A trainable system for object detection

Citation
C. Papageorgiou et T. Poggio, A trainable system for object detection, INT J COM V, 38(1), 2000, pp. 15-33
Citations number
34
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN journal
09205691 → ACNP
Volume
38
Issue
1
Year of publication
2000
Pages
15 - 33
Database
ISI
SICI code
0920-5691(200006)38:1<15:ATSFOD>2.0.ZU;2-Q
Abstract
This paper presents a general, trainable system for object detection in unc onstrained, cluttered scenes. The system derives much of its power from a r epresentation that describes an object class in terms of an overcomplete di ctionary of local, oriented, multiscale intensity differences between adjac ent regions, efficiently computable as a Haar wavelet transform. This examp le-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 detecti on tasks using the same architecture. In addition, we quantify how the repr esentation affects detection performance by considering several alternate r epresentations including pixels and principal components. We also describe a real-time application of our person detection system as part of a driver assistance system.