Visual identification method for driving area of structured road

Abstract

The invention relates to the technical field of image processing, in particular to a visual identification method for a driving area of a structured road. Comprising the following steps: acquiring an image of a structured road; preprocessing the acquired image to obtain a first image processing result; carrying out image edge feature extraction on an image obtained by the first image processing result to obtain a second image processing result; determining a driving area of the structured road according to the obtained second image processing result; according to the method, the real structure information of the road can be reflected more accurately, the image quality influence caused by uneven illumination and other factors is reduced, the contour of the related structure of the road can be drawn more completely and accurately through accurate edge feature extraction, the overall recognition accuracy is remarkably improved, and the recognition efficiency is improved. And the corresponding historical road information is called by using the positioning information of the obtained image, and the historical road information and the feature lines extracted from the current image are subjected to multi-dimensional matching verification, so that the accuracy of determining the driving area is further ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for visually identifying a drivable area of ​​a structured road. Background Art

[0002] With the vigorous development of intelligent transportation systems and the gradual transition of autonomous driving technology from theoretical research to practical application, the accuracy and reliability of road environment perception are increasingly required. In the entire traffic scene understanding, accurately identifying the drivable area of ​​structured roads is a key task, which is directly related to whether the vehicle can drive safely and efficiently.

[0003] Traditional methods for identifying drivable areas on roads mainly rely on hardware facilities such as manually set road signs, but these methods have many limitations. For example, road signs may cause inaccurate or unavailable information due to factors such as wear, obstruction, and bad weather, making it difficult to adapt to the complex and changing actual road conditions and the rapid construction and renovation needs of different cities and road sections.

[0004] Based on this, the present invention provides a visual recognition method for a drivable area of ​​a structured road to solve the technical problems mentioned above. Summary of the invention

[0005] The purpose of the present invention is to provide a method for visually identifying a drivable area of ​​a structured road. The present invention obtains an image of the structured road, pre-processes the obtained image, obtains a first image processing result, and then extracts edge features of the image obtained by the first image processing result to obtain a second image processing result. According to the obtained second image processing result, the drivable area of ​​the structured road is determined; the present invention enables the grayscale image to more accurately reflect the real structural information of the road, reduces the impact of image quality caused by factors such as uneven lighting, and thus helps to more accurately identify the drivable area. Through precise edge feature extraction, the contour of the road-related structure can be more completely and accurately outlined, significantly improving the accuracy of overall recognition, and using the positioning information of the acquired image to retrieve the corresponding historical road information, and multi-dimensional matching and verification are performed on it with the characteristic lines extracted from the current image, further ensuring the accuracy of the determination of the drivable area.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The first aspect of the present invention provides a method for visually identifying a drivable area of ​​a structured road, comprising the following steps:

[0008] Acquire an image of a structured road;

[0009] Preprocessing the acquired image to obtain a first image processing result;

[0010] Extracting edge features of the image obtained by the first image processing result to obtain a second image processing result;

[0011] The drivable area of ​​the structured road is determined according to the obtained second image processing result.

[0012] The present invention is further configured as follows: the image is acquired by a vehicle-mounted camera.

[0013] The present invention is further configured as follows: the process of preprocessing the acquired image is as follows:

[0014] Grayscale the acquired image: divide the acquired image into several non-overlapping sub-areas according to the set window size; calculate the contrast value H of each sub-area; compare the obtained contrast value H with the preset grayscale threshold T. If the contrast value H>the preset grayscale threshold T, adjust the weights of the red, green and blue channels, and then use the formula Y=α2×R i,j +β2×G i,j +γ2×B i,j , where α2, β2, and γ2 are the weights of the adjusted red, green, and blue channels, respectively. The grayscale value of the sub-region is calculated. Otherwise, the formula Y = α1 × R i,j +β1×G i,j +γ1×B i,j , where α1, β1, and γ1 are the weights of the unadjusted red, green, and blue channels, respectively. The grayscale value of the sub-region is calculated to obtain a grayscale image;

[0015] Enhance the grayscale image: divide the grayscale image into several non-overlapping sub-regions according to the set window size, and use the enhancement formula to enhance the image of each sub-region. The enhancement formula is: Z = round [K (i) × 255], where, y(i) is the frequency of pixels with grayscale value i in the sub-region, and n is the total number of pixels in the sub-region.

