A lane recognition method

Abstract

This invention discloses a lane recognition method. By setting a pentagonal recognition area and utilizing its advantage of covering the entire recognition area, it can cover the entire lane and completely identify vehicle license plate information, thus solving the problems existing in the prior art. This lane recognition method, used in a parking lot, includes: a camera for lane recognition, the recognition area being the parking area within the lane that needs to be monitored; S1: setting a pentagonal recognition area based on the recognition area of ​​the lane to be recognized, ensuring that the pentagonal recognition area can cover the recognition area; S2: taking a picture of the pentagonal recognition area to obtain photographic information; S3: analyzing the photographic information to determine whether there are vehicles within the pentagonal recognition area; if so, proceeding to step S4; S4: determining whether all vehicles are located within the pentagonal recognition area; if so, the vehicles are deemed to be parked correctly.

Description

Technical Field

[0001] This invention relates to the field of lane recognition technology, and more particularly to a lane recognition method. Background Technology

[0002] A license plate camera is a camera device specifically designed for recognizing license plates on vehicles.

[0003] To prevent license plate cameras from mistakenly identifying nearby vehicles and to ensure that only license plates within the valid recognition area are identified, a specific lane is typically designated as the recognition zone. In existing technologies, the recognition zone is usually quadrilateral, such as rectangular or trapezoidal. Please refer to [link to relevant documentation]. Figure 1 This recognition area is also called a quadrilateral recognition area. Due to the limited field of view of the camera, traditional cameras cannot capture the entire lane within the quadrilateral recognition area in most cases. Therefore, when processing the quadrilateral recognition area, some lanes must be discarded, meaning that the entire lane cannot be taken into account. This can lead to situations where vehicle license plate information may not be recognized, because the discarded lanes may contain part of the vehicle license plate information.

[0004] Therefore, in view of the above situation, how to improve the existing identification method of camera guns to solve the above problems has become an important technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] This invention discloses a lane recognition method. By setting a pentagonal recognition area and taking advantage of the fact that the pentagonal recognition area can cover the entire recognition area, it can take into account the entire lane and completely recognize vehicle license plate information, thus solving the problems existing in the prior art.

[0006] The lane recognition method provided by this invention includes:

[0007] The camera is used to identify lanes, and the identification area is the parking area within the lane that needs to be monitored;

[0008] S1: Based on the recognition area of ​​the lane to be recognized, set a pentagonal recognition area, with the pentagonal recognition area covering the recognition area as the standard;

[0009] S2: Take a picture of the pentagonal recognition area to obtain photographic information;

[0010] S3: Analyze the photographic information to determine whether there is a vehicle in the pentagonal recognition area; if so, proceed to step S4.

[0011] S4: Determine whether all vehicles are located within the pentagonal recognition area; if so, the vehicle parking standard is determined.

[0012] Preferred,

[0013] Step S1 includes:

[0014] The recognition area is obtained based on the photos or video streams captured by the camera.

[0015] Adjust the five endpoints of the pentagonal recognition area so that the pentagonal recognition area can cover the recognition area.

[0016] Preferred,

[0017] Step S3 includes:

[0018] The photographic information is processed to obtain an image. If the image processing result indicates the presence of a vehicle, then it is determined that a vehicle exists within the pentagonal recognition area.

[0019] Preferred,

[0020] Step S4 includes:

[0021] Image processing is performed based on the photographic information to generate vehicle outline pixels. If all pixels fall within the pentagonal recognition area, the vehicle is determined to be entirely within the pentagonal recognition area.

[0022] Preferred,

[0023] Step S4 includes:

[0024] When the camera detects a vehicle or license plate, it determines whether the vehicle or license plate is located within the pentagonal recognition area based on the shortest distance from the pixel coordinates of the vehicle or license plate to the outline of the pentagonal recognition area.

[0025] Preferred,

[0026] Step S1 includes:

[0027] S11. Obtain the photo to be identified from the photo taken by the camera or the photo extracted from the video stream;

[0028] S12. Perform image analysis on the photo to be identified to obtain the parking area;

[0029] S13. Regularize the parking area to obtain a pentagonal parking area;

[0030] S14. Adjust the pentagonal parking area to obtain a pentagonal recognition area, which can cover the parking area.

