Adapting the Streaming Video Based on the Estimated Position of the Region of Interest

Streaming real time video over wireless networks cannot guarantee that all the frames could meet their deadlines. Wireless networks may suffer from bandwidth limitations. To reduce the streaming data over wireless networks, we propose a technique to identify, and extract the Region Of Interest (ROI), and drop the non-ROI from the frames that are between the reference frames. The Sum of Absolute Differences (SAD) will compute the consecutive video frames to identify the ROI as it considered the most motion and important region. The reconstruction mechanism to the non-ROI is performed on the mobile side by applying linear interpolation between the reference frames. We evaluate the proposed approach by using Mean Opinion Score (MOS) measurements. MOS are used to evaluate the two scenarios with equivalent encoding size, where the users observe the first scenario with a low bit rate for the original videos, while for the second scenario the users observe our proposed approach. The results show that our technique significantly reduces the amount of data, while the reconstruction mechanism provides acceptable video quality to the mobile viewers.