Lane mark determination method and device and storage medium

Abstract

The invention discloses a lane mark determination method and device and a storage medium, and relates to the technical field of automatic driving. The lane identification determination method comprises the steps that a first coordinate and a preset keyword dictionary of a target vehicle are acquired, the first coordinate is a latitude and longitude coordinate of the real world, and the preset keyword dictionary is used for recording multiple keywords corresponding to multiple lanes in a nearby area of the target vehicle; coordinate conversion is carried out on the first coordinate, a second coordinate of the target vehicle is obtained, and the second coordinate is a two-dimensional coordinate under a coordinate system constructed with the roadside equipment as the center; coordinate conversion is carried out on the second coordinate to obtain a third coordinate of the target vehicle, and the third coordinate is a pixel coordinate of the target vehicle in the regional image; determining a target keyword according to the third coordinate; and searching a target lane identifier associated with the target keyword from the keyword dictionary. The technical problem of high complexity during lane sign calculation in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a lane marking determination method and device and storage medium. BACKGROUND

[0002] With the rapid development of intelligent transportation systems, especially the widespread application of autonomous vehicles and advanced driver assistance systems, higher requirements are placed on the speed and accuracy of lane marking calculation. Existing technical means are difficult to balance real-time, precision and computational efficiency, especially when dealing with large-scale, dynamic traffic flow, there are obvious shortcomings.

[0003] In the prior art, many systems rely on lane marking determination methods based on the relationship between target position and lane boundary. Although this method can provide necessary lane information, its inherent complexity and computationally intensive nature limit its computational efficiency, especially in dense traffic and complex road conditions. First, traditional lane marking calculation often requires multiple iterations and complex geometric matching, which not only increases the time consumption of the algorithm, but also may cause the lane information to be unable to be updated in time in a high-speed moving environment. Second, due to the diversity and complexity of the road network structure, this method needs to preprocess a large amount of geographic data, further increasing the computational cost and resource demand. Finally, frequent position queries and lane boundary judgments under high precision requirements are prone to errors, affecting the accuracy of the final lane marking assignment.

[0004] Therefore, there is an urgent need for a more efficient lane marking determination method to improve data processing speed while ensuring the accuracy of lane recognition, thereby improving the performance and reliability of the entire vehicle-road cooperation system. SUMMARY

[0005] The embodiments of the present application provide a lane marking determination method, device and storage medium to at least solve the technical problem of high complexity in calculating lane marking in the prior art.

[0006] According to an embodiment of the present application, a method for determining a lane mark is provided, comprising: obtaining a first coordinate of a target vehicle and a preset keyword dictionary, wherein the first coordinate is a longitude and latitude coordinate in a real world, and the preset keyword dictionary is used to record a plurality of keywords corresponding to a plurality of lanes in a vicinity of the target vehicle; performing coordinate conversion on the first coordinate to obtain a second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system with a roadside device as a center; performing coordinate conversion on the second coordinate to obtain a third coordinate of the target vehicle, wherein the third coordinate is a pixel coordinate of the target vehicle in a region image, and the region image is obtained by image acquisition of the vicinity by an image acquisition device; determining a target keyword according to the third coordinate, wherein the target keyword is a keyword of a current lane of the target vehicle; and searching for a target lane mark associated with the target keyword from the keyword dictionary, wherein the target lane mark is used to locate the target vehicle.

[0007] Optionally, the method further comprises: determining a region of interest corresponding to the target vehicle; obtaining lane information of a plurality of lanes in the region of interest, wherein the lane information comprises a preset lane color; for each lane, determining a plurality of pixel values of the lane according to the preset lane color; determining a plurality of keywords according to the plurality of pixel values; and determining the preset keyword dictionary according to the plurality of keywords corresponding to the plurality of lanes.

[0008] Optionally, the method further comprises: establishing a target coordinate system and determining a roadside device as a target origin, wherein the roadside device is located on both sides of the target vehicle; obtaining a fourth coordinate of the roadside device, wherein the fourth coordinate is a longitude and latitude coordinate of the roadside device in the real world; and performing coordinate conversion on the first coordinate according to the fourth coordinate to obtain the second coordinate.

[0009] Optionally, the method further comprises: determining a plurality of boundary point coordinates of the region of interest; determining a width value of the region image; and performing coordinate conversion on the second coordinate according to the plurality of boundary point coordinates and the width value to obtain the third coordinate.

[0010] Optionally, the method further comprises: determining a length value of the region image; comparing the length value and the width value to obtain a comparison result; in response to the comparison result indicating that the length value is greater than the width value, determining the target keyword according to the length value and the pixel coordinate.

[0011] Optionally, the method further comprises: in response to the comparison result indicating that the length value is less than the width value, determining the target keyword according to the width value and the pixel coordinate.

[0012] Optionally, the method further comprises: searching for a target lane index value associated with the target keyword from the keyword dictionary; and determining the target lane mark according to the target lane index value.

[0013] According to one of the embodiments of the present application, a lane identification determining device is provided, comprising: an acquisition module, configured to acquire a first coordinate of a target vehicle and a preset keyword dictionary, wherein the first coordinate is a longitude and latitude coordinate in a real world, and the preset keyword dictionary is configured to record a plurality of keywords corresponding to a plurality of lanes in a nearby area of the target vehicle; a first conversion module, configured to perform coordinate conversion on the first coordinate to obtain a second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system with a roadside device as a center; a second conversion module, configured to perform coordinate conversion on the second coordinate to obtain a third coordinate of the target vehicle, wherein the third coordinate is a pixel coordinate of the target vehicle in a region image, and the region image is obtained by image acquisition of the nearby area by an image acquisition device; a determination module, configured to determine a target keyword according to the third coordinate, wherein the target keyword is a keyword of a current lane of the target vehicle; and a search module, configured to search for a target lane mark associated with the target keyword from the keyword dictionary, wherein the target lane mark is configured to locate the target vehicle.

[0014] Optionally, the acquisition module comprises: a first determination unit, configured to determine a region of interest corresponding to the target vehicle; a first acquisition unit, configured to acquire lane information of a plurality of lanes in the region of interest, wherein the lane information comprises a preset lane color; a second determination unit, configured to determine, for each lane, a plurality of pixel values of the lane according to the preset lane color; a third determination unit, configured to determine a plurality of keywords according to the plurality of pixel values; and a fourth determination unit, configured to determine the preset keyword dictionary according to the plurality of keywords corresponding to the plurality of lanes.

