Lane line loss processing method, system and device and storage medium

Abstract

The invention discloses a lane line loss processing method, system and device and a storage medium. The method comprises the steps of obtaining current frame left and right lane line information and previous frame left and right lane line information of a current driving vehicle; generating a lane line flag bit according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame; judging whether the current lane line is unilaterally lost or not according to the lane line flag bit; if yes, adjusting a lost-side polynomial curve fitting function of the lost-side lane line according to an opposite-side polynomial curve fitting function of the opposite-side lane line; and reconstructing the lost lane line based on the adjusted lost side polynomial curve fitting function. Compared with the prior art in which a smooth filtering algorithm is used for local optimization and prediction or reconstruction cannot be carried out under the condition of information loss, the method has the advantages that the loss side polynomial coefficient is adjusted through the opposite side polynomial coefficient to complement the loss side lane line, so that the path planning and safe driving of the automatic driving vehicle are maintained.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving perception technology, and in particular to a method, system, device and storage medium for processing lane line loss. Background Art

[0002] The autonomous driving system relies on lane line recognition for precise positioning and path planning. The lack of lane lines may cause the vehicle to be unable to accurately determine its own position, affecting navigation accuracy.

[0003] At present, the lane line preprocessing stage uses a smoothing filter algorithm, which can help remove noise, smooth images, and enhance the continuity and clarity of lane lines in the image. However, its main function is to perform local optimization based on existing information. If the lane line is lost for a long time, it means that the lane line has not been detected for many consecutive frames in the image sequence, which is beyond the capability of the general smoothing filter algorithm.

[0004] When an autonomous vehicle encounters low light, strong backlight, damaged or snow-covered roads, and without clear lane lines to guide it, it may be difficult for the autonomous vehicle to make appropriate driving decisions, such as changing lanes and turning. This may reduce driving smoothness and safety, and increase the possibility of misjudgment by the autonomous vehicle, thereby increasing the risk of traffic accidents. Therefore, how to deal with lost lane lines to maintain the path planning and safe driving of the autonomous vehicle has become an urgent problem to be solved.

[0005] 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

[0006] The main purpose of the present invention is to provide a method, system, device and storage medium for processing lost lane lines, aiming to solve the technical problem of how to process lost lane lines to maintain path planning and safe driving of autonomous driving vehicles.

[0007] To achieve the above object, the present invention provides a method for processing lane line loss, the method for processing lane line loss comprising:

[0008] Get the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the current driving vehicle;

[0009] Generate a lane line marker according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame;

[0010] Determine whether the current lane line is lost on one side according to the lane line mark;

[0011] If so, adjusting the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line;

[0012] The lost lane line is reconstructed based on the adjusted lost side polynomial curve fitting function.

[0013] Optionally, the step of generating a lane line marker according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame includes:

[0014] Determine the left lane line lateral distance of the current frame, the left lane line lateral distance of the previous frame, the right lane line lateral distance of the current frame, and the right lane line lateral distance of the previous frame according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame;

[0015] Determine the left lane line loss result according to the left lane line lateral distance of the current frame and the left lane line lateral distance of the previous frame;

[0016] Determine the right lane line loss result according to the lateral distance of the right lane line in the current frame and the lateral distance of the right lane line in the previous frame;

[0017] A lane line marker is generated based on the left lane line loss result and the right lane line loss result, and the lane line marker is a marker value corresponding to the left and right lane line states.

[0018] Optionally, the step of adjusting the lost-side polynomial curve fitting function of the lost-side lane line according to the opposite-side polynomial curve fitting function of the opposite-side lane line comprises:

[0019] Determine the lane marking data according to the lane marking, and determine the lost side lane marking and the opposite side lane marking according to the lane marking data;

[0020] Calculate the absolute value of the lateral distance difference between the lateral distance of the opposite lane line in the current frame and the lateral distance of the opposite lane line in the previous frame;

[0021] Determining the state of the opposite lane line according to the absolute value of the lateral distance difference;

[0022] The lost-side polynomial curve fitting function of the lost-side lane line is adjusted according to the opposite-side polynomial curve fitting function of the opposite-side lane line based on the opposite-side lane line state.