[0016] The present invention is further configured as follows: the calculation formula of the contrast value is: In the formula, R i,j , G i,j , B i.j are the pixel values ​​of the red, green and blue channels of the pixel point (i, j) in the sub-area respectively.

[0017] The present invention is further configured as follows: the formula for adjusting the weights of the red, green and blue channels is: In the formula, k is a parameter, k∈(0,1).

[0018] The present invention is further configured as follows: the process of edge feature extraction is as follows:

[0019] Get the gradient component X of the image in the horizontal and vertical directions x , X y , calculate the gradient magnitude X and gradient direction angle θ of each pixel, where,

[0020] Compare the gradient amplitude of the pixel with the gradient amplitudes of its two adjacent pixels in the gradient direction. If the pixel is not the maximum value, set its gradient amplitude to 0.

[0021] Pixels in the image whose gradient amplitude is greater than a first preset threshold are marked as edge points, and pixels whose gradient amplitude is less than a second threshold are removed. Meanwhile, pixels between the first preset threshold and the second preset threshold are also marked as edge points if they are connected to edge points, wherein the first preset threshold is greater than the second preset threshold;

[0022] Connect each edge point to obtain an image with edge feature extraction.

[0023] The present invention is further configured as follows: the process of determining the drivable area of ​​the structured road is as follows:

[0024] Obtaining several feature lines in the image from the edge feature extracted image;

[0025] Acquire stored historical road information according to the location information of the acquired image;

[0026] Obtain road edge spacing, lane line number and lane line spacing from historical road information;

[0027] The obtained road edge spacing, lane line number and lane line spacing are matched with several feature lines respectively to obtain the drivable area of ​​the structured road.

[0028] The present invention is further configured as follows: if any of the matching results does not match, the identification of the drivable area of ​​the structured road is performed again, wherein the specific content of the matching is:

[0029] If the difference between the road edge spacing and the spacing between the two outermost feature lines is within the edge gap threshold, the road edge match is consistent;

[0030] If the number of lane lines is equal to the number of characteristic lines without the edge of the road, the number of lane lines matches;

[0031] If the lane line spacing and the adjacent feature line spacing are within the lane line spacing threshold, the lane line spacing match is consistent.

[0032] The second aspect of the present invention also provides a structured road drivable area visual recognition device, comprising:

[0033] one or more processors;

[0034] Memory;

[0035] One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to execute the above-mentioned structured road drivable area visual recognition method.

[0036] The third aspect of the present invention: also provides a computer program product, including computer instructions, wherein the computer instructions instruct a computer device to perform operations corresponding to the above method.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention obtains an image of a structured road, pre-processes the obtained image, obtains a first image processing result, then extracts edge features of the image obtained by the first image processing result to obtain a second image processing result, and determines the drivable area of ​​the structured road according to the obtained second image processing result; the present invention first dynamically adjusts the weight of calculating the gray value based on the sub-region contrast value, can better adapt to the characteristics of images under different lighting and different road scenes, so that the gray-scaled image can more accurately reflect the real structural information of the road, reduce the image quality impact caused by factors such as uneven lighting, and thus help to more accurately identify the drivable area; through accurate edge feature extraction, the outline of the road-related structure can be more completely and accurately outlined, avoid drivable area recognition errors caused by edge misjudgment, and significantly improve the accuracy of overall recognition; the corresponding historical road information is retrieved by using the positioning information of the acquired image, and it is matched and verified in multiple dimensions with the feature lines extracted from the current image, so that prior knowledge is fully used to make up for the information limitations that may exist in a single image, further ensure the accuracy of determining the drivable area, and minimize the occurrence of misidentification. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The present invention is a flowchart of a method for visually identifying a drivable area on a structured road. DETAILED DESCRIPTION

[0040] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Example:

[0042] like Figure 1 As shown, this embodiment provides a method for visually identifying a drivable area of ​​a structured road, comprising the following steps:

[0043] S1. Obtain an image of a structured road.

