Scale-Hierarchical 3D Object Recognition in Cluttered Scenes

被引:38
作者
Bariya, Prabin [1 ]
Nishino, Ko [1 ]
机构
[1] Drexel Univ, Dept Comp Sci, Philadelphia, PA 19104 USA
来源
2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2010年
关键词
REPRESENTATION;
D O I
10.1109/CVPR.2010.5539774
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
3D object recognition in scenes with occlusion and clutter is a difficult task. In this paper, we introduce a method that exploits the geometric scale-variability to aid in this task. Our key insight is to leverage the rich discriminative information provided by the scale variation of local geometric structures to constrain the massive search space of potential correspondences between model and scene points. In particular, we exploit the geometric scale variability in the form of the intrinsic geometric scale of each computed feature, the hierarchy induced within the set of these intrinsic geometric scales, and the discriminative power of the local scale-dependent/invariant 3D shape descriptors. The method exploits the added information in a hierarchical coarse-to-fine manner that lets it cull the space of all potential correspondences effectively. We experimentally evaluate the accuracy of our method on an extensive set of real scenes with varying amounts of partial occlusion and achieve recognition rates higher than the state-of-the-art. Furthermore, for the first time we systematically demonstrate the method's ability to accurately localize objects despite changes in their global scales.
引用
收藏
页码:1657 / 1664
页数:8
相关论文
共 14 条
[1]  
CARMICHAEL O, 1999, P 2 INT C 3D DIG IM, P358, DOI DOI 10.1109/IM.1999.805366
[2]   Point signatures: A new representation for 3D object recognition [J].
Chua, CS ;
Jarvis, R .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 25 (01) :63-85
[3]   COSMOS - A representation scheme for 3D free-form objects [J].
Dorai, C ;
Jain, AK .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (10) :1115-1130
[4]   BONSAI - 3-D OBJECT RECOGNITION USING CONSTRAINED SEARCH [J].
FLYNN, PJ ;
JAIN, AK .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1991, 13 (10) :1066-1075
[5]   The sample tree: A sequential hypothesis testing approach to 3D object recognition [J].
Greenspan, M .
1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1998, :772-779
[6]  
Grimson W., 1990, OBJECT RECOGNITION C
[7]   MODEL-BASED RECOGNITION AND LOCALIZATION FROM SPARSE RANGE OR TACTILE DATA [J].
GRIMSON, WEL ;
LOZANOPEREZ, T .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 1984, 3 (03) :3-35
[8]  
GRIMSON WEL, 1988, P INT C COMP VIS LOS, P218
[9]   Using spin images for efficient object recognition in cluttered 3D scenes [J].
Johnson, AE ;
Hebert, M .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (05) :433-449
[10]  
Mian A., 2006, IEEE T PATTERN ANAL