Books.org participates in affiliate programs including Bookshop.org and the Amazon Services LLC Associates Program. We may earn a commission from qualifying purchases made through links on this page, at no additional cost to you.
Synopsis
The increasing availability of low-cost, low-power, highly accurate video imagery has brought rapid growth in the applications using this data. Video provides multiple temporal constraints, making it easier to analyze a complex and coordinated series of events that cannot be understood by looking at a single image or a few frames. Arguing for a bottom-up approach to object recognition and event detection, the authors present a framework for the extraction of meaningful information from video. The text's underlying principle is that many diverse pieces of evidence are more useful for object recognition and event detection than the most elaborate algorithm working on an impoverished image representation. Annotation c. Book News, Inc., Portland, OR (booknews.com)