Method, device, equipment, medium and product for identifying lane lines

Abstract

This disclosure provides a method and apparatus for lane marking recognition, relating to the fields of artificial intelligence technology, specifically computer vision and deep learning. The specific implementation scheme comprises: acquiring a road image; determining an initial two-lane marking in the road image based on the road image and a preset lane segmentation model; determining a fitted two-lane marking based on the coordinates of unattached lane lines in the initial two-lane marking; and processing the attached regions of the initial two-lane marking using the fitted two-lane marking to obtain a target two-lane marking. This implementation method can improve the accuracy of lane marking recognition for two-lane categories.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically computer vision and deep learning technology. Background Art

[0002] Currently, in the field of autonomous driving, accurate identification of lane lines is often required to assist in generating autonomous driving strategies.

[0003] In practice, it is found that there are some double-line lane markings on the road, such as double yellow lines. When recognizing such double-line lane markings, the recognition accuracy is often poor. Summary of the Invention

[0004] The present disclosure provides a method, apparatus, device, medium, and product for identifying lane lines.

[0005] According to one aspect of the present disclosure, a method for identifying lane lines is provided, comprising: acquiring a road image; determining an initial two-lane line in the road image based on the road image and a preset lane line segmentation model; determining a fitted two-lane line based on the coordinates of unadhered lane lines in the initial two-lane line; and processing the adhered area in the initial two-lane line using the fitted two-lane line to obtain a target two-lane line.

[0006] According to another aspect of the present disclosure, a device for identifying lane lines is provided, including: an image acquisition unit, configured to acquire a road image; an initial lane line acquisition unit, configured to determine an initial two-lane line in the road image based on the road image and a preset lane line segmentation model; a lane line fitting unit, configured to determine a fitted two-lane line based on the coordinates of the non-adhesive lane lines in the initial two-lane line; and a target lane line acquisition unit, configured to use the fitted two-lane line to process the adhered area in the initial two-lane line to obtain a target two-lane line.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: one or more processors; a memory for storing one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above methods for identifying lane lines.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute any one of the above methods for identifying lane lines.

[0009] According to another aspect of the present disclosure, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the computer program implements any one of the above methods for identifying lane lines.

[0010] According to the technology disclosed herein, a method for identifying lane lines is provided, which can improve the accuracy of lane line recognition of the double-line category.

[0011] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0013] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

[0014] Figure 2 is a flowchart of an embodiment of a method for identifying lane lines according to the present disclosure;

[0015] Figure 3 is a schematic diagram of an application scenario of the method for identifying lane lines according to the present disclosure;

[0016] Figure 4 is a flowchart of another embodiment of a method for identifying lane lines according to the present disclosure;

[0017] Figure 5 is a schematic structural diagram of an embodiment of a device for identifying lane lines according to the present disclosure;

[0018] Figure 6 It is a block diagram of an electronic device used to implement the method for identifying lane lines according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] like Figure 1As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0022] The terminal devices 101, 102, and 103 interact with the server 105 via the network 104 to receive or send messages, etc. The terminal devices 101, 102, and 103 can be used for vehicle control in an autonomous driving scenario. When performing vehicle control, the terminal devices 101, 102, and 103 can capture road images and send the road images to the server 105 via the network 104, so that the server 105 can identify lane lines in the road images. The identified lane lines can include single-line lane lines or double-line lane lines, and the identified lane lines are returned to the terminal devices 101, 102, and 103, so that the terminal devices 101, 102, and 103 can generate a driving strategy suitable for autonomous driving.

[0023] Terminal devices 101, 102, and 103 can be hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices, including but not limited to mobile phones, computers, tablets, vehicle-mounted devices, etc. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules (for example, to provide distributed services), or as a single software or software module. No specific limitation is made here.

[0024] Server 105 can be a server that provides various services. For example, server 105 can obtain road images sent by terminal devices 101, 102, and 103, and based on the road image and a preset lane line segmentation model, preliminarily extract the initial two-lane line in the road image. Thereafter, based on the coordinates of the unattached lane lines in the initial two-lane line, the server 105 determines the fitted two-lane line, and uses the fitted two-lane line to process the adhered area in the initial two-lane line to obtain the target two-lane line, and returns the target two-lane line to terminal devices 101, 102, and 103 through network 104.