[0023] Optionally, the step of determining the state of the opposite lane line according to the absolute value of the lateral distance difference includes:

[0024] Determining whether the absolute value of the lateral distance difference is greater than a preset threshold;

[0025] If the absolute value of the lateral distance difference is greater than the preset threshold, it is determined that the state of the opposite lane line is a jump state.

[0026] Optionally, the step of adjusting the lost-side polynomial curve fitting function of the lost-side lane line according to the opposite-side polynomial curve fitting function of the opposite-side lane line based on the opposite-side lane line state comprises:

[0027] When the state of the opposite lane line is a jump state, determining the opposite cubic polynomial coefficient of the opposite lane line according to the opposite polynomial curve fitting function of the opposite lane line, the opposite cubic polynomial coefficient includes the curvature change rate of the opposite lane line in the current frame, the curvature of the opposite lane line in the current frame, and the angle of the opposite lane line in the current frame;

[0028] The cubic polynomial coefficient of the lost side lane line is adjusted according to the opposite numbers corresponding to the curvature change rate of the lane line on the opposite side of the current frame, the curvature of the lane line on the opposite side of the current frame, the angle of the lane line on the opposite side of the current frame and the lateral distance of the lane line on the opposite side of the current frame.

[0029] Optionally, after the step of determining whether the absolute value of the lateral distance difference is greater than a preset threshold, the method further includes:

[0030] If the absolute value of the lateral distance difference is less than or equal to the preset threshold, it is determined that the state of the opposite lane line is not in a jump state.

[0031] Optionally, the step of adjusting the lost-side polynomial curve fitting function of the lost-side lane line according to the opposite-side polynomial curve fitting function of the opposite-side lane line based on the opposite-side lane line state further includes:

[0032] When the state of the opposite lane line is a non-jump state, determining the opposite cubic polynomial coefficient of the opposite lane line according to the polynomial curve fitting function of the opposite lane line, the opposite cubic polynomial coefficient includes the curvature change rate of the opposite lane line in the current frame, the curvature of the opposite lane line in the current frame, and the angle of the opposite lane line in the current frame;

[0033] Calculate the lateral distance of the lost side lane line according to the lane line width and the lateral distance of the opposite side lane line in the current frame;

[0034] The lost side cubic polynomial coefficient of the lost side lane line is adjusted according to the curvature change rate of the opposite side lane line of the current frame, the curvature of the opposite side lane line of the current frame, the angle of the opposite side lane line of the current frame and the lateral distance of the lost side lane line.

[0035] In addition, to achieve the above-mentioned purpose, the present invention further proposes a lane line loss processing system, the lane line loss processing system comprising:

[0036] An acquisition module is used to acquire the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the currently driven vehicle;

[0037] A generation module, used to generate lane markings according to the left and right lane information of the current frame and the left and right lane information of the previous frame;

[0038] A judgment module, used for judging whether the current lane line is lost on one side according to the lane line mark;

[0039] a calculation module, configured to adjust the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line if yes;

[0040] A reconstruction module is used to reconstruct the lost lane line based on the adjusted lost side polynomial curve fitting function.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a lane line loss processing device, which includes: a memory, a processor, and a lane line loss processing program stored in the memory and executable on the processor, and the lane line loss processing program is configured to implement the steps of the lane line loss processing method as described above.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a lane line loss processing program is stored. When the lane line loss processing program is executed by a processor, the steps of the lane line loss processing method described above are implemented.

