GestureCam: A Smart Camera for Gesture Recognition and Gesture-Controlled Web Navigation

Smart camera, or an intelligent camera, is an embedded vision system which captures and processes image to extract application-specific information in real time. Smart cameras are used in many applications such as automatic control systems, machine vision systems, automatic video surveillance systems and human computer interfaces. What makes a smart camera ´smart´ is a special processing unit inside the camera which performs application specific information processing, for example, skin color detection and motion detection for surveillance purpose. The design of smart camera as an embedded system is challenging because on one hand video processing has insatiable demand for performance and power, and on the other hand embedded systems place considerable constraints on the design. We present our work in progress to build GestureCam, an FPGA-based smart camera that can recognize simple pre-defined head and hand gestures. As an application of the GestureCam, we present the design of a GestureBrowser, an extension to the Mozilla Firefox browser which uses the GestureCam to capture and recognize a user´s head and hand gesture commands to control Web navigation. The GestureBrowser idea is a step further toward next generation natural human computer interaction. Also presented is a proof of concept work for the GestureBrowser idea, using a Webcam as image capture device