Recent advances in imaging and embedded computing technology enable widescale computer vision systems that incorporate arrays of low-cost, portable imagers connected through wireless networks. Video surveillance is a particularly important driving application area. This research focuses on embedded systems that can perceive, process, and interpret scene activity.

Sophisticated new video analysis algorithms are emerging for a broad range of important vision and surveillance applications, including activity recognition, anomalous behavior detection, wide-area distributed tracking, and accurate face and gait recognition. Integrating these algorithms into embedded environments creates new research challenges to balance their huge computational and communication demands with the stringent size, power, and memory resource constraints of embedded platforms.

Meeting these challenges requires a systems perspective, drawing on advances from a broad spectrum of fields, including signal processing, AI, computer vision, microelectronics, computer architecture, real-time systems, distributed computing/middleware, and rapid system prototyping. All of these areas are critical to solving real-time automated video surveillance problems with high efficiency and accuracy.

High-Efficiency Background Modeling for low-cost, low-memory embedded platforms	Video-Centric Applications	Parallel Architectures for Multimedia: Portable Video Supercomputers
Midground Object Detection for identifying roadside threats, abandoned luggage, and other suspicious activities	Detecting Illegal Parking in high-traffic areas	High-Performance Color Imaging: color-aware instruction sets
Automated Retargeting of sequential imaging software to parallel execution	Hyperspectral Processing and Data Fusion	Dynamic Optimization of data communication in multimedia architectures