Advanced Video Processing and Compression

One frame from a surveillance video and extracted object tunnels

One frame from a surveillance video and extracted object tunnels

In the last two decades, video has evolved from an analog, narrowly-used and expensive, both in terms of production and distribution, entertainment medium to a digital, uniquitous  and relatively inexpensive commodity with a wide range of applications, from entertainment, through surveillance/security/military to healthcare/elderly-care/enviro-care. All this has been made possible by astonishing advances in digital processing algorithms and hardware, as well as visual capture and display devices.  A palm-size HDTV camera, a 50GB BluRay disk and a 65-in flat panel display,  common today, were unthinkable even a decade ago. Does this mean that no more advances in the area of processing and compression of video data are needed? Not at all. The huge success of wireless services, including video, calls for new solutions in order to assure robust video delivery in mobile applications. The growing interest in 3-D capture, transmission and display technologies fueled by Hollywood’s involvement in 3-D film production calls for new computationally-efficient multi-view processing algorithms. There is also an increasing need for scalable delivery of video content to a range of devices, from smartphones, through netbooks and laptops, to desktop and HDTV screens in a cost- and bit-efficient manner. And there are ubiquitous surveillance cameras, each generating up to 2,592,000 frames per day, that nobody monitors.

Thus, the goal is to develop advanced video processing and compression algorithms to serve the needs of next-generation visual surveillance and communications systems. We have primarily concentrated on automatic algorithms for the detection, localization and summarization of visual events in the field of view of a camera and on alternative video compression algorithms. Below are listed some of our ongoing and recent projects.