A point-based localization with error analysis

Kuo Hua Lo*, Jen-Hui Chuang, Yueh Hsun Hsieh, Hon Yue Chou

*Corresponding author for this work

研究成果: Conference contribution同行評審

摘要

In this paper, we examine implementing a vision-based localization system that can locate objects in the scene from their images by homography and 3D geometry and how to reduce errors arising from radial distortion of cameras, noise during imaging processing and errors associated with manual measurement. By analyzing these errors and trying different scenarios, including simple camera calibration and fine-tuning measurement data, it was possible for us to implement a system that used an appropriate pair of cameras in a multi-camera environment to achieve more accurate localization. Both synthetic and real scene data were used to verify the implemented localization system's results. Experimental results showed that the proposed approach could indeed reduce localization error and improve system stability.

原文English
主出版物標題ICS 2010 - International Computer Symposium
頁面312-318
頁數7
DOIs
出版狀態Published - 1 十二月 2010
事件2010 International Computer Symposium, ICS 2010 - Tainan, Taiwan
持續時間: 16 十二月 201018 十二月 2010

出版系列

名字ICS 2010 - International Computer Symposium

Conference

Conference2010 International Computer Symposium, ICS 2010
國家Taiwan
城市Tainan
期間16/12/1018/12/10

指紋 深入研究「A point-based localization with error analysis」主題。共同形成了獨特的指紋。

引用此