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.

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

Video-based motion analysis is receiving increasing attention in the domain of computer vision.An object classification algorithm is proposed in this paper used for video surveillance,which can classify moving objects into predefined four categories: human being,crowd,car and bicyclist.In this paper,several simple shape features of moving objects are defined and the SVM(Support Vector Machines),which based on small samples statistical learning theory,is chosen to classify different objects.At last,to meet the real-time requirement,the method of alternative classification is presented and several other methods that can improve the efficiency of classification are described.Experiments show that the method can accurately distinguish human being,crowd,car,and bicyclist.

Liu Li-li

Papers

Research on Targets Classification in Video Surveillance