Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (1997)
June 17, 1997 to June 19, 1997
Michael Oren , MIT
Constantine Papageorgiou , MIT
Pawan Sinha , MIT
Edgar Osuna , MIT
Tomaso Poggio , MIT
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 (handcrafted) 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 coeficients 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 eficiency of the wavelet template make it an effective tool for object detection.
E. Osuna, P. Sinha, M. Oren, T. Poggio and C. Papageorgiou, "Pedestrian Detection Using Wavelet Templates," Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR), Puerto Rico, 1997, pp. 193.