Detection of Crowds of People by Use of Wavelet Features and Parameter Free Statistical Models

Based on a sample of 8000 manually segmented video images acquired in a subway station, we examine if heads of pedestrians can be detected by use of wavelet features and parameter free statistical classi-fiers. In particular we address the question of which wavelet filter to use for feature generation and how to model class conditional densities of features. We show that a markov chain based approach in combination with HAAR-wavelets is a good compromise between high recognition rates and computational efficiency. The latter is required since developed algorithms are supposed to run on a dedicated low cost hardware.