Real-Time Object Tracking Based on Optical Flow

The optical flow algorithm has been widely used in object detection and tracking. These applications are hard to implement on the hardware level in real-time, due to their high computational complexity. In this paper, we propose an efficient hardware architecture for the accurate computation of the Lucas-Kanade (L-K) optical flow. The optical flow estimation involves several tasks such as Gaussian smoothing, gradient computation, integral calculation, and the vector computation, which are processed in a parallel architecture. The proposed architecture was simulated and verified by synthesizing onto a Xilinx Field Programmable Gate Array (FPGA), which can process 640×480 resolution frames at 30 frames/s.