Multi-target tracking by using particle filtering and a social force model

This paper presents a particle filter for multiple target tracking. The main contribution of this work is in the proposed likelihood function accounting for the interactions between the objects. The filter likelihood function is calculated by combining a social force model for human behaviour with image features such as colour and motion. The added social force model contributes to coping with occlusions between the objects. The performance of the developed algorithm is validated on real video data. The results demonstrate the algorithm accuracy during complex interactions between the objects.