Vanishing point detection using random forest and patch‐wise weighted soft voting. Issue 11 (1st November 2016)

• Record Type: Journal Article
• Authors: Fan, Xue; Riaz, Irfan; Rehman, Yawar; Shin, Hyunchul
• Is Part Of: IET image processing. Volume 10:Issue 11(2016)
• Page Start: 900
• Page End: 907
• Publication Date: 2016-11-01
• Subjects: traffic engineering computing -- roads -- image representation -- image filtering -- computational complexity -- Gaussian processes -- feature extraction; random forest -- road types -- single image based vanishing point detection -- noise votes -- background region -- valid patch extraction technique -- informative road patches -- background noise -- training patch generation method -- training patch representation -- patch‐wise weighted soft voting scheme -- voting map -- computational complexity -- generalised Laplacian -- Gaussian filter; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2016.0068
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Variations in road types and its ambient environment make the single image based vanishing point detection a challenging task. In this study, a novel and efficient vanishing point detection method is proposed by using random forest and patch‐wise weighted soft voting. To eliminate the noise votes introduced by background region and to reduce the workload of voting stage, random forest based valid patch extraction technique is developed, which distinguishes the informative road patches from the background noise. To prepare training data for the random forest, a training patch generation method is proposed, and a variety of road relevant features are introduced for training patch representation. Since the traditional pixel‐wise voting scheme is time consuming and imprecise, a patch‐wise weighted soft voting scheme is proposed to generate a more precise voting map and to further reduce the computational complexity of voting stage. The experimental results on the benchmark dataset show that the proposed method reveals a step forward in performance. The authors' approach is about 6 times faster in detection speed and 5.6% better in detection accuracy than the generalised Laplacian of Gaussian filter based method, which is a well‐known state‐of‐the‐art approach.