Pedestrian detection using wavelet templates

• Published in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 193 - 199
• Main Authors: Oren, M., Papageorgiou, C., Sinha, P., Osuna, E., Poggio, T.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 1997
• Subjects: Artificial intelligence; Face detection; Humans; Image databases; Layout; Maximum likelihood detection; Object detection; Pattern classification; Robustness; Shape
• ISBN: 9780818678226; 0818678224
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.1997.609319

This paper presents a trainable object detection architecture that is applied to detecting people in static images of cluttered scenes. This problem poses several challenges. People are highly non-rigid objects with a high degree of variability in size, shape, color, and texture. Unlike previous approaches, this system learns from examples and does not rely on any a priori (hand-crafted) models or on motion. The detection technique is based on the novel idea of the wavelet template that defines the shape of an object in terms of a subset of the wavelet coefficients of the image. It is invariant to changes in color and texture and can be used to robustly define a rich and complex class of objects such as people. We show how the invariant properties and computational efficiency of the wavelet template make it an effective tool for object detection.