Estimation of Ego-Vehicle’s Position Based on Image Registration

• DOI: 10.20485/jsaeijae.9.3_151
• Publication Date: 2020-02-28T22:08:47Z
• Authors: Keisuke Kazama; Toshiki Kawakatsu; Yasuhiro Akagi; Hiroshi Mouri
• Keywords: Position (finance); Road surface

This paper describes an estimation method of ego-vehicle’s position using a 2D map. The general approach for localization is to match the white lines between map and real world. However, such approaches suffer from changing environmental conditions painting clearance. If considerable changes occur, false-detection rate increases due noises miss-detected lines. In order solve this issue, based on holistic road area detection proposed. First, extracted predefined boundary Next, world detected LiDAR converted into binary image plane. Finally, registration technique applied calculate overall matching score images. proposed has provided accurate against with low-cost calculation simulation results. addition, validation in performed less than 0.2 m error.