文章基本信息

标题：A Robust and Efficient Homography Based Approach for Ground Plane Detection
本地全文：下载
作者：Ajay Mittal ; Sanjeev Sofat
期刊名称：BVICAM's International Journal of Information Technology
印刷版ISSN：0973-5658
出版年度：2012
卷号：4
期号：2
出版社：Bharati Vidyapeeth's Institute of Computer Applications and Management
摘要：This paper presents a homography based ground plane detection method. The method is developed as a part of stereo vision based obstacle detection technique for the visually impaired people. The method assumes the presence of a texture dominant ground plane in the lower portion of the scene, which is not severe restriction in a real world. SIFT algorithm is used to extract features in the stereo images. The extracted SIFT features are robustly matched by model fitting using RANSAC. A sample of putative matches lying in the lower portion of the image is selected. A fitness function is developed to select matches from this sample, which are used to estimate ground plane homography hypothesis. The ground plane homography hypothesis is used to classify the SIFT features as either belonging to ground plane or not. Image segmentation using mean shift and normalized cut is further used to filter the outliers and augment the ground plane. Experimental tests have been conducted to test the performance of the proposed approach. The tests indicate that the proposed approach has good classification rate and have operating distance range from 3 feet to 12 feet.
关键词：Ground Plane; SIFT; Electronic Travel Aid; Homography