Achieving high quality video exchange between two mobile devices (eg. smart phones) is challenging since both devices are often constrained by resources such as remaining battery life, device temperature, and communication bandwidth. Traditional video compression techniques, Predictive and Distributed Video Coding (PVC and DVC), are designed to manage these resources effectively at either an encoder (video sending device) or a decoder (video receiving device), but not both simultaneously. However, since more than one device is participating in the video exchange, it makes more sense to utilize opportunities at both devices for better resource efficiency. For example, if the video sender is low on energy, the receiver should carry a heavier portion of the video compression workload.

In our research, we have proposed a novel distribute coding and optimization framework that makes better use of encoder and decoder resources. Specifically, we investigated novel schemes that combine elements of state-of-the-art PVC and DVC techniques to partition compression workload between encoder and decoder. Our approach took advantage of such schemes to dynamically optimized the distribution of workload between sender and receiver for lower overall energy consumption under thermal, communication bandwidth, and video quality constraints. Our framework consisted of offline and online phases. In the offline phase, we characterized video complexity, bandwidth usage, and energy usage. In the online phase, we used the parameters and profiles form the offline step to determine better distribution of workload to achieve lower overall energy consumption while maintaining thermal, communication bandwidth, and video quality constraints. Results showed that the proposed framework obtaining significant improvements to resource efficiency compared to strictly PVC and DVC systems.

Our Conference and Journal Papers

NOTE: This directory contains pdf/ps files of articles that may be covered by copyright. You may browse the articles at your convenience, in the same spirit as you may read a journal or a proceedings article in a public library. Retrieving, copying, or distributing these files may violate copyright protection laws.

• D. Forte, A. Srivastava, “Energy and Thermal-Aware Video Coding via Encoder/Decoder Workload Balancing”, ACM Transactions on Embedded Computing Systems (TECS), Vol. 12, No. 2, May 2013. [link]
• D. Forte, A. Srivastava, “Adaptable Video Compression and Transmission using Lossy and Workload Balancing Techniques”, NASA/ESA Conference on Adaptive Hardware and Systems (AHS), June 2011 [Awarded AHS-2011 Best Student Paper] [link]
• D. Forte, A. Srivastava, “Energy-Aware Video Coding of Multiple Views via Workload Balancing”, NASA/ESA Conference on Adaptive Hardware and Systems (AHS), June 2011. [link]
• D. Forte, A.Srivastava, “Energy and Thermal-Aware Video Coding via Encoder/Decoder Workload Balancing”, International Symposium on Low Power Electronics and Design (ISLPED), Aug. 2010. [link]