Contour based object detection using part bundles

被引:19
作者
Lu, ChengEn [1 ,2 ,4 ]
Adluru, Nagesh [3 ]
Ling, Haibin [2 ]
Zhu, Guangxi [1 ,4 ]
Latecki, Longin Jan [2 ]
机构
[1] Wuhan Natl Lab Optoelect, Div Commun & Intelligent Networks, Wuhan 430074, Peoples R China
[2] Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 USA
[3] Univ Wisconsin, Ctr Biotechnol, Madison, WI 53705 USA
[4] Huazhong Univ Sci & Technol, Elect & Informat Engn Dept, Wuhan 430074, Peoples R China
基金
美国国家科学基金会; 中国国家自然科学基金;
关键词
Part bundle; Shape context; Object detection; CLASSIFICATION; TEXTURE; SINGLE;
D O I
10.1016/j.cviu.2010.03.009
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
In this paper we propose a novel framework for contour based object detection from cluttered environments. Given a contour model for a class of objects, it is first decomposed into fragments hierarchically. Then, we group these fragments into part bundles, where a part bundle can contain overlapping fragments. Given a new image with set of edge fragments we develop an efficient voting method using local shape similarity between part bundles and edge fragments that generates high quality candidate part configurations. We then use global shape similarity between the part configurations and the model contour to find optimal configuration. Furthermore, we show that appearance information can be used for improving detection for objects with distinctive texture when model contour does not sufficiently capture deformation of the objects. (C) 2010 Elsevier Inc. All rights reserved.
引用
收藏
页码:827 / 834
页数:8
相关论文
共 40 条
[1]
[Anonymous], 2007, A Stochastic Grammar oF Images
[2]
[Anonymous], P EUR C COMP VIS
[3]
[Anonymous], CVPRW
[4]
[Anonymous], 2007, CVPR
[5]
[Anonymous], ICPR WORKSH LEARN AD
[6]
[Anonymous], NIPS
[7]
[Anonymous], 1999, ICCV
[8]
[Anonymous], ICCV 07
[9]
BAI X, 2009, ACTIVE SKELETON NONR
[10]
Shape matching and object recognition using shape contexts [J].
Belongie, S ;
Malik, J ;
Puzicha, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (04) :509-522