Viz-A-Vis: Toward Visualizing Video Through Computer Vision
2008 (English)In: IEEE Transactions on Visualization and Computer Graphics, ISSN 1077-2626, E-ISSN 1941-0506, Vol. 14, no 6, 1261-1268 p.Article in journal (Refereed) PublishedText
In the established procedural model of information visualization, the first operation is to transform raw data into data tables . The transforms typically include abstractions that aggregate and segment relevant data and are usually defined by a human, user or programmer. The theme of this paper is that for video, data transforms should be supported by low level computer vision. High level reasoning still resides in the human analyst, while part of the low level perception is handled by the computer. To illustrate this approach, we present Viz-A-Vis, an overhead video capture and access system for activity analysis in natural settings over variable periods of time. Overhead video provides rich opportunities for long-term behavioral and occupancy analysis, but it poses considerable challenges. We present initial steps addressing two challenges. First, overhead video generates overwhelmingly large volumes of video impractical to analyze manually. Second, automatic video analysis remains an open problem for computer vision.
Place, publisher, year, edition, pages
IEEE conference proceedings, 2008. Vol. 14, no 6, 1261-1268 p.
Index Terms—, Spatiotemporal visualization, Spatiotemporal visualization, time series data, video visualization, sensor analytics, image/video analytics, image/video analytics, sensor analytics, time series data, video visualization
Computer Science Human Computer Interaction
IdentifiersURN: urn:nbn:se:kth:diva-184694DOI: 10.1109/TVCG.2008.185OAI: oai:DiVA.org:kth-184694DiVA: diva2:916492
QC 201604072016-04-032016-04-032016-04-07Bibliographically approved