Abstract
Abstract. At present, automatic driving technology has become one of the development direction of the future intelligent transportation system. The high high-precision map, which is an important supplement of the on on-board sensors under the condition of shielding or the restriction of observation distance, provides a priori information for high high-precision positioning and path planning of the automatic driving with the level of L3 and above. The position and semantic information of the road markings, such as the absolute coordinates of th e solid line and the bro ken line, are the basic components of the high high-precision map. At present, point cloud data are still one of the most important data source of the high high-precision map. So, how to get road markings information from original point clouds automatically deserve study. In this paper, point cloud is sliced by the mileage of the road, then each slice is projected onto respective vertical section section. Random Sample Consensus (RANSAC) algorithm is applied to establish road surface buffer area . Finally, moving window filtering is used to extract road surface point cloud from road surface buffer area area. On this basis, the road surface point cloud image is transformed into raster image with a certain resolution by using the method of inverse distance weighted interpolation , and the grid image is converted into binary image by using the method of adaptive threshold segmentation based on the integral graph. Then the method of the Euclidean clustering is used to extract the road markings point cloud from the binary image. Characteristic attribute detection is applied to recognize solid line marking from all clusters. Deep learning network framework pointnet++ is applied to recognize remain road markings including guideline, broken line, straight arrow, and right turn arrow.
Highlights
Image processing is applied to get road markings in early studies(Li et al, 2012; Chen et al, 2015; Rebut J et al, 2004; Noda et al, 2011; Foucher et al, 2011)
The road surface point cloud image is transformed into raster image with a certain resolution by using the method of inverse distance weighted interpolation, and the grid image is converted into binary image though using the method of adaptive threshold segmentation based on the integral graph
The reason was that when the method of Euclidean clustering was applied to discrete point clouds, these broken lines which lay very close to the solid line were clustered together with solid line
Summary
Image processing is applied to get road markings in early studies(Li et al, 2012; Chen et al, 2015; Rebut J et al, 2004; Noda et al, 2011; Foucher et al, 2011). Wang et al (2015) adopted self-adaption binary segmentation to extract road marking form raster image, and use deep learning to recognize road marking. This literature only studies pedestrian crossing and arrow marking. Moving window filtering is utilized for the sake of extracting road surface point cloud from road surface buffer area On this basis, the road surface point cloud image is transformed into raster image with a certain resolution by using the method of inverse distance weighted interpolation, and the grid image is converted into binary image though using the method of adaptive threshold segmentation based on the integral graph. Deep learning network framework pointnet++(Charles R, et al, 2017) is applied to recognize remain road markings including guideline, broken line, straight arrow, and right turn arrow
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have