[0043] The present invention first obtains the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the current driving vehicle, and then generates a lane line mark according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame, and then determines whether the current lane line is lost on one side according to the lane line mark; if so, the lost side polynomial curve fitting function of the lost side lane line is adjusted according to the opposite side polynomial curve fitting function of the opposite side lane line, and finally the lost lane line is reconstructed based on the adjusted lost side polynomial curve fitting function. Compared with the prior art, which uses a smoothing filter algorithm for local optimization and cannot be predicted or reconstructed in the case of missing information, if the lane line is temporarily or long-term lost in a complex environment that the smoothing filter algorithm cannot reach, such as low light, strong backlight, road damage or snow cover, the lane line may be completely invisible visually, resulting in the impact of the camera lane line recognition on the automatic driving due to the inaccurate lane line recognition, and the present embodiment adjusts the lost side polynomial coefficient by the opposite side polynomial coefficient to complete the lost side lane line, thereby maintaining the path planning and safe driving of the automatic driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1It is a structural schematic diagram of a lane line loss processing device in a hardware operating environment involved in an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of a flow chart of a first embodiment of a method for processing lane line loss according to the present invention;

[0046] Figure 3 A lane line processing flow chart of a first embodiment of a method for processing lane line loss of the present invention;

[0047] Figure 4 It is a structural block diagram of the first embodiment of the lane line loss processing system 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 1 A schematic diagram of the structure of a lane line loss processing device in a hardware operating environment according to an embodiment of the present invention.

[0051] like Figure 1 As shown, the lane line loss processing 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), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage system 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 lane line loss processing device, and may include more or less components than 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 lane line loss processing program.

[0054] exist Figure 1 In the lane line loss processing 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 lane line loss processing device of the present invention can be set in the lane line loss processing device, and the lane line loss processing device calls the lane line loss processing program stored in the memory 1005 through the processor 1001, and executes the lane line loss processing method provided in the embodiment of the present invention.

[0055] The embodiment of the present invention provides a method for processing lane line loss, referring to Figure 2 , Figure 2 Schematic diagram of the process of the first embodiment of the method for processing lane line loss of the present invention.

[0056] In this embodiment, the method for processing lane line loss includes the following steps:

[0057] Step S10: Obtain the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the currently driven vehicle.

[0058] It is easy to understand that the execution subject of this embodiment can be a lane line loss processing system with functions such as data processing, network communication and program running, or it can be other computer equipment with similar functions, etc., and this embodiment is not limited.

[0059] It should be noted that the left and right lane line information of the current frame is the left lane line information of the current frame and the right lane line information of the current frame collected in real time by the camera of the current driving vehicle, and the left and right lane line information of the previous frame is the left lane line information of the previous frame and the right lane line information of the previous frame collected in real time by the camera of the current driving vehicle.

[0060] It should be understood that the left lane line information of the current frame includes the lateral distance between the left lane line of the current frame and the camera, namely, C0 L1 、C1, the angle of the left lane line in the current frame L1 (Can indicate whether the lane line is curved to the left or to the right), the curvature of the left lane line of the current frame C2 L1 (which can indicate the curvature of the lane line) and the rate of change of the curvature of the left lane line in the current frame C3 L1 The right lane line information of the current frame includes the lateral distance between the right lane line of the current frame and the camera, i.e., C0 R1、C1, the angle of the right lane line in the current frame R1 (Can indicate whether the lane line is curved to the left or right), the curvature of the right lane line of the current frame C2 R1 (which can indicate the curvature of the lane line) and the rate of change of the curvature of the right lane line in the current frame C3 R1 .

[0061] The left lane line information of the previous frame includes the lateral distance C0 between the left lane line of the previous frame and the camera L0 , the left lane line angle of the previous frame C1 L0 , the curvature of the left lane line in the previous frame C2 L0 And the change rate of the left lane curvature in the previous frame C3 L0 The right lane line information of the previous frame includes the lateral distance C0 between the right lane line of the previous frame and the camera. R0 , the angle of the right lane line in the previous frame C1 R0 , the curvature of the right lane line in the previous frame C2 R0 And the change rate of the curvature of the right lane line in the previous frame C3 R0 .

[0062] It should also be noted that the left lane line information of the current frame, the right lane line information of the current frame, the left lane line information of the previous frame, and the right lane line information of the previous frame respectively include the types of lane lines, such as dotted lines, solid lines, etc.

