Unsupervised video objects detection and tracking using region based level-set

Abstract

in this paper, we propose an efficient unsupervised method for moving object detection and tracking. To achieve this goal, we use basically a region-based level-set approach and some conventional methods. Modeling of the background is the first step that initializes the following steps such as objects segmentation and tracking. Our proposed method produces good results and decreases processing time. We present here the main steps of our method and preliminary results which are very encouraging for many applications such as video surveillance and traffic monitoring.

A Survey on Moving Object Tracking in Video

“…Kim and Sim [39] proposed a region-based tracking method for the detection of multiple moving objects which uses a differential image. A method of background image update is applied to ensure accurate object detection in unconstrained environment.…”