[0044] The image is obtained by using a vehicle-mounted camera.

[0045] In this embodiment, it should be noted that the on-board camera, as the source of image acquisition, can capture the actual scene of the structured road in front or around the vehicle in real time during driving, and provide basic data for the subsequent entire drivable area identification process. These images contain rich road information, such as road boundaries, lane lines, road surface conditions, and surrounding environment, which are the original materials for subsequent accurate analysis and identification. Moreover, the viewing angle of the image acquired by the on-board camera is closely related to the direction of vehicle travel, which meets the needs of judging the drivable area in actual driving scenarios, and provides intuitive and critical visual basis for the automatic driving or assisted driving system to accurately plan the driving path and avoid collisions.

[0046] S2. Preprocess the acquired image to obtain a first image processing result.

[0047] The process of preprocessing the acquired image is as follows:

[0048] Grayscale the acquired image: divide the acquired image into several non-overlapping sub-areas according to the set window size; calculate the contrast value H of each sub-area; compare the obtained contrast value H with the preset grayscale threshold T. If the contrast value H>the preset grayscale threshold T, adjust the weights of the red, green and blue channels, and then use the formula Y=α2×R i,j +β2×G i,j +γ2×B i,j , where α2, β2, and γ2 are the weights of the adjusted red, green, and blue channels, respectively. The grayscale value of the sub-region is calculated. Otherwise, the formula Y = α1 × R i,j +β1×G i,j +γ1×B i,j, where α1, β1, and γ1 are the weights of the unadjusted red, green, and blue channels, respectively. The grayscale value of the sub-region is calculated to obtain a grayscale image;

[0049] Enhance the grayscale image: divide the grayscale image into several non-overlapping sub-regions according to the set window size, and use the enhancement formula to enhance the image of each sub-region. The enhancement formula is: Z = round [K (i) × 255], where, y(i) is the frequency of pixels with grayscale value i in the sub-region, and n is the total number of pixels in the sub-region.

[0050] Furthermore, the calculation formula of the contrast value is: In the formula, R i,j , G i,j , B i.j are the pixel values ​​of the red, green and blue channels of the pixel point (i, j) in the sub-area respectively.

[0051] The formula for adjusting the weights of the red, green, and blue channels is In the formula, k is a parameter, k∈(0,1).

[0052] In this embodiment, it should be noted that by dividing the image into a number of non-overlapping sub-regions according to a set window size and then calculating the contrast value of each sub-region, it is possible to process pixel color changes in different local regions. Different road scenes, lighting conditions and other factors will cause the visual performance of different parts of the image to vary greatly. Through this local contrast calculation, the characteristics of the image at the microscopic level can be understood in more detail.

[0053] By comparing the contrast value of the sub-region with the preset grayscale threshold, it is decided whether to adjust the weights of the red, green, and blue channels before calculating the grayscale value. When the contrast value is high, it means that the pixel color in the region changes significantly. Adjusting the weight can make the grayscale image better reflect the real road structure and other information, avoiding the loss of some key features or the introduction of unnecessary interference due to unified processing. As an implementation of this embodiment, α1, β1, and γ1 can be 0.299, 0.587, and 0.114 respectively.

[0054] Through the enhancement formula, the pixel grayscale value is adjusted according to the frequency of pixels with different grayscale values ​​in the sub-region, so that the grayscale distribution in each sub-region of the image is more reasonable, thereby enhancing the contrast and clarity of the overall image, which is helpful for the subsequent accurate extraction of the edge features of the image and the judgment of the drivable area, thereby improving the accuracy and reliability of recognition.

[0055] S3. Extract edge features of the image obtained by the first image processing result to obtain a second image processing result.