[0025] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server 105 is software, it can be implemented as multiple software or software modules (for example, to provide distributed services), or it can be implemented as a single software or software module. No specific limitations are given here.

[0026] It should be noted that the method for identifying lane lines provided in the embodiment of the present disclosure can be executed by the terminal devices 101, 102, 103, or by the server 105, and the device for identifying lane lines can be set in the terminal devices 101, 102, 103, or in the server 105.

[0027] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0028] Continue to refer Figure 2 , shows a process 200 of an embodiment of a method for identifying lane lines according to the present disclosure. The method for identifying lane lines in this embodiment includes the following steps:

[0029] Step 201: Acquire a road image.

[0030] In this embodiment, the execution subject (such as Figure 1 The terminal devices 101, 102, 103 or the server 105 in the embodiment can capture road images in real time using a camera mounted on a vehicle, and obtain the road images captured in real time by the camera. Alternatively, the execution entity can obtain road images from local storage or other pre-connected electronic devices. The specific method for obtaining road images is not limited in this embodiment.

[0031] Step 202 : Determine initial two-lane lines in the road image based on the road image and a preset lane line segmentation model.

[0032] In this embodiment, a preset lane segmentation model is used to extract a segmentation map corresponding to lane lines from a road image. An initial double lane line refers to a lane line composed of two parallel lane lines with a specific traffic meaning, such as a double yellow line. Optionally, the preset lane segmentation model can simultaneously extract at least two lane line categories from a road image, or it can extract only lane lines of a specific category from a road image. Lane line categories may include, but are not limited to, solid yellow, dashed yellow, solid white, dashed white, single, double, and so on, though this embodiment does not impose any restrictions on this.

[0033] Furthermore, for a preset lane segmentation model that extracts at least one lane line category from a road image, the model can pre-set a double-line category to directly extract the initial double-lane line from the road image. However, this direct double-lane line identification method requires a large number of double-lane line sample images during model training, which is rare in practice. This can lead to sample imbalance and difficulty in model training. Therefore, the model can preferably extract single lane lines from the road image, then analyze the single lane lines to obtain a double lane line composed of two single lane lines.

[0034] In some optional implementations of this embodiment, when the lane line segmentation model is used to directly identify the initial two-lane line of the two-line category from the road image, the preset lane line segmentation model can be trained based on the following steps: obtaining a sample image and sample annotation data, the sample annotation data is used to annotate a single lane line or a double lane line; inputting the sample image into the model to be trained so that the model to be trained outputs a sample recognition result corresponding to the sample image, the sample recognition result includes a lane line segmentation image, and the lane line category of the lane line segmentation image is a single lane line or a double lane line; training the model to be trained based on the sample recognition result and the sample annotation data until the model converges to obtain the preset lane line segmentation model.

[0035] Step 203 : Determine a fitted dual lane line based on the coordinates of the unconnected lane lines in the initial dual lane line.

[0036] In this embodiment, because the dual-lane lines in the road image may appear to be distantly connected, directly using the initial dual-lane lines as the final dual-lane line recognition result may result in the initial dual-lane lines being misidentified as single lane lines. To address this issue, after obtaining the initial dual-lane lines, the execution entity can select, based on the coordinates of the initial dual-lane lines, coordinates within a preset distance range from the camera's imaging position as non-adhesive lane line coordinates, and generate the corresponding fitted dual-lane lines based on the non-adhesive lane line coordinates. Alternatively, the execution entity can analyze the coordinates of the initial dual-lane lines and determine the non-adhesive lane line coordinates based on the coordinate distribution. Lane line fitting is then performed based on the non-adhesive lane line coordinates to generate fitted dual-lane lines. The fitting of the dual-lane lines can be achieved using various curve fitting methods, which are not limited in this embodiment.

