A lane feature detection method

Abstract

The present application discloses a lane feature detection method, comprising the following steps: S1, obtaining image information of a target area, and dividing the image information into multiple groups of pixel sets by row; S2, selecting one of the rows of pixel sets, and establishing a brightness distribution map of the group of pixel sets; S3, obtaining the height H and width W of each group of peaks in the brightness distribution map, calculating the ratio of the height to the width, and recording it as the height-to-width ratio of the group of peaks; S4, when it is determined that the height-to-width ratio is greater than a first preset threshold, marking the group of peaks as lane feature waves, and obtaining all pixel points in the feature peak waves as lane feature points; S5, repeating steps S3-S4, obtaining lane feature points in all lane feature waves; S6, repeating steps S2-S5, obtaining lane feature points of all pixel sets, inverting the lane feature points, and outputting a lane feature map.

Description

Technical Field

[0001] The present disclosure relates to the field of lane detection, and in particular to a lane line feature detection method. Background Art

[0002] Target detection and recognition technology has always received much attention and has been widely studied in the field of pattern recognition and image processing. Target types include moving targets (moving people and cars, etc.), static targets (human faces, various signs, targets in specific scenes such as flames, etc.), point targets, weak targets, etc. The application areas are also very wide, such as the common face recognition technology used in access control systems, early warning of vehicles and pedestrians in assisted driving systems, detection, early warning and attack of small targets in the air in the military field, and automatic detection and identification of defective products on production lines.

[0003] Traditional target detection and recognition algorithms often use image segmentation technology. On-board cameras are usually installed on the front of the vehicle, the front of the vehicle or the window. The lane lines appear in the lower half of the image and extend vertically to the distance. When performing lane line detection, a common method is to identify the edge information of the lane and judge the lane line information by comparing the brightness of the edge information with the separation threshold.

[0004] However, the lane edge information is easily affected by interference such as lighting, shadows, damage and other reflective objects, and the detection results are greatly affected by the segmentation threshold. Summary of the invention

[0005] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a lane feature detection method.

[0006] In a first aspect, a lane feature detection method comprises the following steps:

[0007] S1. Acquire image information of a target area, and divide the image information into multiple groups of pixels by row;

[0008] S2, selecting one row of pixel sets and establishing a brightness distribution map of the pixel set;

[0009] S3, obtaining the height H and width W of each group of peaks in the brightness distribution graph, calculating the ratio of the height to the width, and recording it as the height-to-width ratio of the group of peaks;

[0010] S4. When it is determined that the aspect ratio is greater than a first preset threshold, the group of wave peaks is marked as lane line characteristic waves, and all pixel points in the characteristic wave peaks are obtained as lane line characteristic points;

[0011] S5. Repeat steps S3-S4 to obtain lane feature points in all lane feature waves;

[0012] S6. Repeat steps S2-S5 to obtain lane feature points of all pixel sets, perform inversion imaging on the lane feature points, and output a lane feature map.

[0013] According to the technical solution provided in the embodiment of the present application, the step of establishing the brightness distribution map of the pixel set includes the following steps:

[0014] S2-1, obtaining all pixel points in the pixel set,

[0015] S2-2, obtaining the brightness information and position information of the pixel points and establishing a curve graph;

[0016] S2-3, perform mean filtering on the curve graph to obtain a brightness distribution graph.

[0017] According to the technical solution provided in the embodiment of the present application, obtaining the height and width of each group of peaks in the brightness distribution diagram includes the following steps:

[0018] S3-1. Get the peak point of the wave crest and mark it as A(x a ,y a )point;

[0019] S3-2, obtain the valley value points of the two groups of valleys adjacent to point A, and mark the higher valley value point as B (x b ,y b )point;

[0020] S3-3. Draw a horizontal line through point B, intersecting with the wave crest of this group, and mark the intersection point C (x c ,y c ,);

[0021] S3-4. Calculate the peak height H=y a -y b , calculate the peak width W = |x b -x c |.

[0022] According to the technical solution provided in the embodiment of the present application, when the aspect ratio is determined to be greater than the first preset threshold, marking the group of wave peaks as lane line characteristic waves includes the following steps:

[0023] S4-1, when the aspect ratio is greater than a first preset threshold, obtaining the number of peak pixel points in the group;

[0024] S4-2: When it is determined that the number of pixel points is greater than a second preset threshold, mark the group of peak waves as lane line characteristic waves.

[0025] In a second aspect, a server includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned lane feature detection method when executing the computer program.

[0026] In a third aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium has a computer program, and when the computer program is executed by a processor, the steps of a lane feature detection method as described above are implemented.