[0056] The process of edge feature extraction is as follows:

[0057] Get the gradient component X of the image in the horizontal and vertical directions x , X y , calculate the gradient magnitude X and gradient direction angle θ of each pixel, where,

[0058] Compare the gradient amplitude of the pixel with the gradient amplitudes of its two adjacent pixels in the gradient direction. If the pixel is not the maximum value, set its gradient amplitude to 0.

[0059] Pixels in the image whose gradient amplitude is greater than a first preset threshold are marked as edge points, and pixels whose gradient amplitude is less than a second threshold are removed. Meanwhile, pixels between the first preset threshold and the second preset threshold are also marked as edge points if they are connected to edge points, wherein the first preset threshold is greater than the second preset threshold;

[0060] Connect each edge point to obtain an image with edge feature extraction.

[0061] In this embodiment, it should be noted that, as an implementation mode, the Sobel operator template in the horizontal direction is: Convolve with the image to get X x , the vertical template is: After convolution, we get X y . By setting a first preset threshold and a second preset threshold, the pixels in the image whose gradient amplitude is greater than the first preset threshold are directly marked as edge points, and the pixels whose gradient amplitude is less than the second threshold are removed. The pixels between the two thresholds and connected to the determined edge points are also marked as edge points. The above-mentioned dual threshold mechanism can determine the edges more flexibly and accurately. On the one hand, it can retain obvious strong edges. At the same time, by reasonably utilizing the association between the thresholds, it can include pixels whose amplitude is not particularly high but is associated with strong edges and also belongs to the real edge, so as to avoid missing some edge information. Finally, a relatively complete and accurate edge feature extraction image is obtained, which provides clear boundary lines for identifying key elements such as road boundaries and lane lines when determining the drivable area in the future.

[0062] S4. Determine a drivable area of ​​the structured road according to the obtained second image processing result.

[0063] The process of determining the drivable area of ​​the structured road is as follows:

[0064] Obtaining several feature lines in the image from the edge feature extracted image;

[0065] Acquire stored historical road information according to the location information of the acquired image;

[0066] Obtain road edge spacing, lane line number and lane line spacing from historical road information;

[0067] The obtained road edge spacing, lane line number and lane line spacing are matched with several feature lines respectively to obtain the drivable area of ​​the structured road.

[0068] Furthermore, if any of the matching results does not match, the identification of the drivable area of ​​the structured road is performed again, wherein the specific content of the matching is:

[0069] If the difference between the road edge spacing and the spacing between the two outermost feature lines is within the edge gap threshold, the road edge match is consistent;

[0070] If the number of lane lines is equal to the number of characteristic lines without the edge of the road, the number of lane lines matches;

[0071] If the lane line spacing and the adjacent feature line spacing are within the lane line spacing threshold, the lane line spacing match is consistent.

[0072] In this embodiment, it should be noted that the obtained road edge spacing, lane line number and lane line spacing are matched with several characteristic lines respectively, and the drivable area is accurately determined by clearly set matching rules. Then the known road structure standards are used to verify and define the drivable range to ensure that the final determined area meets the actual road layout and traffic rules, and provide accurate and reliable drivable area basis for applications such as path planning of autonomous driving vehicles and violation judgment in intelligent transportation systems. If any of the matching results does not match, the identification of the drivable area of ​​the structured road is re-performed. Through this repeated verification and error correction mechanism, the accuracy and stability of the recognition results are further improved, ensuring that the entire recognition process can still output reliable drivable area information in complex and changeable road environments.

[0073] In addition, this embodiment also provides a structured road drivable area visual recognition device, including: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to execute the above-mentioned structured road drivable area visual recognition method.

[0074] This embodiment also provides a computer program product, including computer instructions, wherein the computer instructions instruct a computer device to execute operations corresponding to the above method.

[0075] An embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the system of the present application are executed.

[0076] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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 above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0077] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0078] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for visually identifying a drivable area on a structured road, characterized in that: The following steps are involved: Acquire an image of a structured road; Preprocessing the acquired image to obtain a first image processing result; Extracting edge features of the image obtained by the first image processing result to obtain a second image processing result; The drivable area of ​​the structured road is determined according to the obtained second image processing result.

