Custom Hardware Architectures for Posture Analysis

This paper describes the design and implementation of hardware architectures for posture analysis. Posture analysis is an active research area in computer vision. It can be used in providing health-care solutions, such as monitoring home care patients. We report four contributions in this paper: (a) requirements for a posture analysis system with hardware support; (b) a workflow for posture analysis that fulfils these requirements; (c) various architectures and their implementation based on a high-level hardware design approach; (d) performance evaluation for our derived designs. For instance our best design, which targets a Xilinx XC2V6000 FPGA at 90.2MHz, is able to perform posture analysis at a rate of 1164 frames per second with frame size of 320 × 240 pixels, or 220 frames per second for DVD quality of 720 × 576 pixels per frame. This represents a 145-fold speedup over a software version running on a 3Ghz Pentium-4 computer.

• Type: Conference
• Year: 2005
• Where: FPT
• Authors: M. P. T. Juvonen, José Gabriel F. Coutinho, J. L. Wang, B. L. Lo, Wayne Luk, Oskar Mencer, G. Z. Yang
• Keywords: Active Research Area, FPT 2005, Hardware, Hardware Architectures, Posture Analysis