Moving Target Classification in Video Sequences Based on Features Combination and SVM

Moving target classification plays a very important role in intelligent video surveillance system. A method for moving target classification in video sequences based on features combination and SVM is presented in this paper. In this method, single Gaussian background model based on the background difference method is used to achieve the motion detection, Hu moment features in moving target are extracted, and then Support Vector Machine (SVM) is used to classify the moving target, human, animal (dog), vehicle and bike. To solve the problem of low classification ratio for human and animal, the other features, Area and euler number, are added, and classification ratio is improved.