[0015] Optionally, the first conversion module comprises: an establishment unit, configured to establish a target coordinate system and determine a roadside device as a target origin, wherein the roadside device is located on both sides of the target vehicle; a second acquisition unit, configured to acquire a fourth coordinate of the roadside device, wherein the fourth coordinate is a longitude and latitude coordinate of the roadside device in the real world; and a first conversion unit, configured to perform coordinate conversion on the first coordinate according to the fourth coordinate to obtain the second coordinate.

[0016] Optionally, the second conversion module comprises: a fifth determination unit, configured to determine a plurality of boundary point coordinates of the region of interest; a sixth determination unit, configured to determine a width value of the region image; and a second conversion unit, configured to perform coordinate conversion on the second coordinate according to the plurality of boundary point coordinates and the width value to obtain the third coordinate.

[0017] Optionally, the determination module comprises: a seventh determination unit, configured to determine a length value of the region image; a comparison unit, configured to compare the length value and the width value to obtain a comparison result; and an eighth determination unit, configured to determine the target keyword according to the length value and the pixel coordinate in response to the comparison result representing that the length value is greater than the width value.

[0018] Optionally, the determining module further comprises a ninth determining unit configured to determine the target keyword according to the width value and the pixel coordinate in response to the comparison result indicating that the length value is less than the width value.

[0019] Optionally, the searching module comprises a searching unit configured to search for a target lane index value associated with the target keyword from the keyword dictionary, and a tenth determining unit configured to determine the target lane identification according to the target lane index value.

[0020] According to an embodiment of the present application, an electronic device is further provided, which comprises a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the lane identification determining method in any of the above.

[0021] According to an embodiment of the present application, a non-volatile storage medium is further provided, which stores a computer program, wherein the computer program is configured to execute the lane identification determining method in any of the above when running.

[0022] According to an embodiment of the present application, a computer program product is further provided, which stores a computer program, wherein the computer program is configured to implement the steps of the lane identification determining method in any of the above when executed by a processor.

[0023] In the embodiment of the present application, the first coordinate of the target vehicle and the preset keyword dictionary are acquired, wherein the first coordinate is the longitude and latitude coordinate in the real world, and the preset keyword dictionary is used to record a plurality of keywords corresponding to a plurality of lanes in the vicinity of the target vehicle. The first coordinate is converted to obtain the second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system with the roadside device as the center. The second coordinate is converted to obtain the third coordinate of the target vehicle, wherein the third coordinate is the pixel coordinate of the target vehicle in the region image, and the region image is obtained by image acquisition of the nearby region by the image acquisition device. The purpose of determining the target keyword according to the third coordinate is achieved, wherein the target keyword is the keyword of the current driving lane of the target vehicle. Thus, the technical effect of searching for the target lane identification associated with the target keyword from the keyword dictionary is achieved, wherein the target lane identification is used to locate the target vehicle, thereby solving the technical problem of high complexity in calculating the lane identification in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and serve to explain the principles of the application. In the drawings:

[0025] Figure 1is a flow chart of a lane marking determination method according to an embodiment of the present application;

[0026] Figure 2 is a structural block diagram of a lane marking determination apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the personnel in the art better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0028] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to an embodiment of the present application, an embodiment of a lane marking determination method is provided. It should be noted that the steps shown in the flow chart of the drawings can be executed in a computer system including at least one set of computer executable instructions, and although a logical order is shown in the flow chart, in some cases, the steps shown or described herein can be executed in an order different from that described herein.

[0030] The method embodiment can also be executed in an electronic device including a memory and a processor, a similar control device, or a vehicle terminal. Taking the vehicle terminal as an example, the vehicle terminal can include one or more processors and a memory for storing data. Optionally, the above-mentioned vehicle terminal can also include a communication device for communication function and a display device. Those skilled in the art can understand that the above-mentioned structural description is only illustrative, which does not limit the structure of the above-mentioned vehicle terminal. For example, the vehicle terminal can also include more or less components than the above-mentioned structural description, or have a different configuration from the above-mentioned structural description.

[0031] The processor can include one or more processing units. For example, the processor can include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural-network processing unit (NPU), a tensor processing unit (TPU), an artificial intelligent (AI) type processor, or the like. Different processing units can be independent components or integrated in one or more processors. In some examples, the electronic device can also include one or more processors.

[0032] The memory can be used to store a computer program, for example, a computer program corresponding to the lane identification determination method in the embodiments of the present application. The processor can implement the lane identification determination method described above by running the computer program stored in the memory. The memory can include a high-speed random access memory, and can also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, and these remote memories can be connected to the electronic device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0033] The communication device is used to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of a mobile terminal. In one example, the communication device includes a network interface controller (NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the communication device can be a radio frequency (RF) module which is used to communicate with the Internet in a wireless manner. In some embodiments of the present application, the communication device is used to connect with a mobile device such as a mobile phone or a tablet computer, and can send instructions to the vehicle terminal through the mobile device.

[0034] The display device can be a touchscreen liquid crystal display (LCD) or a touch display (also referred to as a "touchscreen" or "touch screen"). This LCD allows the user to interact with the user interface of the in-vehicle terminal. In some embodiments, the in-vehicle terminal has a graphical user interface (GUI), allowing the user to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. This human-machine interaction function may include a vehicle gear shifting function. Executable instructions for performing these human-machine interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0035] Figure 1 This is a flowchart of a method for determining lane markings according to one embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0036] Step S102: Obtain the first coordinates of the target vehicle and a preset keyword dictionary. The first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary is used to record multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle.

[0037] Optionally, the execution subject in this embodiment is the lane marking determination system. It should be noted that other electronic devices and processors can also be used as the execution subject, and no further limitations are made here.

[0038] In the technical solution provided by step S102 of the present invention, the positioning of the target vehicle is first based on its latitude and longitude coordinates in the real world, and at the same time, a preset keyword dictionary needs to be obtained simultaneously. The preset keyword dictionary is a pre-built data structure that associates lanes on the map with specific mathematical identifiers (keywords).