2. A method for visually identifying a drivable area on a structured road according to claim 1, characterized in that: The image is obtained by using a vehicle-mounted camera.

3. The method for visually identifying a drivable area on a structured road according to claim 1, characterized in that: The process of preprocessing the acquired image is as follows: Grayscale the acquired image: divide the acquired image into several non-overlapping sub-areas according to the set window size; calculate the contrast value H of each sub-area; compare the obtained contrast value H with the preset grayscale threshold T. If the contrast value H>the preset grayscale threshold T, adjust the weights of the red, green and blue channels, and then use the formula Y=α2×R i,j +β2×G i,j +γ2×B i,j , where α2, β2, and γ2 are the weights of the adjusted red, green, and blue channels, respectively. The grayscale value of the sub-region is calculated. Otherwise, the formula Y = α1 × R i,j +β1×G i,j +γ1×B i,j , where α1, β1, and γ1 are the weights of the unadjusted red, green, and blue channels, respectively. The grayscale value of the sub-region is calculated to obtain a grayscale image; Enhance the grayscale image: divide the grayscale image into several non-overlapping sub-regions according to the set window size, and use the enhancement formula to enhance the image of each sub-region. The enhancement formula is: Z = round [K (i) × 255], where, y(i) is the frequency of pixels with grayscale value i in the sub-region, and n is the total number of pixels in the sub-region.

4. A method for visually identifying a drivable area on a structured road according to claim 3, characterized in that: The calculation formula of the contrast value is: In the formula, R i,j , G i,j , B i.j are the pixel values ​​of the red, green and blue channels of the pixel point (i, j) in the sub-area respectively.

5. The method for visually identifying a drivable area on a structured road according to claim 3, characterized in that: The formula for adjusting the weights of the red, green, and blue channels is In the formula, k is a parameter, k∈(0,1).

6. The method for visually identifying a drivable area on a structured road according to claim 1, characterized in that: The process of edge feature extraction is as follows: Get the gradient component X of the image in the horizontal and vertical directions x , X y , calculate the gradient magnitude X and gradient direction angle θ of each pixel, where, Compare the gradient amplitude of the pixel with the gradient amplitudes of its two adjacent pixels in the gradient direction. If the pixel is not the maximum value, set its gradient amplitude to 0. Pixels in the image whose gradient amplitude is greater than a first preset threshold are marked as edge points, and pixels whose gradient amplitude is less than a second threshold are removed. Meanwhile, pixels between the first preset threshold and the second preset threshold are also marked as edge points if they are connected to edge points, wherein the first preset threshold is greater than the second preset threshold; Connect each edge point to obtain an image with edge feature extraction.

7. The method for visually identifying a drivable area on a structured road according to claim 1, characterized in that: The process of determining the drivable area of ​​the structured road is as follows: Obtaining several feature lines in the image from the edge feature extracted image; Acquire stored historical road information according to the location information of the acquired image; Obtain road edge spacing, lane line number and lane line spacing from historical road information; The obtained road edge spacing, lane line number and lane line spacing are matched with several feature lines respectively to obtain the drivable area of ​​the structured road.

8. The method for visually identifying a drivable area on a structured road according to claim 7, characterized in that: If any of the matching results does not match, the identification of the drivable area of ​​the structured road is performed again, wherein the specific content of the matching is: If the difference between the road edge spacing and the spacing between the two outermost feature lines is within the edge gap threshold, the road edge match is consistent; If the number of lane lines is equal to the number of characteristic lines without the edge of the road, the number of lane lines matches; If the lane line spacing and the adjacent feature line spacing are within the lane line spacing threshold, the lane line spacing match is consistent.

9. A visual recognition device for a structured road drivable area, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and are configured to be executed by the one or more processors, and the one or more applications are configured to execute the structured road drivable area visual recognition method as described in any one of claims 1 to 8.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions instruct a computer device to execute operations corresponding to the method according to any one of claims 1 to 8.

Images