Abnormal lane line recognition methods, electronic devices and computer storage media

By performing length detection and partitioning on the lane line recognition results, abnormal lane lines are identified and filtered out, solving the problem of low lane line recognition accuracy in existing technologies and improving vehicle driving safety.

CN118115960BActive Publication Date: 2026-11-17HON HAI PRECISION INDUSTRY CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202211529892.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-30
Publication Date
2026-11-17
Estimated Expiration
2042-11-30

AI Technical Summary

Technical Problem

Existing lane line recognition methods are prone to misidentifying road markings as lane lines, resulting in low lane line recognition accuracy.

Method used

By performing length detection on the lane line recognition results, marking straight lane lines and determining the marking lines, dividing the lane interval area, and identifying and filtering out abnormal lane lines.

Benefits of technology

It improves the accuracy of lane line recognition and enhances vehicle driving safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118115960B_ABST
    Figure CN118115960B_ABST
Patent Text Reader

Abstract

This application relates to the field of intelligent driving technology, and provides an abnormal lane line recognition method, electronic device, and computer storage medium. The abnormal lane line recognition method includes: acquiring lane line recognition results corresponding to a lane line image; determining multiple lane lines in the lane line image based on the lane line recognition results; identifying lane lines among the multiple lane lines whose length is greater than a first length threshold and which are straight as first lane lines; marking the first lane lines to determine marking points; determining marking lines based on the marking points and the first lane lines; partitioning the lane line image according to the marking lines to obtain lane interval regions; and identifying lane lines within the lane interval regions in the lane line recognition results as abnormal lane lines. Using the embodiments of this application, abnormal lane lines can be identified from the lane line recognition results, improving the accuracy of lane line recognition.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to an abnormal lane line recognition method, electronic device and computer storage medium. Background Technology

[0002] During vehicle operation, the intelligent vehicle system detects lane markings on the road—a process known as lane marking recognition. Based on the detected lane markings and enabled functions, the vehicle then controls or assists in driving. Lane marking recognition has become an indispensable technology for autonomous vehicles. Whether it's lane-level positioning, traffic rule-based avoidance, or local planning, high accuracy is required for lane marking recognition. The lane marking recognition result is typically obtained by a lane marking recognition device installed on the vehicle, which processes image information acquired during vehicle operation using image algorithms.

[0003] Currently, image processing algorithms often employ deep learning schemes based on neural networks. In addition to lane lines, images acquired during vehicle movement may also contain road markings such as road arrows and speed limit signs. The process of lane line detection using image algorithms is prone to misidentifying road markings as lane lines, resulting in low accuracy in lane line recognition. Summary of the Invention

[0004] In view of this, the main objective of this application is to provide an abnormal lane line recognition method, electronic device, and computer storage medium to identify abnormal lane lines in the lane line recognition results and improve the accuracy of lane line recognition.

[0005] The first aspect of this application provides an abnormal lane line recognition method, applied to an electronic device, the abnormal lane line recognition method comprising:

[0006] Obtain the lane line recognition results corresponding to the lane line image;

[0007] Based on the lane line recognition results, multiple lane lines are determined in the lane line image;

[0008] Among the multiple lane lines, the lane line whose length is greater than the first length threshold and is a straight line is determined as the first lane line;

[0009] Mark the first lane line and determine the marking points;

[0010] The marking line is determined based on the marked points and the first lane line;

[0011] The lane line image is divided into zones based on the marked lines to obtain lane interval regions;

[0012] The lane lines within the lane interval area in the lane line recognition results are identified as abnormal lane lines.

[0013] According to an optional embodiment of this application, the step of partitioning the lane line image according to the marking lines to obtain lane spacing regions includes:

[0014] Determine the second lane line corresponding to the first lane line based on the marked line;

[0015] The area between the first lane line and the second lane line in the lane line image is defined as the lane interval area.

[0016] According to an optional embodiment of this application, determining the second lane line corresponding to the first lane line based on the marking line includes:

[0017] The lane line that intersects with the marked line and is adjacent to the first lane line is determined as the second lane line corresponding to the first lane line.