[0039] Specifically, the keyword for each lane is calculated based on its location on the digital map and map attributes (such as pixel resolution and viewpoint). By using the target vehicle's first coordinates, converting them into pixel positions on the map, and then calculating the keyword corresponding to that position, the corresponding lane number can be quickly found in the dictionary, thus avoiding the complex lane boundary calculation and matching process.

[0040] As an alternative implementation, the onboard GPS receiver calculates the vehicle's longitude and latitude coordinates by receiving signals from GPS satellites. This coordinate data is then transmitted to a lane marking system or a cloud server for further processing.

[0041] Specifically, obtaining a vehicle's latitude and longitude coordinates can be achieved through GPS (Global Positioning System) or similar satellite navigation technologies, which can provide precise geographical location information for the target vehicle. Latitude and longitude coordinates are a standard method of representing location on the Earth's surface, where latitude describes north-south location and longitude describes east-west location.

[0042] As an optional implementation, during the system initialization phase, multiple keywords are generated for each lane by parsing a high-precision map, and these keywords, along with the lane number, are stored in a dictionary. Furthermore, considering that road conditions may change over time, such as lane maintenance or temporary closures, the keyword dictionary needs to be dynamically updated. This means the system needs to periodically check for map updates and adjust the mapping between keywords and lane numbers based on the latest road information to ensure the continuous accuracy of lane number queries.

[0043] It is worth noting that by acquiring the latitude and longitude coordinates of the target vehicle in real time and using a preset keyword dictionary for quick lane number lookup, this technical solution significantly reduces the time and computing resources required for lane recognition.

[0044] Step S104: Perform coordinate transformation on the first coordinate to obtain the second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system constructed with the roadside equipment as the center.

[0045] In the technical solution provided by step S104 of the present invention, the first coordinates (latitude and longitude coordinates) of the target vehicle need to be transformed into a local coordinate system centered on the roadside equipment in order to achieve more efficient lane number calculation.

[0046] As an alternative implementation, the first coordinates can be transformed into coordinates relative to the local coordinate system of the roadside equipment using specific mathematical formulas. These formulas take into account the location of the roadside equipment (longitude and latitude), the location of the target vehicle, and the curvature of the Earth's surface, thus achieving a precise coordinate transformation.

[0047] As an alternative implementation, a map matching algorithm can be used to achieve coordinate transformation. This algorithm can more accurately match latitude and longitude coordinates to their corresponding positions in the local coordinate system, especially in scenarios with complex road conditions or high precision requirements.

[0048] Optionally, the local coordinate system is a coordinate system established with a fixed point (in this application, the roadside equipment) as the center, used to describe the positional relationship of the target vehicle relative to that point. In the local coordinate system, coordinates are typically expressed as horizontal and vertical distances relative to the center point.

[0049] It is worth noting that compared to directly processing latitude and longitude coordinates, using two-dimensional coordinates in a local coordinate system simplifies subsequent data processing, reduces computational load, and improves algorithm efficiency. Furthermore, compared to latitude and longitude coordinates, two-dimensional coordinates in a local coordinate system are more convenient for spatial analysis and distance calculation, providing a more intuitive and convenient framework for calculating lane markings for target vehicles.

[0050] Step S106: Perform coordinate transformation on the second coordinates to obtain the third coordinates of the target vehicle. The third coordinates are the pixel coordinates of the target vehicle within the regional image, which is obtained by acquiring images of the surrounding area using an image acquisition device.

[0051] In the technical solution provided by step S106 of the present invention, firstly, an image acquisition device (such as a camera) installed on the roadside is used to acquire images of the area near the target vehicle. Next, the second coordinates (two-dimensional coordinates in the local coordinate system) of the target vehicle need to be mapped to the pixel coordinates on the preprocessed area image to obtain the third coordinates.

[0052] Specifically, the aforementioned image acquisition devices typically have a certain field of view, enabling them to capture images of the surrounding environment. The acquired raw images may require preprocessing, such as brightness adjustment, distortion correction, and image cropping, to adapt to subsequent coordinate transformations and analysis.

[0053] As an alternative implementation, the specific parameters and resolution of the image acquisition device can be used to directly convert the coordinates of the target vehicle in the local coordinate system into pixel coordinates on the image using mathematical formulas. This method is suitable for scenarios where the device parameters are known and can complete the coordinate transformation quickly and directly.

[0054] As an alternative implementation, a mapping matrix can be determined during the initial equipment installation process through calibration. This matrix contains all transformation parameters from the local coordinate system to the image pixel coordinate system. In subsequent applications, the third coordinate on the regional image can be obtained by simply multiplying the second coordinate of the target vehicle by the mapping matrix.

[0055] Optionally, pixel coordinates can be understood as each pixel in a digital image having a specific coordinate, usually represented as (x, y), reflecting the pixel's position in the image.

[0056] It's worth noting that by converting the target vehicle's second coordinates to third coordinates (pixel coordinates), the vehicle's position in the image can be visually displayed, facilitating subsequent image processing and lane recognition. In the field of image analysis, pixel coordinates are the basic unit of operation; therefore, directly using third coordinates for lane recognition and vehicle tracking can significantly improve the efficiency of the algorithm.

[0057] Step S108: Determine the target keyword based on the third coordinate, where the target keyword is the keyword of the target vehicle's current driving lane.

[0058] In the technical solution provided by step S108 of the present invention, firstly, the regional image needs to be segmented to identify different lane regions. Therefore, the system needs to analyze the image, identify the position of the lane lines, and determine the pixel region of each lane based on the lane lines and the pixel distribution in the image. After determining the pixel region of the lane, the target keyword can be obtained by applying specific calculation rules based on the third coordinate of the target vehicle (i.e., its pixel position in the image).

[0059] Specifically, image segmentation is a computer vision technique used to divide the set of pixels in an image into multiple meaningful regions or objects.

[0060] Specifically, the above calculation rules are typically based on the relative position and shape features of the lanes in the image, as well as the image size and resolution. The third coordinates of the target vehicle are input into a preset calculation formula to output a lane keyword related to the vehicle's current position.