[0031] Preferred,

[0032] Step S12 includes:

[0033] If a parking space frame exists in the photo to be identified, the identified parking space frame will be used as the parking area; otherwise, the process will proceed to manual processing, and the parking area will be manually defined.

[0034] Preferred,

[0035] Step S13 includes:

[0036] The front end of the parking area is taken as the front end of the pentagonal parking area, and the end of the image to be identified that is opposite to the front end is taken as the rear end of the pentagonal parking area, thus obtaining the pentagonal parking area.

[0037] Preferred,

[0038] The pentagonal parking area is enlarged by 1.01 to 1.2 times.

[0039] The lane recognition method provided by this invention, used in parking lots, includes: a camera for identifying lanes, the identification area being the parking area within the lane that needs to be monitored; firstly, a pentagonal recognition area is set according to the identification area of ​​the lane to be identified, with the pentagonal recognition area covering the identification area; then, the pentagonal recognition area is photographed to obtain photographic information; then, the photographic information is analyzed to determine whether there are vehicles within the pentagonal recognition area, and if so, whether the vehicles are all located within the pentagonal recognition area, and if so, the vehicles are deemed to be parked according to standards. By setting a pentagonal recognition area and utilizing its advantage of covering the entire identification area, the lane recognition method of this invention can cover the entire lane, completely identify vehicle license plate information, and solve the problems existing in the prior art. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a first identification diagram of a quadrilateral identification area using existing technology;

[0042] Figure 2 This is a second identification diagram using the existing technology for quadrilateral identification areas;

[0043] Figure 3 This is a schematic diagram illustrating the recognition process using the pentagonal recognition area of ​​the present invention.

[0044] Figure 4 This is a flowchart of the first embodiment of the lane recognition method of the present invention;

[0045] Figure 5 This is a flowchart of a second embodiment of the lane recognition method of the present invention;

[0046] Figures 1 to 3 In the diagram, 001 represents the wall, 002 represents the area to be identified, 003 represents the quadrilateral identification area, and 004 represents the pentagonal identification area. Detailed Implementation

[0047] This invention discloses a lane recognition method. By setting a pentagonal recognition area and taking advantage of the fact that the pentagonal recognition area can cover the entire recognition area, it can take into account the entire lane and completely recognize vehicle license plate information, thus solving the problems existing in the prior art.

[0048] The technical solutions of the embodiments of the present invention will be clearly and thoroughly described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] Please see Figures 1 to 4 The first embodiment of the lane recognition method provided by the present invention includes:

[0050] The camera is used to identify lanes, and the identification area is the parking area within the lane that needs to be monitored;

[0051] S1: Based on the recognition area of ​​the lane to be recognized, set a pentagonal recognition area, with the pentagonal recognition area covering the recognition area as the standard;

[0052] First, it should be noted that in most cases, surveillance cameras cannot capture the entire lane; they can only capture it in very rare circumstances. Therefore, this invention is based on embodiments applicable to the vast majority of situations, not on rare occurrences. Next, each lane has a preset recognition area, which can be a marked parking space, an unmarked monitoring area, etc., and is not limited here. Based on the preset recognition area, a pentagonal recognition area can be set, the pentagon being designed to cover the designated recognition area. Please refer to [link / reference]. Figures 1 to 3 It should be noted that the camera identifies the situation on the lane based on the pre-set polygonal recognition area. Existing cameras all use quadrilateral recognition areas. Generally speaking, the front end of the recognition area can be completely identified using a quadrilateral recognition area, but if the rear end is also using a quadrilateral recognition area, there will be a situation where no matter how the quadrilateral recognition area is adjusted, the rear end of the recognition area cannot be completely identified. In this case, the problem of the existing technology can be solved by using the pentagonal recognition area of ​​this invention, which breaks through the conventional approach.

[0053] S2: Take a picture of the pentagonal recognition area to obtain photographic information;

[0054] Once the pentagonal recognition area is determined, photographing or recording the pentagonal recognition area will yield photographic information. This photographic information can include the situation within the pentagonal recognition area, including possible vehicles, time information, etc.

[0055] S3: Analyze the photographic information to determine whether there is a vehicle in the pentagonal recognition area; if so, proceed to step S4.

