Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
It is very important to target detecting hardware and algorithm design in the field of target tracking field. A kind of detection algorithm using SVM (support vector machine) and AdaBoost which selects representative Harr characters is proposed. SVM uses selected Harr wavelet characters as input data in training and classifying procedure. In order to accelerate SVM classify and detect speed, the cascade method is also been used. Moreover, Hardware system design is also a key to decrease algorithm time. This paper introduces construct, theory and mainly chipset function of hardware system in brief. In the end, experiment result shows that this system not only improves the tracking precision but also detecting speed and meets the real time and high precision requirement of target tracking system.