Implementation of face detection and tracking on a low cost embedded system using fusion technique

Abstract

This paper presents the fusion techniques for detecting and tracking the face. The proposed method combines the Viola-Jones method, the CamShift tracking, and the Kalman Filter tracking. The objective is to increase the face detection rate, while reduce the computation cost. The proposed method is implemented on a low cost embedded system based-on the Raspberry Pi module. The experimental results show that the average detection rate of 98.3% is achieved, and it is superior compared to the existing techniques. The proposed system achieves the frame rate of 7.09 fps in the real-time face detection.