[0063] Step S20: Generate lane line markers based on the left and right lane line information of the current frame and the left and right lane line information of the previous frame.

[0064] Furthermore, the lateral distance of the left lane line in the current frame, the lateral distance of the left lane line in the previous frame, the lateral distance of the right lane line in the current frame and the lateral distance of the right lane line in the previous frame are determined according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame; the left lane line loss result is determined according to the lateral distance of the left lane line in the current frame and the lateral distance of the left lane line in the previous frame; the right lane line loss result is determined according to the lateral distance of the right lane line in the current frame and the lateral distance of the right lane line in the previous frame; and the lane line flag bit is generated based on the left lane line loss result and the right lane line loss result, and the lane line flag bit is a flag value corresponding to the left and right lane line states, which can be represented by binary 0 or 1.

[0065] In a specific implementation, the number of data bits of the lane line marking position can be determined according to the type of lane line, which can be 8 bits, 4 bits, etc.

[0066] The result of left lane loss is left lane loss or left lane not lost, and the result of right lane loss is right lane loss or right lane not lost.

[0067] In this embodiment, the C0 of the current left lane line is determined. L1Is the absolute value of the value less than 1e-10 (the scientific notation of floating point numbers specified in C / C++, meaning 1.0x10 to the power of -10), and is the C1 of the left lane line in the previous frame L0 Is the absolute value of the value greater than the preset threshold (e.g. 1.5m)? If the C0 of the current left lane line L1 The absolute value of the value is less than 1e-10, and the C1 of the left lane line in the previous frame L0 If the absolute value of the value is greater than the preset threshold, it is determined that the left lane line is lost, otherwise, it is determined that the left lane line is not lost.

[0068] If the left lane line is lost, the lane width last_lane_width between the left lane line and the right lane line before it is lost is saved, and the data bit number of the lane line flag is 8 bits. It is necessary to go from right to left, and change the first bit data of the flag camera_lane_def_flag_ from 0 to 1. If the flag data (ie decimal data) is 1, it means that the left lane line is lost.

[0069] Determine the current right lane line C0 R1 Is the absolute value of the value less than 1e-10, and is the C0 of the right lane line of the previous frame R0 Is the absolute value of the value greater than the preset threshold (for example, 1.5m)? If the C0 of the current right lane line R1 The absolute value of the value is less than 1e-10, and the C0 of the right lane line in the previous frame R0 If the absolute value of the value is greater than the preset threshold, it is determined that the right lane line is lost, otherwise, it is determined that the right lane line is not lost.

[0070] If the right lane line is lost, the lane width last_lane_width between the right lane line and the left lane line before it is lost is saved, and the data bit number of the lane line flag is 8 bits. It is necessary to go from right to left, and change the second bit of the flag camera_lane_def_flag_ from 0 to 1. If the flag data (ie decimal data) is 2, it means that the right lane line is lost.

[0071] Similarly, if both the left and right lane lines are lost, the first and second data bits of the flag camera_lane_def_flag_ are changed from 0 to 1, and the flag data (ie, decimal data) is 3, indicating that the left and right lane lines are lost.

[0072] Step S30: judging whether the current lane line is lost on one side according to the lane line mark.

[0073] It should be noted that whether the lane line is lost on one side can be determined based on the lane line flag camera_lane_def_flag_.

[0074] Step S40: If yes, adjusting the lost-side polynomial curve fitting function of the lost-side lane line according to the opposite-side polynomial curve fitting function of the opposite-side lane line.

[0075] In a specific implementation, if the flag data is 1 or 2, it is determined that one side is lost, and if the flag data is 3, it is determined that both sides are lost.

[0076] Furthermore, the processing method of adjusting the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line is to determine the mark position data according to the lane line mark position, and determine the lost side lane line and the opposite side lane line according to the mark position data; calculate the absolute value of the lateral distance difference between the lateral distance of the opposite side lane line in the current frame and the lateral distance of the opposite side lane line in the previous frame; determine the state of the opposite side lane line according to the absolute value of the lateral distance difference; and adjust the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line based on the state of the opposite side lane line.