[0061] As an alternative implementation, a pixel histogram of the lane region is constructed to analyze the pixel features at the third coordinate location of the target vehicle. For example, if the target vehicle is located in a pixel-dense region of a specific lane in the image, its lane keyword can be determined through the histogram statistical characteristics of that region. This method is suitable for scenarios with clear lane boundaries and obvious pixel features.

[0062] Optionally, a pixel histogram is a way to statistically analyze the distribution of pixel intensity in an image, and is often used for image feature analysis and pattern recognition.

[0063] It is worth noting that the determination of target keywords is based on image processing and computation, which can quickly identify the lane number of the target vehicle currently traveling in, without the need for complex lane boundary matching algorithms. Furthermore, by encoding lane information into keywords, the logical processing of lane identification is simplified, making the lane number calculation process more concise, easier to implement, and easier to maintain.

[0064] Step S110: Search for the target lane identifier associated with the target keyword in the keyword dictionary, where the target lane identifier is used to locate the target vehicle.

[0065] In the technical solution provided in step S110 of the present invention, the keyword dictionary is constructed based on the digital description of lanes and the parameters of the image acquisition device. Each lane is assigned multiple keywords, which represent the positional characteristics of the lane under specific conditions. The dictionary maps these keywords to lane identifiers, which can be numbers, letters, or a combination of numbers and letters, used to uniquely identify a specific lane. When the third coordinate of the target vehicle is converted into a target keyword, the system needs to query the keyword dictionary for the target lane identifier corresponding to that keyword.

[0066] As an alternative implementation, a hash table can be used as the key dictionary. Hash tables can directly locate lane markers using keywords, avoiding the inefficiency of linear search, and are particularly suitable for fast queries of large-scale data. This method can significantly improve the real-time performance and reliability of lane localization in densely trafficked scenarios.

[0067] As an alternative implementation, if the keyword distribution follows a certain regularity, a tree data structure such as a binary search tree or a B-tree can be used to implement the keyword dictionary. Tree structures can provide more ordered query paths and may be more efficient than hash tables for scenarios with uneven keyword distribution.

[0068] Optionally, a hash table is a data structure that uses a hash function to directly convert keys into storage locations, thereby enabling fast data lookup and retrieval.

[0069] Optionally, a binary search tree is a tree-like data structure in which each node has at most two child nodes, and the value of a node is greater than the value of its left child node and less than the value of its right child node. It is suitable for fast searching of ordered keywords.

[0070] Optionally, a B-tree is a self-balancing tree data structure used in databases and file systems to store large amounts of data, enabling efficient insertion, deletion, and search operations.

[0071] It's worth noting that the keyword dictionary's query mechanism enables rapid lane identification, ensuring the immediacy and accuracy of lane location even under high-frequency vehicle detection and complex road conditions. Employing an efficient data structure for keyword queries reduces the demand for computing resources, allowing the system to operate under limited hardware conditions. Furthermore, the high efficiency of keyword matching improves the overall system's response speed to lane information, which is particularly important for traffic management and autonomous driving systems with high real-time requirements.

[0072] Steps S102 to S110 above show that, in this invention, the first coordinates of the target vehicle and a preset keyword dictionary are obtained. The first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary records multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle. The first coordinates are transformed to obtain the second coordinates of the target vehicle. The second coordinates are two-dimensional coordinates in a coordinate system constructed with the roadside equipment as the center. The second coordinates are transformed to obtain the third coordinates of the target vehicle. The third coordinates are the pixel coordinates of the target vehicle in the regional image. The regional image is obtained by acquiring images of the vicinity using an image acquisition device. This achieves the purpose of determining the target keyword based on the third coordinate. The target keyword is the keyword of the target vehicle's current driving lane. This achieves the technical effect of finding the target lane identifier associated with the target keyword from the keyword dictionary. The target lane identifier is used to locate the target vehicle, thereby solving the technical problem of high complexity in calculating lane identifiers in the prior art.

[0073] The method described in this embodiment will now be described in further detail.

[0074] Step S1021: Determine the region of interest corresponding to the target vehicle;

[0075] Step S1022: Obtain lane information for multiple lanes within the area of ​​interest, wherein the lane information includes preset lane colors;

[0076] Step S1023: For each lane, determine multiple pixel values ​​of the lane based on the preset lane color;

[0077] Step S1024: Determine multiple keywords based on multiple pixel values;

[0078] Step S1025: Determine a preset keyword dictionary based on multiple keywords corresponding to multiple lanes.

[0079] In this embodiment, a small region containing the target vehicle is determined from the image acquired by the roadside equipment, called the region of interest (ROI). The ROI is selected based on the third coordinate (pixel coordinate) of the target vehicle, ensuring that the region contains lane information around the target vehicle. Lane information within the ROI is extracted, including but not limited to lane color information. Lane color can be used as a feature to distinguish lanes in image processing. For each identified lane, multiple pixel values ​​in the image are determined based on the image analysis results of the preset lane color. Then, based on the distribution characteristics of multiple pixel values ​​of the lane, such as the pixel coordinates of the lane centerline, multiple keywords corresponding to the pixel values ​​are calculated. Finally, based on the multiple lanes and their corresponding keywords obtained above, a preset keyword dictionary is constructed, and each keyword is bound to the corresponding lane identifier.

[0080] As an alternative implementation, the region of interest can be determined by automatically setting a fixed-size rectangular bounding box as the region of interest based on the size of the target vehicle and the width information of the adjacent lanes, so as to include the target vehicle and the lane area around it.

[0081] As an optional implementation, for color images, by setting a specific color threshold, the image is segmented into different color regions, thereby identifying the lane region corresponding to the preset lane color.

[0082] Optionally, thresholding is an image processing technique that divides an image into two regions, foreground and background, by setting a threshold for the image's grayscale or color.

[0083] Optionally, in image analysis, to improve processing efficiency, a small region containing the target object can be selected for specialized analysis, which is called the region of interest.

[0084] It is worth noting that effectively extracting lane color information from images provides a foundation for lane recognition, and generating keywords through pixel value analysis enables the rapid identification of different lanes, improving the efficiency of subsequent lane recognition. Furthermore, the construction of a pre-defined keyword dictionary ensures that the system can quickly query lane identifiers based on keywords, providing data support for real-time lane number calculation.

