Efficient two-stream action recognition on FPGA
Journal
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Pages
3070-3074
Date Issued
2021
Author(s)
Abstract
Action recognition is an important research field that has many applications in surveillance, video search, autonomous vehicles, etc. However, current state-of-the-art action classifiers are still not widely adopted in embedded applications yet. The major reason is that action recognition needs to process both spatial and temporal streaming data to precisely identify actions, which is compute- intensive and power hungry. To solve this issue, researchers start using FPGA to run action recognition models with minimum power. In this paper, we propose a new hardware architecture of action recognition on FPGA. Our model is based on the popular two-stream neural network. By optimizing the optical flow and convolution operations in the temporal domain, our method can achieve similar accuracy with one order of magnitude less operations than other C3D baseline models. We have implemented our model on Xilinx Ultrascale+ ZCU102 and released the source code. ? 2021 IEEE.
Subjects
Computer hardware description languages
Computer vision
Security systems
'current
Action classifier
Action recognition
Autonomous Vehicles
Power
Research fields
State of the art
Surveillance video
Two-stream
Video search
Field programmable gate arrays (FPGA)
SDGs
Type
conference paper