SBIR-STTR Award

This Small Business Innovation Research (SBIR) Phase I proposal aims to create a low bandwidth streaming algorithm for high definition (HD) videoconferencing. The ultimate goal is a software system that achieves less than 150 msec one-way end-to-end delay (the typical delays of telephone) for 1280x720 @ 30 fps video at 512 Kbps (the typical upload speeds of high-end consumer broadband). Most videoconferencing systems today stream video at 1/10 of HD resolution. At such resolution, it is often difficult to see facial expressions. Commercial HD products are currently only available in hardware. These systems all require network speeds beyond the limits of broadband. This research aims to develop videoconferencing software for broadband. Faces and whiteboards are the two most common elements of interest in a videoconference. This research will combine real-time network sensing and the domain knowledge of how people perceive facial expressions, whiteboards, and nondescript background to create a unique compression/streaming algorithm. The input video is segmented into different regions. The whiteboard and background will be enhanced for sharpness using novel super resolution techniques. Two core technologies will be developed: 1) perceptual resolution enhancement of whiteboard and background, and 2) network adaptive HD streaming. Although the concepts just described have been explored in principle by thousands of researches over the last few decades, previous efforts did not result in any HD products

This SBIR Phase II project extends the PI's Phase I to create a theoretical bandwidth and latency efficient multimedia streaming framework for communication. The ultimate goal is a software system that achieves less than 150 msec one-way end-to-end delay (the typical delay of telephone) for a 10-30 site meeting supporting wideband audio, full motion video, and application/desktop sharing over broadband networks. The industry norm to achieve multiparty video/web conferencing is the client-server architecture. Client-server architecture is expensive to deploy due to the number of servers required and the bandwidth required at the server nodes. Peer-to-peer approaches have been successfully used for large scale file sharing. However, peer-to-peer approaches have been relatively unexplored to scale the number of participants in a single meeting. This research combines real-time network sensing and the domain knowledge of video and web conferencing to create a scalable and cost effective peer-to-peer streaming algorithm. The maximum number of sites in a multiparty videoconferencing is typically 4-6. Given the limited screen resolution of a laptop/desktop, methods for showing 10-30 full motion video and a shared application are relatively unexplored. Poor user experience from inadequate user interface is a major barrier to the adoption of previous video/web conferencing tools. This research combines recent human factor discoveries to create a novel user interface that intuitively supports multiparty communication. Since AT&T invented videoconferencing in 1927, videoconferencing has been one commercial failure after another. The PI's previous research suggests that such failures are rooted in inadequate knowledge of the human factor requirements of videoconferencing. Based on previous research, they are developing a commercial software system which will make substantial impact on telework, remote education, and humanitarian operations. This project aims to create a low-cost peer-to-peer alternative to client-server architectures for large scale meetings. If successful, the architecture proposed in this effort could have significant commercial impact.