[0085] Step S1041: Establish the target coordinate system and determine the roadside equipment as the target origin, wherein the roadside equipment is located on both sides of the target vehicle;

[0086] Step S1042: Obtain the fourth coordinate of the roadside device, wherein the fourth coordinate is the latitude and longitude coordinate of the roadside device in the real world;

[0087] Step S1043: Perform coordinate transformation on the first coordinate based on the fourth coordinate to obtain the second coordinate.

[0088] In this embodiment, a local coordinate system is established near the roadside equipment. The origin of this coordinate system is located on one of the roadside equipment. The roadside equipment is usually installed on both sides of the road. Therefore, this coordinate system can provide the coordinate information of the target vehicle's position relative to the equipment, with the equipment as the reference point. Then, based on the latitude and longitude coordinates (fourth coordinate) of the roadside equipment in the real-world coordinate system, the first coordinate of the target vehicle in the real-world coordinate system is converted into the second coordinate in the target coordinate system. This usually involves the conversion from geodetic coordinates to a local coordinate system.

[0089] Specifically, the formula for converting the target vehicle's first coordinate in the real-world coordinate system to its second coordinate in the target coordinate system is as follows:

[0090] x=(lon-lon_base)*111319.49079327*cos(lat*0.01745329) (1)

[0091] y=(lat-lat_base)*110946.25761656 (2)

[0092] Where x is the x-value of the second coordinate; y is the y-value of the second coordinate;

[0093] lon represents the longitude value in the first coordinate system to be converted; lat represents the latitude value in the first coordinate system to be converted.

[0094] lon_base is the longitude value of the fourth coordinate of the roadside device; lat_base is the latitude value of the fourth coordinate of the roadside device.

[0095] As an optional implementation, the fourth coordinate of the roadside equipment can be obtained by using an integrated positioning system or an external positioning service to automatically obtain the real-time latitude and longitude coordinates of the roadside equipment, which is suitable for scenarios where the location of the equipment may change.

[0096] As an optional implementation, the fourth coordinate of the roadside equipment can also be obtained by manually measuring and recording the latitude and longitude coordinates of the roadside equipment during the initial stage of equipment installation, and inputting them into the system as the fourth coordinate.

[0097] Optionally, the target coordinate system is a local coordinate system established with the roadside equipment as the origin, used to describe the relative position of the target vehicle with respect to the roadside equipment.

[0098] It's worth noting that converting the absolute position of the target vehicle to its relative position with respect to the roadside equipment simplifies the computational complexity of location tracking and improves tracking efficiency. Furthermore, compared to directly processing data in the real-world coordinate system, using data in the target coordinate system reduces computational resource consumption and improves system processing capabilities.

[0099] Step S1061: Determine the coordinates of multiple boundary points of the region of interest;

[0100] Step S1062: Determine the width value of the region image;

[0101] Step S1063: Perform coordinate transformation on the second coordinate based on the coordinates of multiple boundary points and width values ​​to obtain the third coordinate.

[0102] In this embodiment, the region of interest typically contains important information about the target vehicle, such as lane lines and road signs. Therefore, it is necessary to determine the coordinates of multiple boundary points of the region of interest. In order to perform coordinate transformation, it is also necessary to determine the width value of the region image corresponding to the region of interest. Furthermore, the coordinates of the boundary points in the target coordinate system and the width value of the region image can be used to perform coordinate transformation, converting the second coordinate (coordinates in the target coordinate system) into the third coordinate (pixel coordinates on the image).

[0103] Specifically, the formula for converting the second coordinate (coordinates in the target coordinate system) to the third coordinate (pixel coordinates on the image) is as follows:

[0104] pixel x =floor(xx) min )*pixel2dist (3)

[0105] pixel y = -1*floor(yy) min )*pixel2dist+height (4)

[0106] Where, x min x max y min y max For multiple boundary points of the region of interest;

[0107] pixel2dist is used to represent pixel resolution.

[0108] height represents the width of the region image, and the specific calculation formula is as follows:

[0109] height=ceil((y max -y min ) * pixel2dist) (5)

[0110] Among them, pixel x pixel y These are the pixel coordinates to be converted.

[0111] As an optional implementation, during the image preprocessing stage, the operator can manually delineate the boundaries of the region of interest by inputting the pixel coordinates of the boundary points on the image and then converting them into coordinates in the target coordinate system. Alternatively, computer vision technology can be used to automatically identify and mark the lane line boundaries in the image, and then obtain the coordinates of these boundary points in the target coordinate system. No specific limitation is made here.

[0112] As an optional implementation, the width value of the region image can be obtained by calculating the width value of the region of interest in the image based on the parameters of the image acquisition device, such as the lens focal length and field of view, combined with the width of the region of interest in real space.

[0113] It is worth noting that ensuring the target vehicle's coordinates in the target coordinate system can be accurately converted into pixel coordinates on the image improves the accuracy of subsequent image processing. Furthermore, by determining the coordinates of the boundary points of the region of interest and the image width value, only the image region related to the target vehicle is processed, reducing the amount of data processing and improving processing efficiency.

[0114] Step S1081: Determine the length value of the region image;

[0115] Step S1082: Compare the length value and the width value to obtain the comparison result;

[0116] Step S1083: In response to the comparison result indicating that the length value is greater than the width value, the target keyword is determined based on the length value and pixel coordinates.

[0117] In this embodiment, to determine the keyword corresponding to the lane where the target vehicle is located, it is also necessary to measure the length value of the region image corresponding to the region of interest. After obtaining the length and width values ​​of the region image, the two are compared to determine the proportional relationship of the image. If the length value is greater than the width value, it indicates that the image is more suitable for lane segmentation and keyword determination along the longitudinal direction. In this case, the keyword of the lane where the target vehicle is located needs to be determined according to the appropriate direction (i.e., length value) and image size.

[0118] Specifically, if the length of the region image is greater than its width, the formula for determining the target keyword based on the length and pixel coordinates is as follows:

[0119] haxiIndice = pixel x +pixel y *width (6)

[0120] Here, haxiIndice represents a keyword;

[0121] width represents the length of the region image, and the specific calculation formula is as follows:

[0122] width = ceil((x max -x min (7) *pixel2dist)

[0123] It is worth noting that the adaptive lane recognition strategy can flexibly adjust the lane recognition and keyword determination methods according to different image aspect ratios, enhancing the system's adaptability and robustness. Furthermore, based on image aspect ratio conditional judgment, it ensures that the most suitable method can be adopted to determine the target keyword regardless of the image aspect ratio, thereby enhancing the accuracy of lane recognition.

