ICSL MPEG-4 Project

RAVEN: Research Architecture for Video Editing and eNcoding

Introduction RAVEN is a user-friendly environment for segmenting video objects. Users can segment manually, use a variety of automatic or semi-automatic plug-in algorithms, or use a combination of manual and computer-assisted methods. An integrated MPEG-4 encoder allows users to efficiently compress the video in an industry standard format. Features Plug-in interface allows users to easily add new segmentation and tracking algorithms to the environment Algorithm developers can concentrate on writing algorithms instead of creating a user interface Consistent and friendly user interface for different segmentation and tracking methods Multiple undo/redo for single-frame editing operations Multiple display modes for visualizing segmentations to assess their quality Timeline display for identifying segmented video objects and the frames that have been segmented Interactive segmentation plug-ins enable faster initialization of tracking algorithms and fast segmentation of still images Video objects can be decomposed into sub-objects that may be more easily segmented using semi-automatic methods Integration with an MPEG-4 encoder to efficiently compress segmented video objects System Requirements Microsoft Windows 95/98 or Microsoft Windows NT 4.0, 64 MB RAM. Hard drive space requirements depend on the size of the video sequences that will be edited. For CIF-size sequences of 60 seconds, we recommend at least 500 MB of free space. Screen Shots RAVEN user interface Demonstration Video This video shows the RAVEN user interface and the process of segmenting multiple objects in a video sequence using multiple plug-in algorithms. A fully interactive segmentation algorithm is shown as well as the ATracker algorithm. Separate higher quality movies for the other algorithms can be viewed from their web pages. View video (22.9 MB MPEG-1) Publications T. Schoepflin, C. Lau, R. Garg, D. Kim, and Y. Kim, "A Research Environment for Developing and Testing Object Tracking Algorithms," Proceedings of SPIE Electronic Imaging 2001, vol. 4310, pp. 667-675 (2001). [ PDF ]