Multi-Person Recognition Using Viola-Jones and Kalman Filter for Target Tracking

Multi-person tracking is a summary of single trackers. Everyone's motion is independent of others. This paper presents a multi-level framework for target tracking in simple and complex environments. Kalman filter is using to perform target tracking. The Kalman filter tracks people even if their spots merge, provide more efficiency to track multiple people. It provides the best estimate of its position in each time step. If all the noise is Gaussian, then the optimality is guaranteed. Based on position estimates, KF gives better results to avoid occlusion. For each object in the scene, a separate KF is initialized and its trajectory is modeled. The first phase detects all the faces in the crowded scenes and second phase detects the face of the target person using Viola-Jones algorithm for face recognition and third phase tracks the target person from that crowd.