[0077] It should be understood that the lost lane line can be the left lane line or the right lane line. If the lost lane line is the left lane line, the opposite lane line is the right lane line. If the lost lane line is the right lane line, similarly, the opposite lane line is the left lane line.

[0078] In this embodiment, reference Figure 3 , Figure 3 This is a lane line processing flow chart of the first embodiment of the method for processing lane line loss of the present invention. The flow chart shows that the left lane line is judged first and then the right lane line, but in the specific implementation, there is no restriction on this. The left lane line is judged first and then the right lane line, or the right lane line is judged first and then the left lane line, etc.

[0079] It should be noted that if the flag data is 1, the lane marking on the lost side is the left lane marking, and the lane marking on the opposite side is the right lane marking.

[0080] If the flag data is 1, it means that the left lane line is lost. The processing logic is as follows:

[0081] Since the two lane lines of a lane are parallel in most cases, the cubic polynomial coefficient of the right lane line (i.e., the lateral distance C0 between the right lane line and the camera in the current frame) is used. R1 、C1, the angle of the right lane line in the current frame R1 、C2, the curvature of the right lane line in the current frame R1 And the change rate of the curvature of the right lane line in the current frame C3 R1 ), fill in the cubic polynomial coefficients of the missing left lane line (the lateral distance C0 between the left lane line and the camera in the current frame L1 、C1, the angle of the left lane line in the current frame L1, the curvature of the left lane line in the current frame C2 L1 And the change rate of the curvature of the left lane line in the current frame C3 L1 ), but the completion method is different depending on the status of the right lane line:

[0082] Further, it is determined whether the absolute value of the lateral distance difference is greater than a preset threshold; if the absolute value of the lateral distance difference is greater than the preset threshold, it is determined that the state of the opposite lane line is a jump state.

[0083] When the state of the opposite lane line is a jump state, the opposite side cubic polynomial coefficient of the opposite lane line is determined according to the opposite side polynomial curve fitting function of the opposite lane line, and the opposite side cubic polynomial coefficient includes the curvature change rate of the opposite side lane line in the current frame, the curvature of the opposite side lane line in the current frame and the angle of the opposite side lane line in the current frame; the lost side cubic polynomial coefficient of the lost side lane line is adjusted according to the opposite numbers corresponding to the curvature change rate of the opposite side lane line in the current frame, the curvature of the opposite side lane line in the current frame, the angle of the opposite side lane line in the current frame and the lateral distance of the opposite side lane line in the current frame.

[0084] In this embodiment, the right lane line jumps (i.e., the right lane line C0 in the current frame) R1 The value is the same as the right lane line C0 in the previous frame R0 The absolute value of the difference between the values ​​is greater than a preset threshold (e.g., 0.3): The left lane line C1 is missing L1 / C2 L1 / C3 L1 The value directly uses the C1 of the right lane line R1 / C2 R1 / C3 R1 Value, C0 L1 The value is the right lane line C0 R1 The opposite of a value.

[0085] Furthermore, if the absolute value of the lateral distance difference is less than or equal to a preset threshold, it is determined that the state of the opposite lane line is in a non-jump state. When the state of the opposite lane line is in a non-jump state, the opposite side cubic polynomial coefficient of the opposite lane line is determined according to the polynomial curve fitting function of the opposite lane line, and the opposite side cubic polynomial coefficient includes the curvature change rate of the opposite lane line in the current frame, the curvature of the opposite lane line in the current frame and the angle of the opposite lane line in the current frame; the lateral distance of the lost side lane line is calculated according to the lane line width and the lateral distance of the opposite lane line in the current frame; the lost side cubic polynomial coefficient of the lost side lane line is adjusted according to the curvature change rate of the opposite side lane line in the current frame, the curvature of the opposite side lane line in the current frame, the angle of the opposite side lane line in the current frame and the lateral distance of the lost side lane line.