[0018] According to an optional embodiment of this application, determining the lane line that intersects with the marking line and is adjacent to the first lane line as the second lane line corresponding to the first lane line includes:

[0019] If a lane line intersects the marked line and is adjacent to the first lane line, determine the length of the lane line;

[0020] If the length of the lane line is greater than the second length threshold, the lane line is determined as the second lane line corresponding to the first lane line.

[0021] According to an optional embodiment of this application, the second lane line is a lane line located at the target orientation of the first lane line.

[0022] According to an optional embodiment of this application, marking the first lane line and determining the marking points includes:

[0023] The first lane line is marked according to the target length interval to determine the marking points.

[0024] According to an optional embodiment of this application, determining the lane line with a length greater than a first length threshold and which is a straight line among the plurality of lane lines as the first lane line includes:

[0025] The lane line whose length is greater than a first length threshold and is closest to the vehicle among the multiple lane lines is designated as the first lane line.

[0026] According to an optional embodiment of this application, determining the marking line based on the marking point and the first lane line includes:

[0027] A straight line that passes through the marked point and is perpendicular to the first lane line is defined as a marking line, and the two ends of the marking line intersect the two sides of the lane line image, respectively.

[0028] A second aspect of this application provides an electronic device, the electronic device comprising:

[0029] Memory for storing at least one instruction;

[0030] A processor is configured to implement the abnormal lane line recognition method as described above when executing the at least one instruction.

[0031] A third aspect of this application provides a computer-readable storage medium storing at least one instruction that, when executed by a processor, implements the abnormal lane line recognition method described above.

[0032] As can be seen from the above technical solutions, in this embodiment of the application, by performing length detection on multiple lane lines identified by the lane line recognition results, it is possible to initially determine that there may be abnormal lane lines among the lane lines identified by the lane line recognition results; and the first lane line after length detection is marked to determine the lane interval area; based on the lane interval area, abnormal lane lines among the lane lines identified by the lane line recognition results are further determined, which can determine as many lane lines as possible that may be abnormal in the lane line recognition results, thereby improving the accuracy of lane line detection and further improving the safety of vehicle driving. Attached Figure Description

[0033] Figure 1 This is a flowchart illustrating an abnormal lane line recognition method provided in an embodiment of the present invention.

[0034] Figure 2 This is a schematic diagram of a lane line detection scenario provided in an embodiment of this application.

[0035] Figure 3 This is a schematic diagram of a scenario for filling in dashed lane lines, provided as an embodiment of this application.

[0036] Figure 4 This is a schematic diagram of a scenario for determining lane spacing areas, provided in an embodiment of this application.

[0037] Figure 5 This is a schematic block diagram of an abnormal lane line recognition device provided in an embodiment of the present invention. Detailed Implementation

[0038] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of this application, words such as "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of words such as "exemplary," "or," and "for example" is intended to present the relevant concepts in a concrete manner.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It should be understood that, unless otherwise stated, " / " in this application means "or". For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. "At least one" means one or more. "More than one" means two or more. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, and a, b, and c. It should be understood that the order of steps shown in the flowcharts herein can be changed, and some can be omitted.

[0040] During vehicle operation, the intelligent vehicle system detects lane markings on the road—a process known as lane marking recognition. Based on the detected lane markings and enabled functions, the vehicle then controls or assists in driving. Lane markings refer to lane lines, including but not limited to white dashed and solid lines, and yellow dashed and solid lines. Lane marking recognition has become an indispensable technology for autonomous vehicles. Whether it's lane-level positioning, traffic rule-based avoidance, or local planning, high accuracy in lane marking recognition is required. Lane marking recognition results are typically obtained by a lane marking recognition device installed on the vehicle, which processes image information acquired during vehicle operation using image algorithms.

[0041] Currently, image processing algorithms often employ deep learning schemes based on neural networks. In addition to lane lines, images acquired during vehicle movement may also contain road markings such as road arrows and speed limit signs. The process of lane line detection using image algorithms is prone to misidentifying road markings as lane lines, resulting in low accuracy in lane line recognition.

[0042] To improve the accuracy of lane line recognition, embodiments of this application provide an abnormal lane line recognition method, an electronic device, and a computer-readable storage medium. The abnormal lane line recognition method can be applied to an electronic device.

