Human Detection Based on Second Generation Bandelet Transform

Base on geometric flow of images and the second generation bandelet transform, a new feature extraction method was proposed, and it was used to detect human in still images. In the paper, bandelet coefficients and their statistical values were extracted as the feature of human images, combined with Adaboost classifier to classify and detect human in images. In the proposed algorithm, some general statistical values of the bandelet coefficients were computed to enhance the classification capacity. The results of human detection experiments indicate that the proposed method can describe human characteristics and improve the performance of classifier effectively. It is very suitable for human detection in still images.