[0086] In this embodiment, the missing left lane line C1 L1 / C2 L1 / C3 L1 The value directly uses the C1 of the right lane lineR1 / C2 R1 / C3 R1 value, but C0 L1 The value will be based on the lane width before loss last_lane_width and the right lane line C0 R1 The value is calculated by losing the width of the previous vehicle last_lane_width and the right lane C0 R1 The absolute value of the difference.

[0087] It should also be noted that if the flag data is 2, the lane line on the lost side is the right lane line, and the lane line on the opposite side is the left lane line. If the flag data is 2, the processing logic for the loss of the right lane line is consistent with the processing logic for the loss of the left lane line mentioned above.

[0088] Step S50: Reconstructing the lost lane line based on the adjusted lost-side polynomial curve fitting function.

[0089] It should be understood that, since the adjusted loss side cubic polynomial coefficients are obtained, the adjusted loss side polynomial curve fitting function is: y=C3x 3 +C2x 2 +C1x+C0, the coordinates (x, y) of the lost side lane line can be obtained, and the lost side lane line can be reconstructed according to the coordinates of the lost side lane line.

[0090] It should also be noted that if the flag data is 3, it means that both the left and right lane lines are lost. At this time, the cubic polynomial coefficients cannot be used for completion. Only external lane line data can be introduced, such as the lane line data in the high-precision map, to complete the missing lane lines.

[0091] In this embodiment, first, the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the current driving vehicle are obtained, and then the lane line mark is generated according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame, and then the lane line is judged whether the current lane line is lost on one side according to the lane line mark; if so, the lost side polynomial curve fitting function of the lost side lane line is adjusted according to the opposite side polynomial curve fitting function of the opposite side lane line, and finally the lost lane line is reconstructed based on the adjusted lost side polynomial curve fitting function. Compared with the prior art, which uses a smoothing filter algorithm for local optimization, it cannot be predicted or reconstructed in the case of missing information, and the lane line is temporarily or long-term lost, and the smoothing filter algorithm cannot reach the complex environment, such as low light, strong backlight, road damage or snow cover, etc., the lane line may be completely invisible visually, resulting in the impact of the camera lane line recognition on the automatic driving due to the inaccurate lane line recognition. In this embodiment, the lost side polynomial coefficient is adjusted by the opposite side polynomial coefficient to complete the lost side lane line, thereby maintaining the path planning and safe driving of the automatic driving vehicle.

[0092] Reference Figure 4 , Figure 4 It is a structural block diagram of the first embodiment of the lane line loss processing system of the present invention.

[0093] like Figure 4 As shown, the lane line loss processing system proposed in the embodiment of the present invention includes:

[0094] An acquisition module 4001 is used to acquire the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the currently driven vehicle;

[0095] A generation module 4002 is used to generate a lane line marker according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame;

[0096] A judgment module 4003 is used to judge whether the current lane line is lost on one side according to the lane line mark;

[0097] A calculation module 4004 is configured to adjust the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line if yes;

[0098] The reconstruction module 4005 is used to reconstruct the lost lane line based on the adjusted lost side polynomial curve fitting function.

[0099] Other embodiments or specific implementations of the lane line loss processing system of the present invention can refer to the above-mentioned method embodiments, which will not be repeated here.

[0100] 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.

[0101] 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.

[0102] 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 / random access memory, 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.

[0103] 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 method for processing lane line loss, characterized in that: The method for processing lane line loss comprises the following steps: Get the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the current driving vehicle; Generate a lane line marker according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame; Determine whether the current lane line is lost on one side according to the lane line mark; If so, adjusting the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line; The lost lane line is reconstructed based on the adjusted lost side polynomial curve fitting function.

2. The method according to claim 1, characterized in that The step of generating a lane line marker according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame comprises: Determine the left lane line lateral distance of the current frame, the left lane line lateral distance of the previous frame, the right lane line lateral distance of the current frame, and the right lane line lateral distance of the previous frame according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame; Determine the left lane line loss result according to the left lane line lateral distance of the current frame and the left lane line lateral distance of the previous frame; Determine the right lane line loss result according to the lateral distance of the right lane line in the current frame and the lateral distance of the right lane line in the previous frame; A lane line marker is generated based on the left lane line loss result and the right lane line loss result, and the lane line marker is a marker value corresponding to the left and right lane line states.