[0043] The electronic devices in this application embodiment can be in-vehicle devices, mobile phones, tablet computers, desktop computers, laptop computers, handheld computers, ultra-mobile personal computers (UMPCs), netbooks, as well as cellular phones, personal digital assistants (PDAs), artificial intelligence (AI) devices, wearable devices, smart home devices, and / or smart city devices, etc. This application embodiment does not impose any special limitations on the specific form of the electronic device. The network in which the electronic device is located includes, but is not limited to: the Internet, wide area networks (WANs), metropolitan area networks (MANs), local area networks (LANs), virtual private networks (VPNs), etc.

[0044] To make the purpose, technical solution and advantages of the abnormal lane line recognition method provided in this application clearer, the abnormal lane line recognition method will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0045] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an abnormal lane line recognition method provided in an embodiment of the present invention.

[0046] The lane detection method can be applied to a lane detection device, which can be mounted on a mobile device and have a data connection with it. This mobile device can be a mobile device capable of operating on public transportation roads, such as an autonomous vehicle. Alternatively, the lane detection device can be a driver assistance system with a data connection to the mobile device.

[0047] The lane detection device can be built into a mobile device, such as a system integrated into a mobile device, or it can be externally connected to the mobile device, such as an auxiliary driving device connected to the outside of the mobile device.

[0048] Figure 2 This is a schematic diagram illustrating a lane line detection scenario provided in an embodiment of this application. In some implementations, the lane line detection method can be applied to, for example... Figure 2In the lane detection scenario shown, the mobile device 10 can be a vehicle traveling on a public transportation road, and the lane detection device 100 is built into the mobile device 10. The mobile device 10 also has one or more sensors 101 installed, and the lane detection device 100 can acquire environmental images of the mobile device 10, such as lane line images, through the sensors 101. For example, the sensors 101 may include vision sensors for acquiring environmental images around the mobile device 10. The sensors 101 can be installed in front of, behind, and / or on the roof of the mobile device 10. One or more sensors 101 installed in the mobile device 10 can be installed in the same location or in different locations; this is not limited in this embodiment of the invention. The sensors 101 can collect environmental images of a preset range around the mobile device in real time or at preset intervals, and construct a local map of the environment in which the mobile device is located based on these environmental images. The sensors 101 can acquire an image of the front of the mobile device 10, or a front view, and identify lane line image points in the front view based on an image model. The lane line image points can also be converted into a local map in the world coordinate system by combining the pose information of the mobile device 10 and the 3D environment information, so as to obtain a local map of the environment in which the mobile device 10 is located and determine the lane line position point corresponding to the lane line image point in the local map.

[0049] The lane line detection device 100 may contain a processor that can perform lane line recognition on the lane line image acquired by the sensor 101, identify lane lines and road markings in the lane line image, and obtain the lane line recognition result corresponding to the lane line image. For example, convolutional neural networks (CNNs) can be used for lane line detection.

[0050] The abnormal lane line recognition method provided in this application can be applied to an intelligent driving platform. This platform collects various road surface and road condition information, and identifies and filters out abnormal or erroneous information from the collected data, thereby providing route planning, map navigation, and other functions for different vehicles. Specifically, in this application, the intelligent driving platform can identify abnormal lane lines in various lanes, thus avoiding the misidentification of non-lane road markings (such as road stains, road signs, etc.) as lane lines, thereby correctly planning the vehicle's path and improving driving safety.

[0051] like Figure 1 As shown, the abnormal lane line identification method includes steps S101 to S107.

[0052] Step S101: Obtain the lane line recognition result corresponding to the lane line image.

[0053] The lane line recognition result can include lane line data corresponding to the lane lines and road sign data corresponding to the road signs. The positional information of the lane lines in the lane line image can be determined based on the lane line data. The positional information of the road signs in the lane line image can be determined based on the road sign data.

[0054] Step S102: Based on the lane line recognition results, determine multiple lane lines in the lane line image.

