Comparing viewpoint evaluation functions for model-based inspectional coverage

被引:3
作者
Wong, C [1 ]
Kamel, M [1 ]
机构
[1] Univ Waterloo, Pattern Anal & Machine Intelligence Lab, Waterloo, ON N2L 2R7, Canada
来源
1ST CANADIAN CONFERENCE ON COMPUTER AND ROBOT VISION, PROCEEDINGS | 2004年
关键词
camera planning; camera viewpoints; model-based inspection; object coverage;
D O I
10.1109/CCCRV.2004.1301457
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Though based on rigorously developed ideas from imaging geometry, viewpoint evaluation in the active area of camera placement planning research still relies on the intuition and creativity of researchers for the formulation of objective measures. In this paper, a comparative study of five different viewpoint evaluation functions is presented. All five functions are based on a similar set of imaging requirements and considerations but each is unique in its formulation, and in some cases, in its objective. Functional behaviour and performance for the vision task of model-based inspectional coverage are studied quantitatively and qualitatively.
引用
收藏
页码:287 / 294
页数:8
相关论文
共 25 条
[1]  
BARDON C, 2003, THESIS U WATERLOO WA
[2]  
BATCHELOR BG, 1989, P SPIE INTELLIGENT R, V1193
[3]  
CHEN SY, 2002, P IEEE INT C ROB AUT, V3
[4]   Autonomous selection and modification of camera configurations using visibility and manipulability measures [J].
Chu, GW ;
Chung, MJ .
JOURNAL OF ROBOTIC SYSTEMS, 2002, 19 (05) :219-230
[5]  
COWAN CK, 1989, IEEE INT C ROB AUT
[6]  
COWAN GK, 1988, IEEE T PATTERN ANAL, V10, P407
[7]  
GU X, 1999, P IEEE INT C ROB AUT, V4
[8]  
HODGE L, 2003, IEEE T SYST MAN CYB
[9]  
HODGE L, 2001, THESIS U WATERLOO WA
[10]  
Jain R., 1995, Machine Vision, V5