DocumentCode :
1467156
Title :
Example-based object detection in images by components
Author :
Mohan, Anuj ; Papageorgiou, Constantine ; Poggio, Tomaso
Author_Institution :
Kana Commun., Redwood City, CA, USA
Volume :
23
Issue :
4
fYear :
2001
fDate :
4/1/2001 12:00:00 AM
Firstpage :
349
Lastpage :
361
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
Keywords :
learning (artificial intelligence); object detection; pattern classification; adaptive combination of classifiers; cluttered scenes; component-based approach; data classification architecture; example-based classifier; example-based detectors; example-based object detection; head; left arm; legs; proper geometric configuration; right arm; static images; Detectors; Humans; Layout; Leg; Machine learning; Machine learning algorithms; Magnetic heads; Object detection; Pattern recognition; Robustness;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.917571
Filename :
917571
Link To Document :
بازگشت