[0055] The lane line recognition result includes the length data corresponding to the lane line, which determines the length of the lane line. To avoid misidentifying road surface marks that are similar in shape to lane lines as lane lines, a first length threshold can be preset. This first length threshold is used to verify the determined lane lines. If the length of a determined lane line is greater than the first length threshold, it is more likely that the determined lane line is a lane line. If the length of a determined lane line is equal to or less than the first length threshold, the recognition result is determined to be incorrect, and the determined lane line is not a lane line. Furthermore, this embodiment of the application needs to detect road surface marks that are incorrectly marked as lane lines based on marking lines perpendicular to the lane lines. This requires determining the marking lines on straight lane lines. Therefore, it is necessary to determine whether the lane lines identified by the lane line recognition result are straight.

[0056] Lane lines in a lane line image may be dashed. To improve the processing efficiency of dashed lane lines, in some embodiments of this application, if the lane lines in the lane line image are dashed, they can be filled to obtain solid lane lines. This means filling in the gaps at both ends of the dashed lane lines. Figure 3 This is a schematic diagram of a scenario for filling in dashed lane lines, provided as an embodiment of this application. Figure 3 Image (a) shows a dashed lane line. The gaps at both ends of the dashed lane line are filled to obtain a solid lane line after the dashed lane line is filled, as shown below. Figure 3 As shown in (b).

[0057] The multiple lane lines identified by the lane line recognition results are traversed sequentially to determine whether there is a lane line with a length greater than a first length threshold and that is a straight line. If there is a lane line with a length greater than the first length threshold and that is a straight line, step S103 is executed to identify the lane line with a length greater than the first length threshold and that is a straight line as the first lane line.

[0058] Step S104: Mark the first lane line and determine the marking point.

[0059] The first lane line is marked, leaving one mark point on the first lane line each time, thus identifying at least one mark point. If the first lane line is a solid lane line, the mark point on the solid lane line is a point on the solid lane line. However, if the first lane line is a dashed lane line that has not been filled, the mark point on the dashed lane line may not be a point on the dashed lane line.

[0060] To ensure a certain length pattern among the determined marker points, a target length interval can be preset. This target length interval is used to mark the first lane line. The target length interval can be a length value preset by the user based on experience data, or it can be a length value obtained by adjusting the preset target length interval according to actual needs. This application embodiment does not limit this. For example, the target length interval can be 0.8 meters, 1 meter, 1.2 meters, 1.3 meters, 1.4 meters, 1.5 meters, 1.8 meters, 2 meters, etc. It is understood that the target length interval shown above is relative to the length interval of the actual lane line corresponding to the lane line image. The target length interval can also be set relative to the length shown in the lane line image. For example, 3 centimeters, 5 centimeters, 8 centimeters, etc. In some embodiments of this application, marking the first lane line and determining the marker points includes: marking the first lane line according to the target length interval and determining the marker points.

[0061] For example, either end of a first lane line can be selected, and the first lane line can be marked at preset target length intervals to determine marking points on the first lane line. In some embodiments of this application, multiple lane lines can be selected from one end close to the same direction, without any limitation.

[0062] To ensure the number of markers on the first lane line matches a preset number, the following steps are taken: The preset number can be a value equal to the preset number of markers, or a minimum threshold value where the number of markers is greater than or equal to the preset number. In some embodiments of this application, before marking the first lane line according to the target length interval, the following steps are included:

[0063] The target length interval is determined based on a preset number and the length of the first lane line. The difference between the preset number and the first lane line can be calculated, and the target length interval is determined by the quotient obtained by dividing the length of the first lane line by the difference. The target length interval is equal to or less than the quotient, ensuring that the number of marker points is equal to or greater than the preset number.

[0064] Step S105: Determine the marking line based on the marked point and the first lane line.

[0065] The marking line is a line that passes through the marked point. The marking line is used to verify other lane lines outside the first lane line. Each marked point on the first lane line has its corresponding marking line.

[0066] In some embodiments of this application, determining the marking line based on the marking point and the first lane line includes: determining a straight line that passes through the marking line and is perpendicular to the first lane line as the marking line, wherein the two ends of the marking line intersect the two sides of the lane line image respectively.