[0124] Step S1084: In response to the comparison result indicating that the length value is less than the width value, the target keyword is determined based on the width value and pixel coordinates.

[0125] In this embodiment, to determine the keyword corresponding to the lane where the target vehicle is located, it is also necessary to measure the length value of the region image corresponding to the region of interest. After obtaining the length and width values ​​of the region image, the two are compared to determine the proportional relationship of the image. If the length value is less than the width value, it indicates that the image is more suitable for lane segmentation and keyword determination along the lateral direction. In this case, the keyword of the lane where the target vehicle is located needs to be determined according to the appropriate direction (i.e., the width value) and the image size.

[0126] Specifically, if the length of the region image is less than its width, the formula for determining the target keyword based on the width and pixel coordinates is as follows:

[0127] haxiIndice = pixel x +pixel y *height (8)

[0128] Here, haxiIndice represents a keyword;

[0129] height represents the width of the region image, and the specific calculation formula is shown in formula (5).

[0130] It is worth noting that when the width of the image is significantly greater than its length, the system can automatically adjust its lane recognition strategy, focusing more on horizontal lane features, thus improving the adaptability and accuracy of lane recognition. Therefore, under special image ratio conditions, by using the width value, the system can analyze lane positions more accurately, thereby improving the performance of the entire lane recognition system.

[0131] Step S1101: Search for the target lane index value associated with the target keyword in the keyword dictionary;

[0132] Step S1102: Determine the target lane identifier based on the target lane index value.

[0133] In this embodiment, in the keyword dictionary constructed in step S102, the lane index value corresponding to the target keyword is searched. The keyword dictionary binds the lane attributes (such as lane index) with the keywords obtained through image analysis. Based on the found lane index value, the specific lane identifier, such as lane number or lane type, is determined. This step associates the image analysis results with the actual road information.

[0134] As an optional implementation, a hash table is constructed during system initialization, where the keyword serves as the hash key and the lane index value serves as the value. When a target keyword is received, the corresponding lane index is immediately retrieved through a query operation on the hash table, achieving efficient matching.

[0135] As an alternative implementation, an index is created between keywords and lane information during the database design phase to accelerate the query process. When a target keyword needs to be found, the search is performed directly through the index.

[0136] It is worth noting that through efficient keyword dictionary lookup, the system can quickly determine the lane index value of the target vehicle, thereby rapidly identifying the lane. Based on the lane index value, the system can accurately determine the identification information of the target lane, such as the lane number. This is helpful for subsequent traffic management decisions or autonomous driving navigation. At the same time, using hash tables or database indexes for keyword lookup greatly reduces computation time and improves the efficiency and real-time performance of the entire system in processing lane information.

[0137] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this 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. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or grid device, etc.) to execute the methods of the various embodiments of the present invention.

[0138] This embodiment also provides a lane marking determination device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0139] Figure 2This is a structural block diagram of a lane marking determination device 200 according to one embodiment of the present invention, as shown below. Figure 2 As shown, the device includes: an acquisition module 201, a first conversion module 202, a second conversion module 203, a determination module 204, and a search module 205.

[0140] The acquisition module 201 is used to acquire the first coordinates of the target vehicle and a preset keyword dictionary, wherein the first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary is used to record multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle.

[0141] The first conversion module 202 is used to perform coordinate transformation on the first coordinate to obtain the second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system constructed with the roadside equipment as the center;

[0142] The second conversion module 203 is used to perform coordinate transformation on the second coordinates to obtain the third coordinates of the target vehicle. The third coordinates are the pixel coordinates of the target vehicle in the regional image, which is obtained by acquiring images of the surrounding area using an image acquisition device.

[0143] The determination module 204 is used to determine the target keyword based on the third coordinate, wherein the target keyword is the keyword of the target vehicle's current driving lane;

[0144] The search module 205 is used to search for the target lane identifier associated with the target keyword from the keyword dictionary, wherein the target lane identifier is used to locate the target vehicle.

[0145] Optionally, the acquisition module 201 includes: a first determining unit, configured to determine the region of interest corresponding to the target vehicle; a first acquisition unit, configured to acquire lane information of multiple lanes within the region of interest, wherein the lane information includes a preset lane color; a second determining unit, configured to determine multiple pixel values ​​of each lane based on the preset lane color; a third determining unit, configured to determine multiple keywords based on the multiple pixel values; and a fourth determining unit, configured to determine a preset keyword dictionary based on the multiple keywords corresponding to the multiple lanes.

[0146] Optionally, the first conversion module 202 includes: an establishment unit, used to establish a target coordinate system and determine the roadside equipment as the target origin, wherein the roadside equipment is located on both sides of the target vehicle; a second acquisition unit, used to acquire the fourth coordinate of the roadside equipment, wherein the fourth coordinate is the latitude and longitude coordinate of the roadside equipment in the real world; and a first conversion unit, used to perform coordinate transformation on the first coordinate based on the fourth coordinate to obtain the second coordinate.

[0147] Optionally, the second conversion module 203 includes: a fifth determining unit for determining the coordinates of multiple boundary points of the region of interest; a sixth determining unit for determining the width value of the region image; and a second conversion unit for performing coordinate transformation on the second coordinates based on the multiple boundary point coordinates and the width value to obtain the third coordinates.

[0148] Optionally, the determining module 204 includes: a seventh determining unit for determining the length value of the region image; a comparison unit for comparing the length value and the width value to obtain a comparison result; and an eighth determining unit for determining the target keyword based on the length value and pixel coordinates in response to the comparison result indicating that the length value is greater than the width value.

[0149] Optionally, the determining module 204 further includes a ninth determining unit, used to determine the target keyword based on the width value and pixel coordinates in response to the comparison result indicating that the length value is less than the width value.

[0150] Optionally, the search module 205 includes: a search unit for searching for the target lane index value associated with the target keyword from the keyword dictionary; and a determination unit for determining the target lane identifier based on the target lane index value.