[0037] In some optional implementations of this embodiment, determining the fitted dual-lane line based on the non-adhesive lane line coordinates in the initial dual-lane line may include: obtaining the lane line coordinates corresponding to the initial dual-lane line; dividing the lane line coordinates into multiple lane line coordinate groups, each lane line coordinate group containing multiple coordinates corresponding to coordinate positions, and the corresponding coordinate positions may be the same or approximately the same horizontal coordinates and different vertical coordinates; for each lane line coordinate group, calculating the lane line spacing corresponding to the lane line coordinate group; based on the lane line spacing of each group, estimating the target lane line spacing corresponding to the initial dual-lane line; determining the coordinates in the lane line coordinate group whose lane line spacing is greater than the target lane line spacing as non-adhesive lane line coordinates; based on the non-adhesive lane line coordinates, predicting the non-adhesive lane line curve to obtain the fitted dual-lane line.

[0038] In step 204 , the adhesion region in the initial two-lane line is processed using the fitted two-lane line to obtain a target two-lane line.

[0039] In this embodiment, the fitted two-lane line can be a partial two-lane line obtained by fitting the adhesion region of the initial two-lane line, or a complete two-lane line including the adhesion region and the non-adhesion region, which is not limited in this embodiment. After obtaining the fitted two-lane line, the execution entity can determine the fitted lane line coordinates corresponding to the adhesion region from the fitted two-lane line, and process the adhesion region of the initial two-lane line based on the fitted lane line coordinates to obtain the non-adhesion target two-lane line.

[0040] Continue to see Figure 3 , which shows a schematic diagram of an application scenario of the method for identifying lane lines according to the present disclosure. Figure 3 In an application scenario, an execution entity can obtain a road image 301 and then, based on the road image 301 and the lane segmentation model 302, determine an initial two-lane line 303 from the road image 301. The execution entity can then determine a non-adhesive lane line portion 3031 from the initial two-lane line 303 and obtain the non-adhesive lane line coordinates corresponding to the non-adhesive lane line portion 3031. The execution entity can then determine a fitted two-lane line 304 based on the non-adhesive lane line coordinates and use the fitted two-lane line 304 to process the adhering regions of the initial two-lane line 303, thereby eliminating adhering regions and obtaining a target two-lane line 305.

[0041] The method for identifying lane lines provided in the above-mentioned embodiment of the present disclosure can combine lane line segmentation and curve fitting, and process the adhesion area in the segmented double-line lane lines, thereby improving the recognition accuracy of the double-line lane lines.

[0042] Continue to see Figure 4, which shows a process 400 of another embodiment of the method for identifying lane lines according to the present disclosure. Figure 4 As shown, the method for identifying lane lines in this embodiment may include the following steps:

[0043] Step 401: Acquire a road image.

[0044] In this embodiment, for the detailed description of step 401 , please refer to the detailed description of step 201 , which will not be repeated here.

[0045] In step 402, the road image is input into a preset lane segmentation model to obtain the lane category corresponding to each pixel in the road image output by the preset lane segmentation model, as well as the confidence level that the pixel belongs to the lane category.

[0046] In this embodiment, the execution entity may input a road image into a preset lane segmentation model, so that the preset lane segmentation model inputs the road image into a segmentation network to obtain a segmentation map and confidence map corresponding to the road image. Based on the segmentation map and confidence map, the execution entity may determine the lane category corresponding to each pixel in the road image, as well as the confidence that the pixel belongs to that lane category. Optionally, if the preset lane segmentation model is designed to determine a specific lane category, such as a single lane category, the output data of the lane segmentation model may be the probability that each pixel in the road image belongs to a specific lane category.

[0047] Step 403 : Based on the lane line category and the confidence level, determine from the road image that the lane line category is a single lane line of the single line category.

[0048] In this embodiment, the execution entity can determine from the road image that a single lane line has a lane line category of a single line based on the recognition results of the road image, that is, the lane line category corresponding to each pixel in the road image and the confidence level that the pixel belongs to the lane line category. The single line category here refers to the category corresponding to a single lane line. Optionally, if the execution entity needs to identify a specific dual lane line, such as a double yellow line, the single line category here can be the category corresponding to the specific dual lane line, such as a single yellow line.

[0049] In some optional implementations of this embodiment, based on the lane line category and the confidence level, determining from the road image that the lane line category is a single lane line of the single line category includes: for each pixel in the road image, in response to determining that the lane line category corresponding to the pixel is the single line category and the confidence level that the pixel belongs to the single line category is greater than a preset threshold, determining the pixel as a pixel corresponding to the single lane line.

