Scalable video visual analytics. (January 2015)

• Record Type: Journal Article
• Authors: Höferlin, Benjamin; Höferlin, Markus; Heidemann, Gunther; Weiskopf, Daniel
• Other Names: Cook Kristin guest-editor.; Grinstein Georges guest-editor.; Whiting Mark guest-editor.
• Is Part Of: Information visualization. Volume 14:Number 1(2015:Jan.)
• Page Start: 10
• Page End: 26
• Publication Date: 2015-01
• Subjects: Visual analytics -- video analysis -- VAST Challenge 2009 -- scalability -- situational awareness; Information visualization -- Periodicals; 006.605
• DOI: 10.1177/1473871613488571
• Languages: English
• ISSNs: 1473-8716

Abstract

Video visual analytics is the research field that addresses scalable and reliable analysis of video data. The vast amount of video data in typical analysis tasks renders manual analysis by watching the video data impractical. However, automatic evaluation of video material is not reliable enough, especially when it comes to semantic abstraction from the video signal. In this article, we describe the video visual analytics method that combines the complementary strengths of human recognition and machine processing. After inspecting the challenges of scalable video analysis, we derive the main components of visual analytics for video data. Based on these components, we present our video visual analytics system that has its origins in our IEEE VAST Challenge 2009 participation.