Region-of-interest prediction for interactively streaming regions of high resolution video

Aditya Mavlankar, David Varodayan, Bernd Girod
2007 Packet Video 2007  
This projects considers region-of-interest (ROI) prediction strategies for a client-server system that interactively streams regions of high resolution video. The system operates in two modes. In manual mode, the user interacts actively to view select regions in each frame of video. In tracking mode, the user simply indicates an object to track and the system supplies a ROI trajectory without further interaction. In both cases, the client has a buffer of low resolution overview video frames
more » ... ew video frames available. We propose and study ROI prediction schemes that can take advantage of the motion information contained in these buffer frames. For the manual mode, prediction aids pre-fetching and aims to reduce distortion experienced by the viewer. For the tracking mode, the prediction aims to create a smooth and stable trajectory that satisfies the user's expectation of tracking.
doi:10.1109/packet.2007.4397027 fatcat:apdk37c7xfcb5cskfbeqwd5gw4