[0050] In this implementation, the execution entity may pre-set a threshold for filtering lane lines with poor accuracy. When determining from a road image that a lane line is a single lane line of the single-line category, the confidence level of each pixel belonging to the single-line category may be compared with the preset threshold. If the confidence level is greater than the preset threshold, the pixel is determined to correspond to a single lane line. Preferably, the preset threshold may be 0.8.

[0051] In some other optional implementations of this embodiment, based on the lane line category and confidence, determining that the lane line category is a single lane line of the single line category from the road image includes: in response to determining that the confidence of each pixel in the road image belongs to the single line category is less than or equal to a preset threshold, selecting a preset number of pixels in descending order of confidence belonging to the single line category as pixels corresponding to the single lane line.

[0052] In this implementation, if the confidence level of each pixel in the road image belonging to the single-line category is less than or equal to the preset threshold, to ensure that the road image contains lane markings, a preset number of pixels may be selected in descending order of confidence level as pixels corresponding to the single lane markings. This preset number may be one or any number greater than one, and is not limited in this embodiment.

[0053] Furthermore, for lane lines of other categories in the road image, each pixel in the road image can also be filtered according to the confidence level of the corresponding category to obtain lane lines of the corresponding category, thereby improving the generation accuracy of the lane lines.

[0054] Step 404: Determine an initial two-lane line based on the single-lane line.

[0055] In this embodiment, the execution entity can use the aforementioned lane segmentation model to extract single lanes. The execution entity can then analyze the single lanes to derive a dual lane composed of single lanes. For example, the execution entity can calculate the distance between each single lane and combine two single lanes whose distance is less than a threshold into an initial dual lane. Alternatively, the execution entity can calculate the distance and angle between each single lane and combine two single lanes whose distance is less than a threshold and whose angle is parallel to each other into an initial dual lane.

[0056] Step 405 : performing a preset opening and closing operation on the lane markings in the designated area of ​​the initial two-lane markings.

[0057] In this embodiment, the designated area may be an area whose shooting distance from the camera device is greater than a preset distance threshold. Because the lane lines at the visually distant end of the initial two-lane line are not smooth, the lane lines in this designated area can be smoothly segmented based on the opening and closing operations in image morphology to obtain smoothed initial two-lane lines, thereby improving the smoothness of the lane lines.

[0058] Step 406 : Determine a two-lane line within a preset distance range from the initial two-lane lines.

[0059] In this embodiment, the execution entity can pre-set a position reference point. For example, the position reference point can be set to the center position of the vehicle capturing the road image, and the coordinates of the lane line closest to the vehicle center position can be determined from the initial two-lane line. Furthermore, the execution entity can pre-set a distance range to represent the unattached front end area of ​​the lane line. After obtaining the lane line coordinates closest to the vehicle center position, the execution entity can determine, from the lane line coordinates corresponding to the initial two-lane line, lane line coordinates whose distances from the lane line coordinates are within a preset distance range. Based on the lane line coordinates within the preset distance range, the execution entity can generate two-lane lines within the preset distance range.

[0060] Step 407 : Determine the coordinates of the dual lane lines within a preset distance range as the coordinates of the unattached lane lines.

[0061] In this embodiment, the execution entity may determine the lane line coordinates within the preset distance range as the non-adhesive lane line coordinates.

[0062] Step 408 : Generate a fitted two-lane line based on the unattached lane line coordinates and a preset curve equation.

[0063] In this embodiment, the execution entity can use a preset curve equation to fit the unconnected lane line coordinates to generate a fitted dual-lane line. Specifically, the execution entity can input the unconnected lane line coordinates into the preset curve equation to generate a fitted curve, i.e., the fitted dual-lane line described above. The description of step 408 should be referred to the description of step 203 and will not be repeated here.

[0064] Step 409 : Determine the target lane line coordinates corresponding to the position of the adhesion area from the fitted dual lane lines.

[0065] In this embodiment, the fitted dual lane line includes at least the target lane line coordinates corresponding to the location of the adhesion region. After the execution entity obtains the fitted dual lane line, it can determine the target lane line coordinates corresponding to the location of the adhesion region from the fitted dual lane line by comparing the position coordinates of the fitted dual lane line with the initial dual lane line.

