Lane line processing method and device
Embodiments of the present application provide a lane line processing method and a lane line processing device. The method can include: performing a binarization processing on a first image to obtain a binary image, the first image including lane line points and non-lane line points; performing a connected domain analysis on the binary image to obtain at least one connected domain in the binary image, the connected domain including a plurality of adjacent lane line points; determining lane line points in a group corresponding to a lane line, based on the connected domain; and obtaining representation information of the lane line corresponding to the group, by using the lane line points in the group.
1. A lane line processing method, comprising:
performing a binarization processing on a first image to obtain a binary image, the first image comprising lane line points and non-lane line points;
performing a connected domain analysis on the binary image to obtain at least one connected domain in the binary image, the connected domain comprising a plurality of adjacent lane line points;
determining a plurality of lane line points in a group corresponding to a lane line, based on the connected domain; and
obtaining representation information of the lane line corresponding to the group, by using the plurality of lane line points in the group,
wherein the method further comprises:
inputting a second image to a deep learning model, to obtain the first image, there being a scaling ratio between the first image and the second image, and
wherein the obtaining representation information of the lane line corresponding to the group by using the plurality of lane line points in the group comprises:
mapping coordinates of the lane line points of the group in the first image back to the second image, to obtain coordinates of the lane line points of the group in the second image; and
selecting a plurality of lane line points from the group, and performing a polynomial fitting on coordinates of the selected plurality of lane line points in the second image, to obtain a polynomial curve of the lane line corresponding to the group.
2. The lane line processing method of claim 1 , wherein the performing a binarization processing on a first image to obtain a binary image comprises:
setting brightness values of the lane line points in the first image to be 0, and setting brightness values of the non-lane line points in the first image to be 255; or
setting brightness values of the lane line points in the first image to be 255, and setting brightness values of the non-lane line points in the first image to be 0.
3. The lane line processing method of claim 1 , wherein the performing a connected domain analysis on the binary image to obtain at least one connected domain in the binary image comprises:
performing the connected domain analysis on the binary image in combination with a region of interest, to obtain the at least one connected domain in the region of interest.
4. The lane line processing method of claim 1 , wherein the determining a plurality of lane line points in a group corresponding to a lane line, based on the connected domain comprises:
determining lane line points of the connected domain in the first image, as lane line points in the group corresponding to the lane line.
5. The lane line processing method of claim 1 , wherein the obtaining representation information of the plurality of lane lines corresponding to the group, by using the lane line points in the group further comprises:
determining a start point coordinate and/or an end point coordinate of the lane line from the polynomial curve of the lane line.
6. A lane line processing device, comprising:
one or more processors; and
a storage device configured to store one or more programs, that, when executed by the one or more processors, cause the one or more processors to:
perform a binarization processing on a first image to obtain a binary image, the first image comprising lane line points and non-lane line points;
perform a connected domain analysis on the binary image to obtain at least one connected domain in the binary image, the connected domain comprising a plurality of adjacent lane line points;
determine a plurality of lane line points in a group corresponding to a lane line, based on the connected domain; and
obtain representation information of the lane line corresponding to the group, by using the plurality of lane line points in the group,
wherein the one or more programs, when executed by the one or more processors, further cause the one or more processors to:
input a second image to a deep learning model, to obtain the first image, there being a scaling ratio between the first image and the second image, and
wherein the one or more programs, when executed by the one or more processors, further cause the one or more processors to:
map coordinates of the lane line points of the group in the first image back to the second image, to obtain coordinates of the lane line points of the group in the second image; and
select a plurality of lane line points from the group, and perform a polynomial fitting on coordinates of the selected plurality of lane line points in the second image, to obtain a polynomial curve of the lane line corresponding to the group.
7. The lane line processing device of claim 6 , wherein the one or more programs, when executed by the one or more processors, cause the one or more processors further to:
perform the connected domain analysis on the binary image in combination with a region of interest, to obtain the at least one connected domain in the region of interest.
8. The lane line processing device of claim 6 , wherein the one or more programs, when executed by the one or more processors, cause the one or more processors further to:
determine a start point coordinate and/or an end point coordinate of the lane line from the polynomial curve of the lane line.
9. A non-transitory computer readable storage medium, in which a computer program is stored, wherein the program, when executed by a processor, causes the processor to implement the method of claim 1 .