[0027] Beneficial effects of the present invention: The present application discloses a lane line feature detection method, which obtains image information of a target area, decomposes the image information into multiple rows of pixel sets, selects the first row of pixel sets, establishes a brightness distribution map of the first row of pixel sets, obtains the height and width of each group of peaks in the brightness distribution map, each group of peaks represents that a reflective area is provided under the position, and the peak height represents the brightness difference between the reflective area and the adjacent area, that is, the higher the peak height, the more obvious the brightness difference; the peak width represents the width of the reflective area, that is, the wider the peak width, the wider the reflective area. Since the lane line has high brightness and a limited width range, when it is determined that the peak height-to-width ratio corresponding to the reflective area is greater than the first preset threshold, that is, the reflective area is a lane line, the group of peaks is marked as a lane line characteristic wave, and all pixel points therein are lane feature points. Repeat the above method to select the lane line characteristic wave in each row of pixel sets, and obtain the lane line feature points in all lane line characteristic waves, invert the lane line feature points to image, and output the lane line feature map.

[0028] Since the peak height depends on the brightness difference, the brightness difference does not change significantly even when the illumination in the target area is reduced or there is a shadow. Since the peak width depends on the width of the reflective area and the lane line width is a standard width, the height-to-width ratio of the peak is compared with the first preset threshold to identify the brightness difference and the reflective area width in two dimensions. On the one hand, the influence of illumination on lane line recognition can be reduced, and on the other hand, the influence of reflective objects other than lane lines on the detection results can be prevented. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0030] Figure 1 Schematic diagram of collecting image information for a camera;

[0031] Figure 2 It is a schematic diagram of a pixel curve graph;

[0032] Figure 3 is the lane feature map;

[0033] Figure 4The following is a block diagram of the server principle.

[0034] Numbers in the figure: 501, CPU; 502, ROM; 503, RAM; 504, bus; 505, I / O interface; 506, input part; 507, output part; 508, storage part; 509, communication part; 510, drive; 511, removable media. DETAILED DESCRIPTION

[0035] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0036] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0037] Example 1

[0038] See also Figure 1-3 , a lane feature detection method, comprising the following steps:

[0039] S1. Obtain image information of a target area, and divide the image information into multiple groups of pixels by row.

[0040] Among them, the vehicle-mounted camera is usually installed in the front of the vehicle, the front of the vehicle or the window. The lane line appears in the lower half of the image and extends to the distance in the vertical direction, such as Figure 1 Imaging the image information line by line is helpful to improve the detection accuracy and prevent the influence of lane line damage on the detection results.

[0041] S2, selecting one row of pixel sets and establishing a brightness distribution map of the pixel set;

[0042] Among them, all the pixel points in the pixel set are obtained, the brightness information and position information of the pixel points are obtained, a coordinate system is established, the position information is the horizontal coordinate, the brightness information is the vertical coordinate, all the pixel points are fitted, and a curve graph is established, such as Figure 2 As shown, it is a brightness distribution diagram of a row of pixel sets. The curve graph is mean filtered to eliminate the burrs on the brightness distribution diagram, avoid the influence of the burrs on the subsequent steps, and obtain a relatively smooth brightness distribution diagram.

[0043] S3. Obtain the height H and width W of each group of peaks in the brightness distribution diagram, calculate the ratio of the height to the width, and record it as the height-to-width ratio of the group of peaks.

[0044] Among them, it is preferred to select one group of peaks, which represent the reflective area, obtain the peak point, and mark A(x a ,y a ) point; obtain the valley value points of the two groups of valleys adjacent to point A, and mark the higher valley value point as B (x b ,y b ) point; draw a horizontal line through point B, intersecting with the wave peaks of this group, and mark the intersection point C (x c ,y c ,);

[0045] The peak height is calculated by formula 1, and the peak width is calculated by formula 2.

[0046] H=y a -y b Formula 1

[0047] W=|x b -x c | Formula 2

[0048] S4. When it is determined that the aspect ratio is greater than a first preset threshold, the group of wave peaks is marked as lane line characteristic waves, and all pixel points in the characteristic wave peaks are obtained as lane line characteristic points;

[0049] Among them, when the aspect ratio is greater than the first preset threshold, the number of pixel points of this group of peaks is obtained. When it is judged that the number of pixel points is greater than the second preset threshold, the group of peak waves is marked as lane line characteristic waves. Peaks with points or fewer pixels can be eliminated to prevent the impact of high-brightness but small-shaped reflective areas on the road on the detection results.

[0050] S5. Repeat steps S3-S4 to obtain lane feature points in all lane feature waves;

[0051] S6, repeat steps S2-S5, obtain lane feature points of all pixel sets, perform inversion imaging on the lane feature points, and output a lane feature map, such as Figure 3 shown.

