Untitled

Abstract

Laser scanners have a lot of advantages over conventional video cameras. Data processing in laser scanner system becomes faster and easier because there is no need to record real world videos. Besides, the problem of private life conservation is taken away. This paper proposes an approach to track objects from laser scanned dataset. Data points collected by each scan of laser scanners are considered as video frame. Support vector machine (SVM) along with Hungarian algorithm and Kalman filter are used to obtain trajectories of objects from the laser scanned dataset. Experimental results on the same laser scanned datasetshow that the method of SVM with Hungarian algorithm and Kalman filter performs better than that of its alternative having various thresholds with Hungarian algorithm and Kalman filter.