[0067] Step S106: Divide the lane line image into zones according to the marked lines to obtain lane interval regions.

[0068] Based on the marked lines, adjacent lane lines in the lane line image can be identified. The lane line image is then divided into zones based on these adjacent lane lines to obtain lane spacing regions. A lane spacing region is the area between two lane lines.

[0069] In some embodiments of this application, the step of partitioning the lane line image according to the marked lines to obtain lane spacing regions includes:

[0070] Determine the second lane line corresponding to the first lane line based on the marking line;

[0071] The area between the first lane line and the second lane line in the lane line image is defined as the lane spacing area. The second lane line is the lane line that is positionally adjacent to the first lane line.

[0072] Figure 4 This is a schematic diagram illustrating a scenario for determining lane spacing areas, provided as an embodiment of this application. Figure 4 As shown, a first lane line is marked, comprising multiple marker points. Based on the marker points and the first lane line, multiple marking lines are determined. A second lane line corresponding to the first lane line is determined based on the marking lines. The area between the first lane line and the second lane line in the lane line image is defined as a lane spacing region, resulting in two lane spacing regions.

[0073] In some embodiments of this application, determining the second lane line corresponding to the first lane line based on the marking line includes: determining the lane line that intersects with the marking line and is adjacent to the first lane line as the second lane line corresponding to the first lane line.

[0074] To avoid misidentifying non-lane road markings as lane lines again, in some embodiments of this application, determining the lane line intersecting the marking line and adjacent to the first lane line as the second lane line corresponding to the first lane line includes:

[0075] If a lane line intersects the marked line and is adjacent to the first lane line, determine the length of the lane line;

[0076] If the length of the lane line is greater than the second length threshold, the lane line is determined as the second lane line corresponding to the first lane line.

[0077] If the length of the lane line is equal to or less than the second length threshold, it is determined that the lane line is likely to be misidentified as a lane line, and may be a road surface mark that is not a lane line.

[0078] Some first lane lines may have adjacent lane lines on both sides. If both sides of a first lane line have adjacent lane lines, it may lead to the existence of identical lane interval areas in multiple determined lane interval regions. To avoid the waste of computing power caused by identical lane interval areas, in some embodiments of this application, a target orientation can be preset. The target orientation can be set according to the actual situation and is not limited here. It can be the left or right side, or the east, south, west, or north. The second lane line is the lane line located at the target orientation of the first lane line. For example, the second lane line is the lane line located to the left of the first lane line; or the second lane line is the lane line located to the right of the first lane line. By uniformly setting the target orientation, the occurrence of determining identical lane interval areas can be avoided, thereby avoiding the waste of computing power caused by determining identical lane interval areas.

[0079] There should be no lane lines within two adjacent lane lines, i.e., within the lane interval area. Therefore, lane lines detected by lane line monitoring within the lane interval area are abnormal lane lines. Abnormal lane lines are road markings that are not lane lines.

[0080] Step S107: Identify the lane lines within the lane interval area in the lane line identification result as abnormal lane lines.

[0081] In some embodiments of this application, after identifying lane lines within the lane spacing area as abnormal lane lines, the lane line recognition result can be corrected so that the recognition result corresponding to the abnormal lane lines in the corrected lane line recognition result is a non-lane line. The above method can filter out incorrectly identified lane lines in the lane line recognition result, improving the accuracy of lane line detection.

[0082] The abnormal lane line recognition method provided in the above embodiments can initially determine the existence of abnormal lane lines among the lane lines identified by the lane line recognition results by performing length detection on multiple lane lines identified by the lane line recognition results; and mark the first lane line after length detection to determine the lane interval area; based on the lane interval area, further determine the abnormal lane lines among the lane lines identified by the lane line recognition results. This method can identify lane lines that may be abnormal in the lane line recognition results as much as possible, thereby improving the accuracy of lane line detection and further improving the safety of vehicle driving.

[0083] When the abnormal lane line recognition method provided in the above embodiments is applied to an intelligent platform, it can identify abnormal lane lines on each road in the initial lane line recognition results, filter out abnormal lane lines in the recognition results, and store the updated lane line recognition results to plan the correct driving path for different vehicles, so that the vehicles can drive correctly.

