Tracking human motions for security system
Junzo Watada, Zalih Binti Musaand · 2008
The aim of this study is to build a prototype of a multi-camera tracking system for a security system that enables us to track several human motions at one time. In this paper two innovative methods: foot step detection method and particle filtering method. Generally, to recognize a single human motion is easier than to link several human motions. This is because several human motions move different directions, while a single human motion moves one direction in a certain period. Therefore, we need a system that is reliable to track of several human motions in every frame. In this paper we propose a new method for human tracking systems using foot step direction with prediction formula to forecast the direction of human movement. Furthermore, an enhanced method based on particle filtering enables us to detect and track a human movement. This process can enable the system to predict which direction the object will move and also can give the signal to other cameras to aware about that the object will appear. The detail outcome and expected result are discussed in this paper..