DIRECT EVIDENCE FOR OCCLUSION IN STEREO AND MOTION

被引:19
作者
LITTLE, JJ [1 ]
GILLETT, WE [1 ]
机构
[1] MIT,ARTIFICIAL INTELLIGENCE LAB,CAMBRIDGE,MA 02139
基金
加拿大自然科学与工程研究理事会; 美国国家科学基金会;
关键词
MACHINE VISION; OCCLUSION; STEREO; MOTION;
D O I
10.1016/0262-8856(90)80009-I
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Discontinuities of surface properties are the most important locations in a scene; they are crucial for segmentation because they often coincide with object boundaries1. Standard approaches to discontinuity detection decouple detection of disparity discontinuities from disparity computation. We have developed techniques for locating disparity discontinuities using information internal to the stereo algorithm of Drumheller and Poggio2, rather than by post-processing the stereo data. The algorithm determines displacements by maximizing the sum, at overlapping small regions, of local comparisons. The detection methods are motivated by analysis of the geometry of matching and occlusion, and the fact that detection is not just a pointwise decision. Our methods can be used in combination to produce robust performance. This research is part of a project to build a Vision Machine3 at MIT that integrates outputs from early vision modules. Our techniques have been extensively tested on real images.
引用
收藏
页码:328 / 340
页数:13
相关论文
共 27 条
[1]   A COMPUTATIONAL FRAMEWORK AND AN ALGORITHM FOR THE MEASUREMENT OF VISUAL-MOTION [J].
ANANDAN, P .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1989, 2 (03) :283-310
[2]   ILL-POSED PROBLEMS IN EARLY VISION [J].
BERTERO, M ;
POGGIO, TA ;
TORRE, V .
PROCEEDINGS OF THE IEEE, 1988, 76 (08) :869-889
[3]   A PARALLEL ALGORITHM FOR REAL-TIME COMPUTATION OF OPTICAL-FLOW [J].
BULTHOFF, H ;
LITTLE, J ;
POGGIO, T .
NATURE, 1989, 337 (6207) :549-553
[5]  
DRUMHELLER M, 1986, IEEE J ROBOTIC AUTOM, P1439
[6]  
GAMBLE EB, 1987, AI970 MIT ART INT ME
[7]  
GILLETT W, 1988, THESIS MIT US
[8]  
Hildreth E.C., 1984, MEASUREMENT VISUAL M
[9]  
HILLIS LD, 1985, CONNECTION MACHINE
[10]  
Horn B., 1986, ROBOT VISION, DOI DOI 10.1137/1030032