3. The method according to claim 1 or 2, characterized in that The step of adjusting the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line comprises: Determine the lane marking data according to the lane marking, and determine the lost side lane marking and the opposite side lane marking according to the lane marking data; Calculate the absolute value of the lateral distance difference between the lateral distance of the opposite lane line in the current frame and the lateral distance of the opposite lane line in the previous frame; Determining the state of the opposite lane line according to the absolute value of the lateral distance difference; The lost-side polynomial curve fitting function of the lost-side lane line is adjusted according to the opposite-side polynomial curve fitting function of the opposite-side lane line based on the opposite-side lane line state.

4. The method according to claim 3, characterized in that The step of determining the state of the opposite lane line according to the absolute value of the lateral distance difference comprises: Determining whether the absolute value of the lateral distance difference is greater than a preset threshold; If the absolute value of the lateral distance difference is greater than the preset threshold, it is determined that the state of the opposite lane line is a jump state.

5. The method according to claim 4, characterized in that The step of adjusting the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line based on the opposite side lane line state comprises: When the state of the opposite lane line is a jump state, determining the opposite cubic polynomial coefficient of the opposite lane line according to the opposite polynomial curve fitting function of the opposite lane line, the opposite cubic polynomial coefficient includes the curvature change rate of the opposite lane line in the current frame, the curvature of the opposite lane line in the current frame, and the angle of the opposite lane line in the current frame; The cubic polynomial coefficient of the lost side lane line is adjusted according to the opposite numbers corresponding to the curvature change rate of the lane line on the opposite side of the current frame, the curvature of the lane line on the opposite side of the current frame, the angle of the lane line on the opposite side of the current frame and the lateral distance of the lane line on the opposite side of the current frame.

6. The method according to claim 4, characterized in that After the step of determining whether the absolute value of the lateral distance difference is greater than a preset threshold, the method further includes: If the absolute value of the lateral distance difference is less than or equal to the preset threshold, it is determined that the state of the opposite lane line is not in a jump state.

7. The method according to claim 6, characterized in that The step of adjusting the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line based on the opposite side lane line state also includes: When the state of the opposite lane line is a non-jump state, determining the opposite cubic polynomial coefficient of the opposite lane line according to the polynomial curve fitting function of the opposite lane line, the opposite cubic polynomial coefficient includes the curvature change rate of the opposite lane line in the current frame, the curvature of the opposite lane line in the current frame, and the angle of the opposite lane line in the current frame; Calculate the lateral distance of the lost side lane line according to the lane line width and the lateral distance of the opposite side lane line in the current frame; The lost side cubic polynomial coefficient of the lost side lane line is adjusted according to the curvature change rate of the opposite side lane line of the current frame, the curvature of the opposite side lane line of the current frame, the angle of the opposite side lane line of the current frame and the lateral distance of the lost side lane line.

8. A lane line loss processing system, characterized in that: The lane line loss processing system includes: An acquisition module is used to acquire the left and right lane line information of the current frame and the left and right lane line information of the previous frame of the currently driven vehicle; A generation module, used to generate lane line markings according to the left and right lane line information of the current frame and the left and right lane line information of the previous frame; A judgment module, used for judging whether the current lane line is lost on one side according to the lane line mark; a calculation module, configured to adjust the lost side polynomial curve fitting function of the lost side lane line according to the opposite side polynomial curve fitting function of the opposite side lane line if yes; The reconstruction module is used to reconstruct the lost lane line based on the adjusted lost side polynomial curve fitting function.

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

10. A storage medium, characterized in that: The storage medium stores a lane line loss processing program, and when the lane line loss processing program is executed by the processor, the steps of the lane line loss processing method according to any one of claims 1 to 7 are implemented.

Images