An Efficient Tracking Algorithm Based on Spatial Kernel and FCM Classifier

A modified movable object tracking algorithm which uses the flexible Metric Distance Transform kernel and FCM Classifier is proposed and tested. The target shape which defines the dn Distance Transform is found based on conventional statistical parameters as feature vector extraction and Fuzzy C-Mean (FCM) classifier to differentiate tracked target from background. This replaces the more usual Epanechnikov kernel (E-kernel), improving target representation and localization without increasing the processing time, minimizing the similarity measure using the Bhattacharya coefficient. The algorithm is tested on several image sequences and shown to achieve robust and reliable framerate tracking.