A principled approach to detecting surprising events in video

Primates demonstrate unparalleled ability at rapidly orienting towards important events in complex dynamic environments. During rapid guidance of attention and gaze towards potential objects of interest or threats, often there is no time for detailed visual analysis. Thus, heuristic computations are...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 631 - 637 vol. 1
Main Authors Itti, L., Baldi, P.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Bioinformatics
Brain modeling
Computer science
Computer vision
Event detection
Genomics
Humans
Image analysis
Neuroscience
Streaming media
Online AccessGet full text

Cover

More Information
Summary:Primates demonstrate unparalleled ability at rapidly orienting towards important events in complex dynamic environments. During rapid guidance of attention and gaze towards potential objects of interest or threats, often there is no time for detailed visual analysis. Thus, heuristic computations are necessary to locate the most interesting events in quasi real-time. We present a new theory of sensory surprise, which provides a principled and computable shortcut to important information. We develop a model that computes instantaneous low-level surprise at every location in video streams. The algorithm significantly correlates with eye movements of two humans watching complex video clips, including television programs (17,936 frames, 2,152 saccadic gaze shifts). The system allows more sophisticated and time-consuming image analysis to be efficiently focused onto the most surprising subsets of the incoming data.
ISBN:0769523722
9780769523729
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2005.40