An intelligent framework for spatio-temporal vehicle tracking

Recently, the Intelligent Transportation Systems (ITS) have been identified as the new paradigm to address the growing mobility problems, and to alleviate congestion and augment the quality of vehicular flow. This paper presents an intelligent and automatic framework for spatio-temporal vehicle tracking in video sequences in order to provide useful information to the traffic control center. The spatio-temporal relationships of the objects are captured automatically via a proposed unsupervised image/video segmentation method and multimedia input strings. A traffic video sequence is used to demonstrate the effectiveness of the proposed framework to identify and track the vehicle objects in the video sequence.