[0052] Working principle: The present application discloses a lane line feature detection method, which obtains image information of a target area, decomposes the image information into multiple rows of pixel sets, selects the first row of pixel sets, establishes a brightness distribution map of the first row of pixel sets, obtains the height and width of each group of peaks in the brightness distribution map, each group of peaks represents that a reflective area is set under the position, and the peak height represents the brightness difference between the reflective area and the adjacent area, that is, the higher the peak height, the more obvious the brightness difference; the peak width represents the width of the reflective area, that is, the wider the peak width, the wider the reflective area. Since the lane line has high brightness and a limited width range, when it is determined that the peak height-to-width ratio corresponding to the reflective area is greater than the first preset threshold, that is, the reflective area is a lane line, the group of peaks is marked as a lane line feature wave, and all the pixels therein are lane feature points. Repeat the above method to select the lane line feature wave in each row of pixel sets, and obtain the lane line feature points in all lane line feature waves, invert the lane line feature points to image, and output the lane line feature map.

[0053] Since the peak height depends on the brightness difference, the brightness difference does not change significantly even when the illumination in the target area is reduced or there is a shadow. Since the peak width depends on the width of the reflective area and the lane line width is a standard width, the height-to-width ratio of the peak is compared with the first preset threshold to identify the brightness difference and the reflective area width in two dimensions. On the one hand, the influence of illumination on lane line recognition can be reduced, and on the other hand, the influence of reflective objects other than lane lines on the detection results can be prevented.

[0054] Example 2

[0055] A server includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a lane feature detection method as described in Example 1 are implemented.

[0056] In this embodiment, if Figure 4 As shown, the computer system includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion into a random access memory (RAM) 503. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0057] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0058] In particular, according to an embodiment of the present invention, the above reference process Figure 1 The described process can be implemented as a computer software program. For example, embodiment 3 of the present invention includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains program code for executing the method shown in the flow chart. 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) 501, the above-mentioned functions defined in the system of the present application are executed.

[0059] 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.

[0060] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0061] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves. The units or modules described may also be arranged in a processor, for example, they may be described as: a processor includes a first generation module, an acquisition module, a search module, a second generation module, and a merging module. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves, for example, the acquisition module may also be described as "an acquisition module for acquiring multiple instances to be detected in the basic table."

[0062] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements a lane feature detection method as described in the above embodiment.

[0063] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves. The units or modules described may also be arranged in a processor, for example, they may be described as: a processor includes a first generation module, an acquisition module, a search module, a second generation module, and a merging module. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves, for example, the acquisition module may also be described as "an acquisition module for acquiring multiple instances to be detected in the basic table."

[0064] Example 3

[0065] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements a lane feature detection method as described in the above embodiment.

[0066] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

Claims

1. A lane feature detection method, characterized in that: The following steps are involved: S1. Acquire image information of a target area, and divide the image information into multiple groups of pixels by row; S2, selecting one row of pixel sets and establishing a brightness distribution map of the pixel set; S3, obtaining the height H and width W of each group of peaks in the brightness distribution graph, calculating the ratio of the height to the width, and recording it as the height-to-width ratio of the group of peaks; S4. When it is determined that the aspect ratio is greater than a first preset threshold, the group of wave peaks is marked as a lane line characteristic wave, and all pixel points in the characteristic wave are obtained as lane line characteristic points; S5. Repeat steps S3-S4 to obtain lane feature points in all lane feature waves; S6. Repeat steps S2-S5 to obtain lane feature points of all pixel sets, perform inversion imaging on the lane feature points, and output a lane feature map.

2. A lane feature detection method according to claim 1, characterized in that: The step of establishing the brightness distribution map of the pixel set comprises the following steps: S2-1, obtaining all pixel points in the pixel set, S2-2, obtaining the brightness information and position information of the pixel points and establishing a curve graph; S2-3, perform mean filtering on the curve graph to obtain a brightness distribution graph.

3. The lane feature detection method according to claim 1, characterized in that: The step of obtaining the height and width of each group of peaks in the brightness distribution graph comprises the following steps: S3-1. Get the peak point of the wave crest and mark it as A(x a ,y a )point; S3-2, obtain the valley value points of the two groups of valleys adjacent to point A, and mark the higher valley value point as B (x b ,y b )point; S3-3. Draw a horizontal line through point B, intersecting with the wave crest of this group, and mark the intersection point C (x c ,y c ,); S3-4. Calculate the peak height H=y a -y b , calculate the peak width W = |x b -x c |.

4. The lane feature detection method according to claim 1, characterized in that: When the height-to-width ratio is greater than the first preset threshold, marking the group of wave peaks as lane line characteristic waves comprises the following steps: S4-1, when the aspect ratio is greater than a first preset threshold, obtaining the number of peak pixel points in the group; S4-2: When it is determined that the number of pixel points is greater than a second preset threshold, mark the group of wave peaks as lane line characteristic waves.

5. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a lane feature detection method as described in any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium, the computer-readable storage medium having a computer program, characterized in that: When the computer program is executed by a processor, the steps of a lane feature detection method as described in any one of claims 1 to 4 are implemented.

Images