Multiobject trajectory tracking

Authors: Mei Han Wei Xu Hai Tao Yihong Gong

Publish Date: 2007/03/31

Volume: 18, Issue: 3-4, Pages: 221-232

PDF Link

Abstract

The majority of existing tracking algorithms are based on the maximum a posteriori solution of a probabilistic framework using a Hidden Markov Model where the distribution of the object state at the current time instance is estimated based on current and previous observations However this approach is prone to errors caused by distractions such as occlusions background clutters and multiobject confusions In this paper we propose a multiple object tracking algorithm that seeks the optimal state sequence that maximizes the joint multiobject stateobservation probability We call this algorithm trajectory tracking since it estimates the state sequence or “trajectory” instead of the current state The algorithm is capable of tracking unknown timevarying number of multiple objects We also introduce a novel observation model which is composed of the original image the foreground mask given by background subtraction and the object detection map generated by an object detector The image provides the object appearance information The foreground mask enables the likelihood computation to consider the multiobject configuration in its entirety The detection map consists of pixelwise object detection scores which drives the tracking algorithm to perform joint inference on both the number of objects and their configurations efficiently The proposed algorithm has been implemented and tested extensively in a complete CCTV video surveillance system to monitor entries and detect tailgating and piggybacking violations at access points for over six months The system achieved 983 precision in event classification The violation detection rate is 904 and the detection precision is 852 The results clearly demonstrate the advantages of the proposed detection based trajectory tracking framework

Keywords: