Quantitative analysis of the viewpoint consistency constraint in model-based vision
作者： L. Du , G.D. Sullivan , K.D. Baker
关键词:
摘要: The authors present a quantitative analysis of the viewpoint consistency constraint (VCC), which is fundamental principle behind model-based methods for recognizing 3-D objects from 2-D data. It defines measure error (VCE), based on formal model image feature errors. Existing establishing correspondences using VCC are discussed. poor performance incremental demonstrated and attributed to failure ensure that global improves during search. A more reliable method, ascent, uses VCE explicitly as heuristic state-space search, presented. two algorithms compared in an experimental study. approach alternative illustrated, may be applied object recognition generally. >
sci-hub.se 参考文章(12)
W Eric, L Grimson, Tomás Lozano-Pérez, Model-based recognition and localization from sparse range or tactile data The International Journal of Robotics Research. ,vol. 3, pp. 382- 414 ,(1987) , 10.1177/027836498400300301
R. M. Bodington, G. D. Sullivan, K. D. Baker, Experiments on the use of the ATMS to label features for object recognition european conference on computer vision. pp. 542- 551 ,(1990) , 10.1007/BFB0014904
L. Du, G. D. Sullivan, K. D. Baker, Modelling Data Complexity for Model-based Vision british machine vision conference. pp. 570- 579 ,(1992) , 10.1007/978-1-4471-3201-1_59
A.D. Worrall, K.D. Baker, G.D. Sullivan, Model bases perspective inversion Image and Vision Computing. ,vol. 7, pp. 17- 23 ,(1989) , 10.1016/0262-8856(89)90015-2
A. Rydz, G. D. Sullivan, K. D. Baker, Model-Based Vision using a Planar Representation of the Viewsphere alvey vision conference. pp. 1- 6 ,(1988) , 10.5244/C.2.1
G. D. Sullivan, Alvey MMI-007 Vehicle Exemplar: Performance and Limitations. alvey vision conference. pp. 1- 8 ,(1987) , 10.5244/C.1.6
S Zhang, G.D. Sullivan, K.D. Baker, Relational model construction and 3D object recognition from single 2D monochromatic image british machine vision conference. ,vol. 10, pp. 313- 318 ,(1992) , 10.1016/0262-8856(92)90048-8
L Du, G.D. Sullivan, K.D. Baker, 3D grouping by viewpoint consistency ascent british machine vision conference. ,vol. 10, pp. 301- 307 ,(1992) , 10.1016/0262-8856(92)90046-6
Chris Goad, Special purpose automatic programming for 3D model-based vision Morgan Kaufmann Publishers Inc.. pp. 371- 381 ,(1987) , 10.1016/B978-0-08-051581-6.50041-6
David G. Lowe, Three-dimensional object recognition from single two-dimensional images Artificial Intelligence. ,vol. 31, pp. 355- 395 ,(1987) , 10.1016/0004-3702(87)90070-1