[0066] Step 410 : The target lane line coordinates are used to replace the lane line coordinates corresponding to the adhesion area to obtain the replaced target dual lane line.

[0067] In this embodiment, the execution entity may use the target lane line coordinates to replace the lane line coordinates corresponding to the adhesion area in the initial dual lane line to obtain the replaced target dual lane line.

[0068] The lane line identification method provided by the above-mentioned embodiments of the present disclosure can also generate fitted lane lines based on the coordinates of the unattached lane lines at the front of the initial dual-lane line and a preset curve equation. The fitted lane lines replace the lane line coordinates of the attached areas with the fitted lane lines, thereby improving the accuracy of the acquired target dual-lane line. Furthermore, by processing designated areas of the initial dual-lane line using preset opening and closing operations, the smoothness of the lane lines can be improved, further enhancing the lane line recognition effect. Furthermore, confidence filtering can be used to obtain lane line information with higher confidence, thereby improving lane line recognition accuracy.

[0069] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a device for identifying lane lines. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to electronic devices such as terminal devices and servers.

[0070] like Figure 5 As shown, the lane line recognition device 500 of this embodiment includes: an image acquisition unit 501, an initial lane line acquisition unit 502, a lane line fitting unit 503 and a target lane line acquisition unit 504.

[0071] The image acquisition unit 501 is configured to acquire a road image.

[0072] The initial lane line acquisition unit 502 is configured to determine the initial two-lane lines in the road image based on the road image and a preset lane line segmentation model.

[0073] The lane line fitting unit 503 is configured to determine the fitted dual lane line based on the coordinates of the unconnected lane lines in the initial dual lane line.

[0074] The target lane line acquisition unit 504 is configured to process the adhesion area in the initial two-lane line using the fitted two-lane line to obtain the target two-lane line.

[0075] In some optional implementations of this embodiment, the lane line fitting unit 503 is further configured to: determine the dual lane line within a preset distance range from the initial dual lane line; determine the coordinates of the dual lane line within the preset distance range as the non-adhesive lane line coordinates; and generate a fitted dual lane line based on the non-adhesive lane line coordinates and a preset curve equation.

[0076] In some optional implementations of this embodiment, the target lane line acquisition unit 504 is further configured to: determine the target lane line coordinates corresponding to the position of the adhesion area from the fitted dual-lane line; and use the target lane line coordinates to replace the lane line coordinates corresponding to the adhesion area to obtain the replaced target dual-lane line.

[0077] In some optional implementations of this embodiment, the system further includes: an image processing unit configured to perform preset opening and closing operations on the lane lines in a designated area of ​​the initial two-lane line.

[0078] In some optional implementations of this embodiment, the initial dual-lane line acquisition unit 502 is further configured to: input the road image into a preset lane line segmentation model to obtain the lane line category corresponding to each pixel in the road image output by the preset lane line segmentation model, and the confidence that the pixel belongs to the lane line category; based on the lane line category and the confidence, determine from the road image a single lane line whose lane line category is a single line category; and based on the single lane line, determine the initial dual-lane line.

[0079] In some optional implementations of this embodiment, the initial dual-lane line acquisition unit 502 is further configured to: for each pixel in the road image, in response to determining that the lane line category corresponding to the pixel is a single-line category and the confidence that the pixel belongs to the single-line category is greater than a preset threshold, the pixel is determined to be a pixel corresponding to a single lane line.

[0080] In some optional implementations of this embodiment, the initial dual-lane line acquisition unit 502 is further configured to: in response to determining that the confidence level of each pixel in the road image belonging to the single-line category is less than or equal to a preset threshold, select a preset number of pixels in descending order of confidence level belonging to the single-line category as pixels corresponding to the single-lane line.

[0081] It should be understood that the units 501 to 504 described in the device for identifying lane lines 500 are respectively the same as those in the reference Figure 2 Therefore, the operations and features described above for the method for identifying lane lines are also applicable to the device 500 and the units contained therein, and will not be repeated here.