[0056] By analyzing photographic information, such as performing image processing or license plate recognition, it is possible to determine whether there is a vehicle within the pentagonal recognition area.

[0057] S4: Determine whether all vehicles are located within the pentagonal recognition area; if so, the vehicle parking standard is determined.

[0058] Once a vehicle is identified within the pentagonal recognition area, it can be further determined whether all vehicles are located within the pentagonal recognition area, and the parking standard is determined when all vehicles are located within the pentagonal recognition area.

[0059] The lane recognition method provided by this invention, used in parking lots, includes: a camera for identifying lanes, the identification area being the parking area within the lane that needs to be monitored; firstly, a pentagonal recognition area is set according to the identification area of ​​the lane to be identified, with the pentagonal recognition area covering the identification area; then, the pentagonal recognition area is photographed to obtain photographic information; then, the photographic information is analyzed to determine whether there are vehicles within the pentagonal recognition area, and if so, whether the vehicles are all located within the pentagonal recognition area, and if so, the vehicles are deemed to be parked according to standards. By setting a pentagonal recognition area and utilizing its advantage of covering the entire identification area, the lane recognition method of this invention can cover the entire lane, completely identify vehicle license plate information, and solve the problems existing in the prior art.

[0060] The first embodiment of the lane recognition method of the present invention has been described above, and the method of using the pentagonal recognition area has been described in detail in the first embodiment. The second embodiment of the lane recognition method of the present invention is described below, which includes:

[0061] A1. Obtain the photo to be identified from the photo taken by the camera or the photo extracted from the video stream;

[0062] If it is a photograph, it can be used directly. If it is a video stream, the photo at the required moment can be extracted from the video stream and used as the photo to be identified.

[0063] A 2. Perform image analysis on the photo to be identified to obtain the parking area;

[0064] If a parking space outline exists within the image to be identified, the identified parking space outline will be used as the parking area; otherwise, the process will proceed to manual processing, where the parking area will be manually defined. It is important to note that in some identification areas, there may not be a defined outline. In such cases, the parking area must be manually defined, for example, in areas used solely for monitoring purposes and not designated as parking areas.

[0065] A 3. Regularize the parking area to obtain a pentagonal parking area;

[0066] The front end of the parking area is designated as the front end of the pentagonal parking area, and the end in the image to be identified that is opposite to the front end is designated as the rear end of the pentagonal parking area, thus obtaining the pentagonal parking area. Please refer to [link / reference]. Figures 1 to 3 As can be seen, regardless of whether a quadrilateral or pentagonal recognition area is used, the front end of the parking area can be easily and completely identified, while the rear end cannot be completely identified by the quadrilateral recognition area. This invention can directly use the end of the image to be identified that is opposite to the front end as the rear end of the pentagonal parking area, so that the resulting pentagonal recognition area can completely cover the entire parking area.

[0067] In addition, the pentagonal parking area can be enlarged by 1.01 to 1.2 times to more completely identify the entire identification area; no limit is set here.

[0068] A4. Adjust the pentagonal parking area to obtain a pentagonal recognition area, which can cover the parking area;

[0069] It should be noted that manual intervention is also possible to adjust the pentagonal parking area. By adjusting the five endpoints of the pentagonal parking area, a pentagonal recognition area that fully covers the entire parking area can be obtained.

[0070] A5: Take a picture of the pentagonal recognition area to obtain photographic information;

[0071] A6: Analyze the photographic information to determine whether there is a vehicle in the pentagonal recognition area. If there is, proceed to step A7.

[0072] The photographic information is processed to obtain an image. If the image processing result indicates the presence of a vehicle, then it is determined that a vehicle exists within the pentagonal recognition area.

[0073] A7: Determine whether all vehicles are located within the pentagonal recognition area; if so, the vehicle parking standard is determined.

[0074] There are many methods to determine whether a vehicle is located within the pentagonal recognition area. Specifically, image processing can be performed based on photographic information to generate vehicle outline pixels. If all pixels fall within the pentagonal recognition area, then the vehicle is determined to be located within the pentagonal recognition area. Alternatively, when the camera detects a vehicle or license plate, the shortest distance from the coordinates of the pixel where the vehicle or license plate is located to the outline of the pentagonal recognition area can be used to determine whether the vehicle or license plate is located within the pentagonal recognition area. No specific method is used here.