[0151] Embodiments of the present invention also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the lane marking determination method described above.

[0152] Optionally, in this embodiment, the electronic device may be configured to store a computer program for performing the following steps:

[0153] Step S102: Obtain the first coordinates of the target vehicle and a preset keyword dictionary, wherein the first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary is used to record multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle.

[0154] Step S104: Perform coordinate transformation on the first coordinate to obtain the second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system constructed with the roadside equipment as the center;

[0155] Step S106: Perform coordinate transformation on the second coordinates to obtain the third coordinates of the target vehicle, wherein the third coordinates are the pixel coordinates of the target vehicle in the regional image, and the regional image is obtained by acquiring images of the surrounding area using an image acquisition device.

[0156] Step S108: Determine the target keyword based on the third coordinate, wherein the target keyword is the keyword of the target vehicle's current driving lane;

[0157] Step S110: Search for the target lane identifier associated with the target keyword in the keyword dictionary, where the target lane identifier is used to locate the target vehicle.

[0158] Optionally, when the processor executes the program, it also performs the following steps: determining the region of interest corresponding to the target vehicle; obtaining lane information of multiple lanes within the region of interest, wherein the lane information includes a preset lane color; for each lane, determining multiple pixel values ​​of the lane based on the preset lane color; determining multiple keywords based on the multiple pixel values; and determining a preset keyword dictionary based on the multiple keywords corresponding to the multiple lanes.

[0159] Optionally, the processor may also perform the following steps when executing the program: establish a target coordinate system and determine the roadside equipment as the target origin, wherein the roadside equipment is located on both sides of the target vehicle; obtain the fourth coordinate of the roadside equipment, wherein the fourth coordinate is the latitude and longitude coordinate of the roadside equipment in the real world; and perform coordinate transformation on the first coordinate based on the fourth coordinate to obtain the second coordinate.

[0160] Optionally, when the processor executes the program, it also performs the following steps: determining the coordinates of multiple boundary points of the region of interest; determining the width value of the region image; and performing coordinate transformation on the second coordinates based on the multiple boundary point coordinates and the width value to obtain the third coordinates.

[0161] Optionally, the processor may further perform the following steps when executing the program: determining the length value of the region image; comparing the length value and the width value to obtain a comparison result; and determining the target keyword based on the length value and pixel coordinates in response to the comparison result indicating that the length value is greater than the width value.

[0162] Optionally, the processor also performs the following steps when executing the program: in response to the comparison result indicating that the length value is less than the width value, the target keyword is determined based on the width value and the pixel coordinates.

[0163] Optionally, the processor may also perform the following steps when executing the program: searching for the target lane index value associated with the target keyword in the keyword dictionary; and determining the target lane identifier based on the target lane index value.

[0164] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0165] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program configured to perform the lane marking determination method described above when run on a computer or processor.

[0166] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0167] Step S102: Obtain the first coordinates of the target vehicle and a preset keyword dictionary, wherein the first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary is used to record multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle.

[0168] Step S104: Perform coordinate transformation on the first coordinate to obtain the second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system constructed with the roadside equipment as the center;

[0169] Step S106: Perform coordinate transformation on the second coordinates to obtain the third coordinates of the target vehicle, wherein the third coordinates are the pixel coordinates of the target vehicle in the regional image, and the regional image is obtained by acquiring images of the surrounding area using an image acquisition device.

[0170] Step S108: Determine the target keyword based on the third coordinate, wherein the target keyword is the keyword of the target vehicle's current driving lane;

[0171] Step S110: Search for the target lane identifier associated with the target keyword in the keyword dictionary, where the target lane identifier is used to locate the target vehicle.

[0172] Optionally, the storage medium is configured to store program code for performing the following steps: determining the region of interest corresponding to the target vehicle; acquiring lane information of multiple lanes within the region of interest, wherein the lane information includes a preset lane color; for each lane, determining multiple pixel values ​​of the lane based on the preset lane color; determining multiple keywords based on the multiple pixel values; and determining a preset keyword dictionary based on the multiple keywords corresponding to the multiple lanes.

[0173] Optionally, the storage medium is configured to store program code for performing the following steps: establishing a target coordinate system and determining the roadside equipment as the target origin, wherein the roadside equipment is located on both sides of the target vehicle; obtaining the fourth coordinate of the roadside equipment, wherein the fourth coordinate is the latitude and longitude coordinate of the roadside equipment in the real world; and performing coordinate transformation on the first coordinate based on the fourth coordinate to obtain the second coordinate.

[0174] Optionally, the storage medium is configured to store program code for performing the following steps: determining the coordinates of multiple boundary points of the region of interest; determining the width value of the region image; and performing coordinate transformation on the second coordinates based on the multiple boundary point coordinates and the width value to obtain the third coordinates.

[0175] Optionally, the storage medium is configured to store program code for performing the following steps: determining the length value of the region image; comparing the length value and the width value to obtain a comparison result; and, in response to the comparison result indicating that the length value is greater than the width value, determining the target keyword based on the length value and pixel coordinates.

[0176] Optionally, the storage medium is configured to store program code for performing the following steps: in response to a comparison result indicating that the length value is less than the width value, determining the target keyword based on the width value and pixel coordinates.

[0177] Optionally, the storage medium is configured to store program code for performing the following steps: looking up the target lane index value associated with the target keyword from the keyword dictionary; and determining the target lane identifier based on the target lane index value.

[0178] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0179] Embodiments of the present invention also provide a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the steps of the lane marking determination method described above.

[0180] Optionally, in this embodiment, the computer program product described above may be configured to store a computer program for performing the following steps:

[0181] Step S102: Obtain the first coordinates of the target vehicle and a preset keyword dictionary, wherein the first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary is used to record multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle.

[0182] Step S104: Perform coordinate transformation on the first coordinate to obtain the second coordinate of the target vehicle, wherein the second coordinate is a two-dimensional coordinate in a coordinate system constructed with the roadside equipment as the center;

[0183] Step S106: Perform coordinate transformation on the second coordinates to obtain the third coordinates of the target vehicle, wherein the third coordinates are the pixel coordinates of the target vehicle in the regional image, and the regional image is obtained by acquiring images of the surrounding area using an image acquisition device.

