Block Division Based CAMShift Algorithm for Real-Time Object Tracking Using Distributed Smart Cameras

Abstract

In this paper, we present a histogram based real-time object tracking system using distributed smart cameras. Each such smart camera module consists of a camera and an embedded device that is capable of performing the task of object tracking entirely by itself. The module recognizes and tracks the object in real time. The processed video stream containing the marked object is then transmitted to a central server for display. The embedded device runs a novel block division based CAMShift algorithm proposed in this paper. We show that this technique reduces the number of computations required and hence is more suitable for embedded platforms. The solution is implemented using a central server and multiple camera modules with non-overlapping fields of view in indoor settings. We validate the improvement in the performance by comparing the experimental results with existing solutions.