Smart Cameras as Embedded Systems

I ncreasingly powerful integrated circuits are making an entire range of new applications possible. Complementary metal-oxide semiconductor (CMOS) sensors, for example, have made the digital camera a commonplace consumer item. These light-sensitive chips, positioned where film would normally be, capture images as reusable digital files that users can upload to their computer, manipulate with software, and distribute electronically. Recent technological advances are enabling a new generation of smart cameras that represent a quantum leap in sophistication. While today's digital cameras capture images, smart cameras capture high-level descriptions of the scene and analyze what they see. These devices could support a wide variety of applications including human and animal detection, surveillance, motion analysis, and facial identification. Video processing has an insatiable demand for real-time performance. Fortunately, Moore's law provides an increasing pool of available computing power to apply to real-time analysis. Smart cameras leverage very large-scale integration (VLSI) to provide such analysis in a low-cost, low-power system with substantial memory. Moving well beyond pixel processing and compression, these systems run a wide range of algorithms to extract meaning from streaming video. Because they push the design space in so many dimensions, smart cameras are a leading-edge application for embedded system research. has developed a first-generation smart camera system that can detect people and analyze their movement in real time. Although there are many approaches to real-time video analysis, we chose to focus initially on human gesture recognition—identifying whether a subject is walking, standing, waving his arms, and so on. Because much work remains to be done on this problem, we sought to design an embedded system that can incorporate future algorithms as well as use those we created exclusively for this application. As Figure 1 shows, our algorithms use both low-level and high-level processing. The low-level component identifies different body parts and categorizes their movement in simple terms. The high-level component, which is application-dependent, uses this information to recognize each body part's action and the person's overall activity based on scenario parameters. The system captures images from the video input, which can be either uncompressed or compressed (MPEG and motion JPEG), and applies four different algorithms to detect and identify human body parts. Region extraction. The first algorithm transforms the pixels of an image, like that shown in Figure 2a, into an M × N bitmap and eliminates the background. It then detects the body part's skin area using a YUV …