Road vanishing point detection using weber adaptive local filter and salient-block-wise weighted soft voting

• Published in: IET computer vision Vol. 10; no. 6; pp. 503 - 512
• Main Authors: Fan, Xue, Shin, Hyunchul
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.09.2016; Wiley
• Subjects: adaptive filters; Background noise; Computation; computational complexity; image texture; Orientation; pixel wise texture orientation estimation; pixel-wise texture orientations; pixel-wise voting scheme; Research Article; road edges; road trails; road vanishing point detection; Roads; salient-block-wise weighted soft voting; Surface layer; Texture; texture-based methods; traffic engineering computing; vanishing point detection; Voting; voting map generation; weber adaptive local filter; Workload; adaptive filters; pixel-wise voting scheme; roads; pixel wise texture orientation estimation; traffic engineering computing; weber adaptive local filter; pixel-wise texture orientations; road trails; road edges; vanishing point detection; image texture; salient-block-wise weighted soft voting; voting map generation; texture-based methods; road vanishing point detection; computational complexity
• DOI: 10.1049/iet-cvi.2015.0313
• ISSN: 1751-9632; 1751-9640

In this study, a novel and efficient technique is proposed for road vanishing point detection in challenging scenes. Currently, most existing texture-based methods detect the vanishing point using pixel wise texture orientation estimation and voting map generation, which suffers from high computational complexity. Since only road trails (e.g. road edges, ruts, and tire tracks) would contribute informative votes to vanishing point detection, the Weber adaptive local filter is proposed to distinguish road trails from background noise, which is envisioned to reduce the workload and to eliminate uninformative votes introduced by the background noise. Furthermore, instead of using the conventional pixel-wise voting scheme, the salient-block-wise weighted soft voting is developed to eliminate most of the noise votes introduced by incorrectly estimated pixel-wise texture orientations, and to further reduce the computation time of voting stage as well. The experimental results on the benchmark dataset demonstrate that the proposed method shows superior performance. The authors’ method is about ten times faster in detection speed and outperforms by 3.6% in detection accuracy, when compared with a well-known state-of-the-art approach.