Clustering and a joint probabilistic data association filter for dealing with occlusions in multi-target tracking

This paper proposes an improved data association technique for dealing with occlusions in tracking multiple people in indoor environments. The developed technique can mitigate complex inter-target occlusions by maintaining the identity of targets during their close physical interactions. It can cope with the origin uncertainty of the multiple measurements and performs measurement to target association by automatically detecting the measurement relevance. The measurements are clustered by using the variational Bayesian method. An improved joint probabilistic data association filter (JPDAF) is proposed to associate measurements to targets with the aid of clustering process and extracting image features. A particle filter is used to track the multiple targets by exploiting the data association information. Both qualitative and quantitative evaluations are presented on real data sets which demonstrate that the proposed algorithm successfully tracks targets while solving complex occlusions.