|
Abstract : |
This thesis presents a general trainable framework for object detection in static images of cluttered scenes and a novel motion based extension that enhances performance over video sequences. The detection technique we develop is based on a wavelet representation of an object class derived from a statistical analysis of the class instances. By learning an object class in terms of a subset of an overcomplete dictionary of wavelet basis functions, we derive a compact representation of an object class which is used as input to a support vector machine classifier. The paradigm we present successfully handles the major difficulties of object detection: overcoming the in-class variability of complex classes such as faces and pedestrians and providing a very low false detection rate, even in unconstrained environments. We demonstrate the capabilities of the technique in two domains whose inherent information content differs significantly. The first system is face detection; we extend the methodology to the domain of people which, unlike faces, vary greatly in color, texture, and patterns. Unlike previous approaches, this system learns from examples, |