[0082] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0083] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0084] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0085] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0086] Computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 601 performs the various methods and processes described above, such as the method for identifying lane lines. For example, in some embodiments, the method for identifying lane lines can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by computing unit 601, one or more steps of the method for identifying lane lines described above can be performed. Alternatively, in other embodiments, computing unit 601 can be configured to perform the method for identifying lane lines via any other suitable means (e.g., via firmware).

[0087] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0088] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0089] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0090] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0091] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0092] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0093] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0094] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for identifying lane lines, comprising: Acquire road images; Determining an initial two-lane line in the road image based on the road image and a preset lane line segmentation model; Determining a dual lane line within a preset distance range from the initial dual lane line; determining the coordinates of the dual lane line within the preset distance range as the unattached lane line coordinates; Generating a fitted two-lane line based on the unattached lane line coordinates and a preset curve equation; Determine target lane line coordinates corresponding to the position of the adhesion area from the fitted dual-lane line; and use the target lane line coordinates to replace the lane line coordinates corresponding to the adhesion area to obtain a replaced target dual-lane line.

2. The method according to claim 1, further comprising: Performing preset opening and closing operations on the lane lines in the designated area of ​​the initial two-lane line.

3. The method according to claim 1, wherein The determining of the initial two-lane lines in the road image based on the road image and a preset lane line segmentation model includes: Inputting the road image into the preset lane segmentation model, obtaining the lane category corresponding to each pixel in the road image output by the preset lane segmentation model, and the confidence level that the pixel belongs to the lane category; Based on the lane line category and the confidence level, determining from the road image that the lane line category is a single lane line of a single line category; Based on the single lane line, the initial two-lane line is determined.

4. The method according to claim 3, wherein: The determining, based on the lane line category and the confidence level, from the road image, that the lane line category is a single lane line of a single line category includes: For each pixel in the road image, in response to determining that the lane line category corresponding to the pixel is a single line category and the confidence that the pixel belongs to the single line category is greater than a preset threshold, the pixel is determined to be a pixel corresponding to the single lane line.

5. The method according to claim 3, wherein The determining, based on the lane line category and the confidence level, from the road image, that the lane line category is a single lane line of a single line category includes: In response to determining that the confidence level of each pixel in the road image belonging to the single line category is less than or equal to a preset threshold, a preset number of pixels are selected in descending order of confidence level of belonging to the single line category as pixels corresponding to the single lane line.

6. A device for identifying lane lines, comprising: an image acquisition unit configured to acquire a road image; an initial lane line acquisition unit, configured to determine initial two-lane lines in the road image based on the road image and a preset lane line segmentation model; a lane line fitting unit configured to determine a dual lane line within a preset distance range from the initial dual lane lines; Determining the coordinates of the dual lane lines within the preset distance range as unattached lane line coordinates; Generating a fitted two-lane line based on the unattached lane line coordinates and a preset curve equation; The target lane line acquisition unit is configured to determine the target lane line coordinates corresponding to the position of the adhesion area from the fitted dual-lane line; and use the target lane line coordinates to replace the lane line coordinates corresponding to the adhesion area to obtain the replaced target dual-lane line.

7. The apparatus according to claim 6, further comprising: The image processing unit is configured to perform a preset opening and closing operation on the lane lines in a designated area of ​​the initial two-lane line.

8. The device according to claim 6, wherein The initial dual lane line acquisition unit is further configured to: Inputting the road image into the preset lane segmentation model, obtaining the lane category corresponding to each pixel in the road image output by the preset lane segmentation model, and the confidence level that the pixel belongs to the lane category; Based on the lane line category and the confidence level, determining from the road image that the lane line category is a single lane line of a single line category; Based on the single lane line, the initial two-lane line is determined.

9. The device according to claim 8, wherein The initial dual lane line acquisition unit is further configured to: For each pixel in the road image, in response to determining that the lane line category corresponding to the pixel is a single line category and the confidence that the pixel belongs to the single line category is greater than a preset threshold, the pixel is determined to be a pixel corresponding to the single lane line.

10. The device according to claim 9, wherein The initial dual lane line acquisition unit is further configured to: In response to determining that the confidence level of each pixel in the road image belonging to the single line category is less than or equal to a preset threshold, a preset number of pixels are selected in descending order of confidence level of belonging to the single line category as pixels corresponding to the single lane line.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images