A Specific Target Track Method Based on SVM and AdaBoost

Some target tracking occasions often requires to tracking a kind of target, such as human face, automobile and so on. A specific target tracking algorithm based on support vector machine (SVM) and AdaBoost is proposed. Moreover, the characteristic data of SVM is a critical factor to success to detecting target. The method selects part of Harr wavelet characters by AdaBoost as input data of SVM training and classifying. In order to accelerate SVM classify and detect speed, the cascade method is also been used. It is shows by experiments that this system improves not only the tracking precision but also detecting speed.