The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-3
https://doi.org/10.5194/isprs-archives-XLII-3-1643-2018
https://doi.org/10.5194/isprs-archives-XLII-3-1643-2018
30 Apr 2018
 | 30 Apr 2018

SEMANTIC INFORMATION EXTRACTION OF LANES BASED ON ONBOARD CAMERA VIDEOS

L. Tang, T. Deng, and C. Ren

Keywords: Lane Marking Detection, Lane Semantic Recognition, Lane Classification, Onboard Camera Video, Lane-Based Road Network

Abstract. In the field of autonomous driving, semantic information of lanes is very important. This paper proposes a method of automatic detection of lanes and extraction of semantic information from onboard camera videos. The proposed method firstly detects the edges of lanes by the grayscale gradient direction, and improves the Probabilistic Hough transform to fit them; then, it uses the vanishing point principle to calculate the lane geometrical position, and uses lane characteristics to extract lane semantic information by the classification of decision trees. In the experiment, 216 road video images captured by a camera mounted onboard a moving vehicle were used to detect lanes and extract lane semantic information. The results show that the proposed method can accurately identify lane semantics from video images.