[0084] Furthermore, in another embodiment, the abnormal lane line recognition method can also be applied to vehicles. The abnormal lane lines are identified through the vehicle system or the images obtained by the vehicle's camera are communicated with the cloud server to obtain the calculation and recognition results of the cloud server, thereby determining whether the vehicle has identified non-lane road surface traces as abnormal lane lines during driving, thus avoiding the planning of incorrect paths.

[0085] During driving, the vehicle does not need to pay attention to the identification results of all lane lines on the road surface. It can only focus on whether there are abnormal lane lines near the lane line where the vehicle is currently traveling, and identify them. For example, when the vehicle is traveling in a lane, the lane line with a length greater than a first length threshold and closest to the vehicle can be identified as the first lane line. For specific implementation steps of identifying abnormal lane lines based on the first lane line, please refer to [link to relevant documentation]. Figure 1 The relevant descriptions will not be repeated here.

[0086] To further reduce the computational load in identifying abnormal lane lines, in some embodiments of this application, a second lane line can be determined based on the lane the vehicle is in and / or the vehicle's orientation relative to a first lane line. The second lane line can be a lane line positioned relative to the first lane line. For example, if the vehicle's orientation relative to the first lane line is to the left of the first lane line, the second lane line can be a lane line to the left of the first lane line. Alternatively, if the determined first lane line is one of the two lane lines in the lane the vehicle is in, the second lane line can be the other of the two lane lines in the lane the vehicle is in. It is understood that the vehicle is between the determined first and second lane lines. Through these embodiments, only abnormal lane lines within the vehicle's current lane can be identified and path planning can be performed, eliminating the need to identify abnormal lane lines outside the vehicle's current lane, thus reducing the computational load in the abnormal lane line identification process.

[0087] In some embodiments of this application, when a vehicle identifies an abnormal lane line, the vehicle's driving path can be replanned based on the identified abnormal lane line to obtain a more accurate path plan, thereby improving the safety of vehicle driving.

[0088] Please see Figure 5 , Figure 5 This is a schematic block diagram of an electronic device provided in an embodiment of this application. The electronic device 30 can be a server or a terminal device.

[0089] The network in which the electronic device 30 is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, and virtual private network (VPN).

[0090] like Figure 5 As shown, the electronic device 30 includes a communication interface 301, a memory 302, a processor 303, an input / output (I / O) interface 304, and a bus 305. The processor 303 is coupled to the communication interface 301, the memory 302, and the I / O interface 304 via the bus 305.

[0091] The communication interface 301 is used for communication. The communication interface 301 can be an existing interface on the electronic device 30, or it can be a newly created interface on the electronic device 30. The communication interface 301 can be a network interface, such as a Wireless Local Area Network (WLAN) interface, a cellular network communication interface, or a combination thereof.

[0092] The memory 302 can be used to store operating systems and computer programs. For example, the memory 302 stores the program corresponding to the above-described abnormal lane line recognition method.

[0093] It should be understood that the memory 302 may include a program storage area and a data storage area. The program storage area may be used to store the operating system, at least one application program required by the method (such as an abnormal lane line recognition method), etc.; the data storage area may store data created based on the use of the electronic device 30, etc. Furthermore, the memory 302 may include volatile memory, and may also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one disk storage device, flash memory device, or other storage devices.

[0094] The processor 303 provides computing and control capabilities to support the operation of the entire computer device. For example, the processor 303 is used to execute computer programs stored in the memory 302 to implement the steps in the abnormal lane line recognition method described above.

[0095] It should be understood that processor 303 is a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0096] I / O interface 304 is used to provide a channel for user input or output. For example, I / O interface 304 can be used to connect various input and output devices (mouse, keyboard or 3D touch device, etc.) and displays, so that users can enter information or visualize information.

[0097] Bus 305 is used at least to provide a channel for communication between communication interface 301, memory 302, processor 303 and I / O interface 304 in electronic device 30.

