Moving Object Detection and Tracking Algorithm Using Hybrid Decomposition Parallel Processing

Abstract

Moving object detection, classification and tracking are more crucial and challenging task in most of the computer vision and machine vision applications such as robot navigation, human behavior analysis, traffic flow analysis and etc. However, most of object detection and tracking algorithms are not suitable for real time processing and causes slower processing speed due to the processing and analyzing of high resolution video from high-end multiple cameras. It requires more computation and storage. To address the aforementioned problem, this paper proposes a way of parallel processing of temporal frame differencing algorithm for object detection and contour tracking using the mixture of functional and domain decomposition parallel processing techniques. It has two main contributions. First, steps of frame differencing are parallelized using functional decomposition technique. Second, the processing of frames in each steps of frame differencing is again parallelized using domain decomposition technique. Finally, the performance is evaluated in Aneka Private Cloud platform and which yields to detect and track the object very swiftly and accurately.