Download:
|
by Liang Zhao, Chuck Thorpe
In IEEE Workshop on Human Modeling, Analysis and Synthesis
http://www-dev.ri.cmu.edu:8080/pub_files/pub2/zhao_liang_2000_1/zhao_liang_2000_1.ps.gz
Add To MetaCart
Abstract:
Human detection and body parts identification are important and challenging problems in computer vision. High performance human detection depends on reliable contour extraction, but contour extraction is an under constrained problem without the knowledge about the objects to be detected. This paper proposes a recursive context reasoning (RCR) approach to solving the above dilemma. A TRS 1-invariant probabilistic model is designed to encode the shapes of the body parts and the context information--- the size and spatial relationships between body parts. A Bayesian framework is developed to perform human detection and part identification under partial occlusion. A contour reconstruction procedure is introduced to integrate the human model and the identified body parts to predict the shapes and locations of the parts missed by the contour detector; the refined contours are used to reevaluate the likelihood ratio. Therefore, contour extraction, part identification, and human detection are improved iteratively. The experimental results of the RCR approach to human detection and body parts identification in cluttered scenes are very encouraging.
Citations
|
1118
|
A method for registration of 3-D shapes
– Besl, Mckay
- 1992
|
|
170
|
Model-based vision: a program to see a walking person
– Hogg
- 1983
|
|
146
|
Towards model-based recognition of human movements in image sequences
– Rohr
- 1994
|
|
135
|
Cardboard people: A parameterized model of articulated image motion
– Ju, Black, et al.
- 1996
|
|
107
|
Model-based image analysis of human motion using constraint propagation
– O’Rourke, Badler
- 1980
|
|
82
|
A probabilistic approach to object recognition using local photometry and global geometry
– Burl, Weber, et al.
- 1998
|
|
68
|
Recognition by Parts
– Pentland
- 1987
|
|
53
|
Body plans
– Forsyth, Fleck
- 1997
|
|
43
|
Ghost: A Human Body Part Labeling System Using Silhouettes
– Haritaoglu, Harwood, et al.
- 1998
|
|
36
|
Approximate tree matching and shape similarity
– Liu, Geiger
- 1999
|
|
35
|
Stereo and Neural Network-Based Pedestrian Detection
– Zhao, Thorpe
- 2000
|
|
31
|
Pfinder: Real time tracking of the human body
– Wren, Azarbayejani, et al.
- 1997
|
|
29
|
On characterizing ribbons and finding skewed symmetries
– Ponce
- 1989
|
|
28
|
Axial representations of shape
– Rosenfeld
- 1986
|
|
14
|
Constraint fusion for recognition and localization of articulated and constrained objects
– Hel-Or, Werman
- 1996
|
|
13
|
Exploiting the generic viewpoint assumption
– Freeman
- 1996
|
|
10
|
W ---Real Time Detection and Tracking of People and their Parts
– Haritaoglu, Harwood, et al.
- 1997
|
|
8
|
The Measure of Man and Woman
– Tilley
- 1993
|
|
8
|
A Model Based Approach to Labeling Human Body Outlines
– Leung, Yang
- 1994
|
|
6
|
A Contour-based Part Segmentation Algorithm”, Int'l
– Bennamoun
- 1994
|
|
5
|
Active Motion-Based Segmentation of Human Body Outlines
– Kakadiaris, Metsxas, et al.
- 1994
|
|
2
|
Stochastic Models, Estimation and Control
– Mayback
- 1982
|
|
1
|
Backpack: Detection of People Carrying Objects Using Silhouettes
– al
- 1999
|
|
1
|
Dynamic Feature Ordering for Efficient Registration", ICCV'99, pp 10841091
– Cham, Rehg
- 1999
|