[0098] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0099] In one embodiment, when the processor 303 executes the computer program stored in the memory 302 to implement the abnormal lane line recognition method, it performs the following steps:

[0100] Obtain the lane line recognition results corresponding to the lane line image;

[0101] Based on the lane line recognition results, multiple lane lines are determined in the lane line image;

[0102] Among the multiple lane lines, the lane line whose length is greater than the first length threshold and is a straight line is determined as the first lane line;

[0103] Mark the first lane line and determine the marking points;

[0104] The marking line is determined based on the marked points and the first lane line;

[0105] The lane line image is divided into zones based on the marked lines to obtain lane interval regions;

[0106] The lane lines within the lane interval area in the lane line recognition results are identified as abnormal lane lines.

[0107] Specifically, the processor 303's specific implementation method for the above instructions can be found in the description of the relevant steps in the aforementioned abnormal lane line recognition method embodiment, and will not be repeated here.

[0108] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can refer to various embodiments of the abnormal lane line recognition method of this application.

[0109] The computer-readable storage medium can be an internal storage unit of the electronic device described in the foregoing embodiments, such as a hard disk or memory of the electronic device. Alternatively, the computer-readable storage medium can be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device.

[0110] Furthermore, the computer-readable storage medium may primarily include a program storage area and a data storage area, wherein the program storage area may store the operating system, at least one application program required for a function, etc.; and the data storage area may store data created based on the use of the electronic device, etc.

[0111] The electronic device and computer-readable storage medium provided in the foregoing embodiments can initially determine the presence of abnormal lane lines among the lane lines identified by the lane line recognition results by performing length detection on multiple lane lines identified by the lane line recognition results; and mark the first lane line after length detection to determine the lane interval area; based on the lane interval area, further determine the abnormal lane lines among the lane lines identified by the lane line recognition results, which can determine the lane lines that may be abnormal in the lane line recognition results as much as possible, thereby improving the accuracy of lane line detection and further improving the safety of vehicle driving.

[0112] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0113] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, herein, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0114] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An abnormal lane mark recognition method characterized by, include: Obtain the lane line recognition results corresponding to the lane line image; Based on the lane line recognition results, multiple lane lines are determined in the lane line image; Among the multiple lane lines, the lane line whose length is greater than the first length threshold and is a straight line is determined as the first lane line; Mark the first lane line and determine the marking points; Determining a marking line based on the marking point and the first lane line includes: determining a straight line that passes through the marking point and is perpendicular to the first lane line as the marking line, wherein the two ends of the marking line intersect the two sides of the lane line image respectively; The lane line image is partitioned according to the marking lines to obtain lane interval regions, including: determining the lane line that intersects with the marking lines and is adjacent to the first lane line as the second lane line corresponding to the first lane line; and determining the area between the first lane line and the second lane line in the lane line image as the lane interval region. The lane lines within the lane interval area in the lane line recognition results are identified as abnormal lane lines.

2. The abnormal lane marking recognition method of claim 1, wherein, The step of determining the lane line that intersects with the marked line and is adjacent to the first lane line as the second lane line corresponding to the first lane line includes: If a lane line intersects the marked line and is adjacent to the first lane line, determine the length of the lane line; If the length of the lane line is greater than the second length threshold, the lane line is determined as the second lane line corresponding to the first lane line.

3. The abnormal lane marking recognition method of claim 1, wherein, The second lane line is the lane line located at the target orientation of the first lane line.

4. The abnormal lane marking recognition method of claim 1, wherein, The step of marking the first lane line and determining the marking points includes: The first lane line is marked according to the target length interval to determine the marking points.

5. The abnormal lane marking recognition method of claim 1, wherein, The step of determining the lane line with a length greater than a first length threshold and which is a straight line among the multiple lane lines as the first lane line includes: The lane line whose length is greater than a first length threshold and is closest to the vehicle among the multiple lane lines is designated as the first lane line.

6. An electronic device, comprising: The electronic device includes a memory and a processor; The memory is used to store at least one instruction; The processor is used to implement the abnormal lane line recognition method as described in any one of claims 1 to 5 when executing the at least one instruction.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the abnormal lane line recognition method as described in any one of claims 1 to 5.

Citation Information

Patent Citations

  • Method for detecting abnormal lane line in map and readable storage medium

    CN113758501A