Efficient Error Analysis of a Real-Time Vision-Based Pointing Systems

檔案

日期

2014-01-01

類型

期刊名稱

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING

卷期與頁次

第 30 卷第 1 期,頁 43–64

ISSN

1016-2364

語言

英文

摘要

In this paper, an efficient error analysis of a real-time vision-based pointing system is proposed. We use two cameras to implement the pointing system according to a simplified 3D reconstruction scheme which is based on image feature extraction, homography, and 3D geometry. To that end, we study the relationship between image noises and the ultimate reconstruction errors, and develop efficient methods to find the error range of the latter given a range of the former. Experimental results show that the proposed approach can find the error range satisfactorily. Accordingly, users of similar pointing systems can get more robust pointing results by selecting a special pointer location, or possibly a special pair of cameras, that will result in minimal range of pointing error.

所屬典藏

期刊論文
顯示完整詮釋資料 統計資料

引用此條目

Lo, K.-H., Chuang, J.-H., & Chen, H.-T. (2014). Efficient Error Analysis of a Real-Time Vision-Based Pointing Systems. JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 30(1), 43–64. https://ir.lib.nycu.edu.tw/handle/11536/23875

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/23875