DMCA
A Trainable System for Object Detection (2000)
| Citations: | 343 - 7 self |
BibTeX
@MISC{Papageorgiou00atrainable,
author = {Constantine Papageorgiou and Tomaso Poggio},
title = { A Trainable System for Object Detection},
year = {2000}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes an object class in terms of an overcomplete dictionary of local, oriented, multiscale intensity differences between adjacent regions, efficiently computable as a Haar wavelet transform. This example-based learning approach implicitly derives a model of an object class by training a support vector machine classifier using a large set of positive and negative examples. We present results on face, people, and car detection tasks using the same architecture. In addition, we quantify how the representation affects detection performance by considering several alternate representations including pixels and principal components. We also describe a real-time application of our person detection system as part of a driver assistance system.
Keyphrases
trainable system object detection object class real-time application car detection task detection performance support vector machine classifier several alternate representation cluttered scene example-based learning approach multiscale intensity difference large set adjacent region negative example principal component present result person detection system driver assistance system haar wavelet transform overcomplete dictionary
