Robust Real-time Object Detection

DMCA

Robust Real-time Object Detection (2001)

Cached

Download Links

Other Repositories/Bibliography

CiteULike

by Paul Viola , Michael Jones

Venue:	International Journal of Computer Vision
Citations:	1184 - 4 self

BibTeX

@INPROCEEDINGS{Viola01robustreal-time,
    author = {Paul Viola and Michael Jones},
    title = {Robust Real-time Object Detection},
    booktitle = {International Journal of Computer Vision},
    year = {2001}
}

OpenURL

Abstract

This paper describes a visual object detection framework that is capable of processing images extremely rapidly while achieving high detection rates. There are three key contributions. The first is the introduction of a new image representation called the “Integral Image ” which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features and yields extremely efficient classifiers [6]. The third contribution is a method for combining classifiers in a “cascade ” which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. A set of experiments in the domain of face detection are presented. The system yields face detection performace comparable to the best previous systems [18, 13, 16, 12, 1]. Implemented on a conventional desktop, face detection proceeds at 15 frames per second. 1.

Keyphrases

robust real-time object detection background region detection performace efficient classifier integral image high detection rate face detection visual object detection framework learning algorithm object-like region new image representation third contribution previous system system yield critical visual feature face detection proceeds small number key contribution conventional desktop

DMCA