A Video Objects Classification Method Based on GLDM and SVDD

In order to classify specific objects extracted from videos, an improved algorithm is proposed in this paper. Firstly it extracts characters of proportion of skin color, ratio of area to perimeter, ratio of height to width and the statistical features of gray level dependence matrices (GLDM) to distinguish person, vehicle, crowd and the other class. It trains three kinds of support vector data description (SVDD) with features synthesized by the extracted characters. A decision tree is built with three nodes corresponding to the trained SVDDs. The experiments show that the features are properly to discriminate objects from each other and the decision tree classifier built by SVDD achieves an improved performance.