A novel low-cost FPGA-based real-time object tracking system

In current visual object tracking system, the CPU or GPU-based visual object tracking systems have high computational cost and consume a prohibitive amount of power. Therefore, in this paper, to reduce computational burden of Camshift algorithm, we propose a novel visual object tracking algorithm by exploiting the properties of binary classifier and Kalman predictor. Moreover, we present a low-cost FPGA-based real-time object tracking hardware architecture. Extensive evaluations on OTB benchmark demonstrate that the proposed system has extremely compelling real-time, stability and robustness. The evaluation results show that the accuracy of our algorithm is about 53%, the overlap rate is about 50%, and the average speed is about 309 fps.