Hiroyuki Ishida; Jun-ichi Meguro; Yoshiko Kojima; Takashi Naito (Toyota Central R&D Labs., Inc.), IPSJ Transactions on Computer Vision and Applications; ISSN: 1882-6695; VOL.5; NO.0; PAGE.176-182; (2013), Pub.Country: Japan, Language: English, DOI: 10.2197/ipsjtcva.5.1.176
Abstract: This paper presents a novel method for detecting 3D road boundaries, such as walls, guardrails, and curbs, using on-board stereo cameras. The proposed method uses conformal geometric algebra, which can describe different shapes in a common representation. 3D road boundaries on straight and curved roads are seamlessly detected by use of this representation, and this framework is also applied to curb detection by a subtle modification. Experimental results show that despite its algorithmic simplicity, the proposed method exhibited competitive detection performance compared with conventional model fitting and curb detection methods.
Keywords: road environment recognition, map generation, point cloud analysis, geometric algebra
Source: H. Ishida, 13 February 2015.