[0184] Step S108: Determine the target keyword based on the third coordinate, wherein the target keyword is the keyword of the target vehicle's current driving lane;

[0185] Step S110: Search for the target lane identifier associated with the target keyword in the keyword dictionary, where the target lane identifier is used to locate the target vehicle.

[0186] Optionally, when the computer program executes the program, it also performs the following steps: determining the region of interest corresponding to the target vehicle; obtaining lane information of multiple lanes within the region of interest, wherein the lane information includes a preset lane color; for each lane, determining multiple pixel values ​​of the lane based on the preset lane color; determining multiple keywords based on the multiple pixel values; and determining a preset keyword dictionary based on the multiple keywords corresponding to the multiple lanes.

[0187] Optionally, when the computer program executes the program, it also performs the following steps: establishing a target coordinate system and determining the roadside equipment as the target origin, wherein the roadside equipment is located on both sides of the target vehicle; obtaining the fourth coordinate of the roadside equipment, wherein the fourth coordinate is the latitude and longitude coordinate of the roadside equipment in the real world; and performing coordinate transformation on the first coordinate based on the fourth coordinate to obtain the second coordinate.

[0188] Optionally, when the computer program executes the program, it also performs the following steps: determining the coordinates of multiple boundary points of the region of interest; determining the width value of the region image; and performing coordinate transformation on the second coordinates based on the multiple boundary point coordinates and the width value to obtain the third coordinates.

[0189] Optionally, when the computer program executes the program, it also performs the following steps: determining the length value of the region image; comparing the length value and the width value to obtain a comparison result; in response to the comparison result indicating that the length value is greater than the width value, determining the target keyword based on the length value and pixel coordinates.

[0190] Optionally, when the computer program executes the program, it also performs the following steps: in response to the comparison result indicating that the length value is less than the width value, the target keyword is determined based on the width value and the pixel coordinates.

[0191] Optionally, when the computer program executes the program, it also performs the following steps: searching for the target lane index value associated with the target keyword in the keyword dictionary; and determining the target lane identifier based on the target lane index value.

[0192] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0193] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0194] In the embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0195] The units described as separate components may or may not be physically separate. Similarly, the components shown as units may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0196] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0197] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or grid device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0198] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining lane markings, characterized in that, include: Obtain the first coordinates of the target vehicle and a preset keyword dictionary, wherein the first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary is used to record multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle; The first coordinates are transformed to obtain the second coordinates of the target vehicle, wherein the second coordinates are two-dimensional coordinates in a coordinate system constructed with the roadside equipment as the center; The second coordinates are transformed to obtain the third coordinates of the target vehicle, wherein the third coordinates are the pixel coordinates of the target vehicle in the regional image, and the regional image is obtained by acquiring images of the nearby area using an image acquisition device; The target keyword is determined based on the third coordinate, wherein the target keyword is the keyword of the target vehicle's current driving lane; The target lane identifier associated with the target keyword is searched from the keyword dictionary, wherein the target lane identifier is used to locate the target vehicle.

2. The method for determining lane markings according to claim 1, characterized in that, Obtaining the preset keyword dictionary includes: Determine the region of interest corresponding to the target vehicle; Obtain lane information for multiple lanes within the region of interest, wherein the lane information includes preset lane colors; For each lane, multiple pixel values ​​of the lane are determined based on the preset lane color; Multiple keywords are determined based on the multiple pixel values; The preset keyword dictionary is determined based on the multiple keywords corresponding to the multiple lanes.

3. The method for determining lane markings according to claim 1, characterized in that, The second coordinates are obtained by performing coordinate transformation on the first coordinates, including: Establish a target coordinate system and determine the roadside equipment as the target origin, wherein the roadside equipment is located on both sides of the target vehicle; Obtain the fourth coordinates of the roadside device, wherein the fourth coordinates are the latitude and longitude coordinates of the roadside device in the real world; The first coordinate is transformed based on the fourth coordinate to obtain the second coordinate.

4. The method for determining lane markings according to claim 2, characterized in that, The third coordinate is obtained by performing a coordinate transformation on the second coordinate, including: Determine the coordinates of multiple boundary points of the region of interest; Determine the width value of the region image; The second coordinate is transformed based on the coordinates of the multiple boundary points and the width value to obtain the third coordinate.

5. The method for determining lane markings according to claim 4, characterized in that, Determining the target keyword based on the third coordinate includes: Determine the length value of the region image; The length value and the width value are compared to obtain the comparison result; In response to the comparison result indicating that the length value is greater than the width value, the target keyword is determined based on the length value and the pixel coordinates.

6. The method for determining lane markings according to claim 5, characterized in that, The method further includes: In response to the comparison result indicating that the length value is less than the width value, the target keyword is determined based on the width value and the pixel coordinates.

7. The method for determining lane markings according to claim 1, characterized in that, The search for the target lane identifier associated with the target keyword from the keyword dictionary includes: Search the keyword dictionary for the target lane index value associated with the target keyword; The target lane identifier is determined based on the target lane index value.

8. A lane marking determination device, characterized in that, include: The acquisition module is used to acquire the first coordinates of the target vehicle and a preset keyword dictionary, wherein the first coordinates are real-world latitude and longitude coordinates, and the preset keyword dictionary is used to record multiple keywords corresponding to multiple lanes in the vicinity of the target vehicle; The first transformation module is used to transform the first coordinates to obtain the second coordinates of the target vehicle, wherein the second coordinates are two-dimensional coordinates in a coordinate system constructed with the roadside equipment as the center; The second conversion module is used to perform coordinate transformation on the second coordinates to obtain the third coordinates of the target vehicle, wherein the third coordinates are the pixel coordinates of the target vehicle in the regional image, and the regional image is obtained by acquiring images of the nearby area using an image acquisition device; The determination module is used to determine the target keyword based on the third coordinate, wherein the target keyword is the keyword of the target vehicle's current driving lane; The search module is used to search for the target lane identifier associated with the target keyword from the keyword dictionary, wherein the target lane identifier is used to locate the target vehicle.

9. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor being configured to run the computer program to perform the method for determining the lane marking according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the lane marking determination method as described in any one of claims 1 to 7 when run on a computer or processor.

Images