Low-Cost Real-Time Gesture Recognition
Brian C. Lovell, Daniel Heckenberg · 2002
A major impediment to developing real-time computer vision systems has been the computational power and level of skill required to process video streams in real-time. This has meant that many researchers have either analysed video streams off-line or used expensive dedicated hardware ac-celeration techniques. Recent software and hardware devel-opments have greatly eased the development burden of real-time image analysis leading to the development of portable systems using cheap PC hardware and software exploiting the Multimedia Extension (MMX) instruction set of the In-tel Pentium chip. This paper describes the implementation of a computationally efficient computer vision system for recognizing hand gestures using efficient coding and MMX-acceleration to achieve real-time performance on low cost hardware. 1.