[0075] The lane recognition method provided by this invention, used in parking lots, includes: a camera for lane recognition, the recognition area being the parking area within the lane that needs to be monitored; firstly, obtaining a photo to be recognized from a photograph taken by the camera or extracted from a video stream; then, performing image analysis on the photo to be recognized to obtain the parking area; next, regularizing the parking area to obtain a pentagonal parking area; then, adjusting the pentagonal parking area to obtain a pentagonal recognition area that covers the parking area; then, photographing the pentagonal recognition area to obtain photographic information; finally, analyzing the photographic information to determine whether there are vehicles within the pentagonal recognition area, and if so, determining whether all vehicles are located within the pentagonal recognition area, and if so, confirming that the vehicle is parked correctly. By setting a pentagonal recognition area and utilizing its advantage of covering the entire recognition area, the lane recognition method of this invention can cover the entire lane, completely recognize vehicle license plate information, and solve the problems existing in the prior art.

[0076] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0077] The lane recognition method provided by the present invention has been described in detail above. For those skilled in the art, there will be changes in the specific implementation and application scope based on the ideas of the embodiments of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A lane recognition method, characterized in that, include: The camera is used to identify lanes, and the identification area is the parking area within the lane that needs to be monitored; S1: Based on the recognition area of ​​the lane to be recognized, set a pentagonal recognition area, with the pentagonal recognition area covering the recognition area as the standard; S2: Take a picture of the pentagonal recognition area to obtain photographic information; S3: Analyze the photographic information to determine whether there is a vehicle in the pentagonal recognition area. If there is, proceed to step S4. S4: Determine whether all vehicles are located within the pentagonal recognition area; if so, the vehicle parking standard is determined. Step S1 includes: The recognition area is obtained based on the photos or video streams captured by the camera. Adjust the five endpoints of the pentagonal recognition area so that the pentagonal recognition area can cover the recognition area; Step S3 includes: The photographic information is processed to obtain an image. If the image processing result indicates the presence of a vehicle, then it is determined that a vehicle exists within the pentagonal recognition area. Step S4 includes: When the camera detects a vehicle or license plate, it determines whether the vehicle or license plate is located within the pentagonal recognition area based on the shortest distance from the pixel coordinates of the vehicle or license plate to the outline of the pentagonal recognition area.

2. The lane recognition method according to claim 1, characterized in that, Step S3 includes: The photographic information is processed to obtain an image. If the image processing result indicates the presence of a vehicle, then it is determined that a vehicle exists within the pentagonal recognition area.

3. The lane recognition method according to claim 1, characterized in that, Step S4 includes: Image processing is performed based on the photographic information to generate vehicle outline pixels. If all pixels fall within the pentagonal recognition area, the vehicle is determined to be entirely within the pentagonal recognition area.

4. The lane recognition method according to claim 1, characterized in that, Step S4 includes: When the camera detects a vehicle or license plate, it determines whether the vehicle or license plate is located within the pentagonal recognition area based on the shortest distance from the pixel coordinates of the vehicle or license plate to the outline of the pentagonal recognition area.

5. The lane recognition method according to any one of claims 1 to 4, characterized in that, Step S1 includes: S11. Obtain the photo to be identified from the photo taken by the camera or the photo extracted from the video stream; S12. Perform image analysis on the photo to be identified to obtain the parking area; S13. Regularize the parking area to obtain a pentagonal parking area; S14. Adjust the pentagonal parking area to obtain a pentagonal recognition area, which can cover the parking area.

6. The lane recognition method according to claim 5, characterized in that, Step S12 includes: If a parking space frame exists in the photo to be identified, the identified parking space frame will be used as the parking area; otherwise, the process will proceed to manual processing, and the parking area will be manually defined.

7. The lane recognition method according to claim 6, characterized in that, Step S13 includes: The front end of the parking area is taken as the front end of the pentagonal parking area, and the end in the photo to be identified that is opposite to the front end is taken as the rear end of the pentagonal parking area, thus obtaining the pentagonal parking area.

8. The lane recognition method according to claim 7, characterized in that, The pentagonal parking area is enlarged by 1.01 to 1.2 times.

Images