When the association state is no association, determining the current segmentation interval according to preset requirements; The target lane line is segmented according to the fixed endpoint and the current segmentation interval to generate segmented short solid line segments.

4. The method according to claim 1, characterized in that The step of segmenting the target lane line according to the fixed endpoints to generate segmented short solid line segments includes: When the association state is associated, the target lane line is segmented according to the fixed endpoints to determine the interval between the first segmented short solid line segment and the current segmentation; Determine the remaining lane lines according to the first segmented short solid line segment; According to the current segmentation interval and the fixed endpoint, the remaining lane line is segmented and expanded to obtain a second segmented short solid line segment; The first split short solid line segment and the second split short solid line segment are used as the split short solid line segment.

5. The method according to claim 1, characterized in that After acquiring the attribute of the target lane line, the method further includes: When the attribute of the target lane line is a mixed lane line, obtaining a real lane line and a virtual lane line in the target lane line; Performing visual rendering on the actual lane line; The virtual lane line is used as the target lane line, and the step of determining a fixed endpoint in the target lane line according to the association state is returned to be executed.

6. A virtual lane line tracking and rendering device, characterized in that: The virtual lane line tracking and rendering device comprises: An acquisition module, used to acquire a target lane line, track and compare the target lane line with the rendered lane line, and determine the association state between the target lane line and the rendered lane line; The acquisition module is further used to acquire the attributes of the target lane line; A segmentation module, used for determining a fixed endpoint in the target lane line according to the association state when the attribute of the target lane line is a virtual lane line; The segmentation module is further used to segment the target lane line according to the fixed endpoints to generate segmented short solid line segments; A rendering module, used for visually rendering the segmented short solid line segments; The segmentation module is further used to obtain the endpoints at both ends of the target lane line and the endpoint positions corresponding to each of the endpoints when the association state is unassociated, and determine whether the endpoints are respectively located in the front range and the rear range of the vehicle according to the endpoint positions, and when the endpoints are respectively located in the front range and the rear range of the vehicle, the endpoint located in the rear range of the vehicle is used as the fixed endpoint; When the association state is associated, a known segmented short solid line segment corresponding to the target lane line is obtained, and a matching endpoint is determined in the target lane line as the fixed endpoint according to an endpoint of the known segmented short solid line segment.

7. A virtual lane line tracking and rendering device, characterized in that: The device comprises: a memory, a processor, and a virtual lane line tracking and rendering program stored in the memory and executable on the processor, wherein the virtual lane line tracking and rendering program is configured to implement the steps of the virtual lane line tracking and rendering method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a virtual lane line tracking and rendering program, and when the virtual lane line tracking and rendering program is executed by the processor, the steps of the virtual lane line tracking and rendering method according to any one of claims 1 to 5 are implemented.

Images