Real-Time Implementation Of Human Action Recognition System Based On Motion Analysis

This paper proposes a Pixel Streams-based FPGA implementation of a real-time system that can detect and recognize human activity using Handel-C. The first part of this work details the hardware implementation of a real-time video surveillance system on FPGA, including all the stages, i.e., capture, processing, and display, using DK IDE. The targeted circuit is an XC2V1000 FPGA embedded on Agility's RC200E board. In the second part of this work, we propose a GUI programmed using Visual C++ to facilitate the implementation for novice users. Using this GUI, the user can program/erase the FPGA or change the parameters of different algorithms and filters. The PixelStreams-based implementation was successfully realized and validated for real-time motion detection and recognition.