New sensing strategies for monitoring moving polyhedral objects by machine vision

ASIA unversity > 資訊學院 > 資訊傳播學系 > 期刊論文 > Item 310904400/4321

請使用永久網址來引用或連結此文件: http://asiair.asia.edu.tw/ir/handle/310904400/4321

題名:	New sensing strategies for monitoring moving polyhedral objects by machine vision
作者:	J. J. Leou;W. H. Tsai
貢獻者:	Department of Information Communication
日期:	1989
上傳時間:	2009-11-25 02:30:51 (UTC+0)
出版者:	Asia University
摘要:	A new sxt of sensing strategies for monitoring three-dimensional (3-11) moviq objects by computer vision is proposed. Here 3-D object surface points are selected as the features for nmnitoring 3-0 moving objects because the point features are easy to detect, extract. stow, and manipulate. It is proved that the minimum measurable feature point set for monitoring a 3-D moving convex polyhedral object is just the set containing all the junction points d the object. Based on the sampling theorem a d sevenl properties of photogrammetry, it is proved that the minimum data .rquisil:ion rate of a vision system monitoring 3-D moving objects can be determined with discretely sampled hvo-dimensional image sequence data only. Certain properties of orthographic projection useful for determining the minimum number y, of sensors needed to monitor 3-D moving convex polyhedral objects are investigated, and the bounds on N, are rho M v e d . Finailly, an algorithm for determining N, and the corresponding directions a I the sensors is proposed. “he feasibility of the pmposed algorithm is shown by three illustrative examples and an application example.
關聯:	IEEE Transactions on Systems, Man and Cybernetics SMC-19 (4): 872-880
顯示於類別:	[資訊傳播學系] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
310904400-4321.doc		31Kb	Microsoft Word	366	檢視/開啟

在ASIAIR中所有的資料項目都受到原著作權保護.

資料載入中.....