Example-based object detection in images by components
Mohan, A.
Papageorgiou, C.
Poggio, T.
Kana Commun., Redwood City, CA;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Apr 2001
Volume: 23,
Issue: 4
On page(s): 349-361
ISSN: 0162-8828
References Cited: 27
CODEN: ITPIDJ
INSPEC Accession Number: 6921862
Digital Object Identifier: 10.1109/34.917571
Current Version Published: 2002-08-07
Abstract
We present a general example-based framework for detecting objects
in static images by components. The technique is demonstrated by
developing a system that locates people in cluttered scenes. The system
is structured with four distinct example-based detectors that are
trained to separately find the four components of the human body: the
head, legs, left arm, and right arm. After ensuring that these
components are present in the proper geometric configuration, a second
example-based classifier combines the results of the component detectors
to classify a pattern as either a “person” or a
“nonperson.” We call this type of hierarchical architecture,
in which learning occurs at multiple stages, an adaptive combination of
classifiers (ACC). We present results that show that this system
performs significantly better than a similar full-body person detector.
This suggests that the improvement in performance is due to the
component-based approach and the ACC data classification architecture.
The algorithm is also more robust than the full-body person detection
method in that it is capable of locating partially occluded views of
people and people whose body parts have little contrast with the
background
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
