2-point RANSAC for scene image matching under large viewpoint changes

Chih Chung Chou, Chieh-Chih Wang

研究成果: Conference article同行評審

14 引文 斯高帕斯(Scopus)

摘要

This work aims to accurately match two scene images under large viewpoint changes, which is the key issue in appearance-based localization tasks. In this paper, two key ideas are proposed to solve the challenging problem. First, to detect extreme small overlapping regions between two images, a new approach is developed to estimate the camera motion using only two pairs of matched features, while the state-of-art needs at least five. Second, proper prior knowledge to the environmental structures is utilized to strengthen the outlier rejection. The proposed 2-point approach is tested on challenging scenes and shows good robustness to the drastic occlusion and scaling caused by viewpoint changes.

原文English
文章編號7139705
頁(從 - 到)3646-3651
頁數6
期刊Proceedings - IEEE International Conference on Robotics and Automation
2015-June
發行號June
DOIs
出版狀態Published - 29 6月 2015
事件2015 IEEE International Conference on Robotics and Automation, ICRA 2015 - Seattle, United States
持續時間: 26 5月 201530 5月 2015

指紋

深入研究「2-point RANSAC for scene image matching under large viewpoint changes」主題。共同形成了獨特的指紋。

引用此