An FPGA-Optimized Architecture of Real-time Farneback Optical Flow
Zhe Pan, Yuruo Jin, Xiaohong Jiang, Jian Wu · 2020
Optical flow estimation is a fundamental tool for computer vision applications. As a classical optical flow algorithm, Farneback version was a good blend of accuracy and runtime performance for a long time. This work presents a dataflow-based architecture of Farneback optical flow with high level synthesis (HLS) tools. Multi-dimension separable convolution, Block RAM array and deep pipeline optimization techniques are applied to reduce both space and time. The system is implemented on XC7K325T FPGA with an image size of $640 \times 480.$ It supports complete Farneback algorithm for any user-defined image pyramid levels and iteration times. It can process 31 fps, 8x faster than OpenCV version with 3 pyramid levels and 1 iteration time.