Spatiotemporal visual attention architecture for video analysis
- 1 January 2004
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Several visual attention (VA) schemes have been proposed with the saliency-based ones being the most popular. The proposed work provides an extension towards VA in video sequences by incorporating the temporal dimension. The architecture is presented in detail and potential applications are investigated. We expect that the extended VA scheme will reveal interesting events across the sequence like occlusions and short occurrences of objects, providing a basis for video surveillance (e.g. intruder detection), segmentation and summarization applicationsKeywords
This publication has 10 references indexed in Scilit:
- Background noise suppression for acoustic localization by means of an adaptive energy detection approachInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008
- Automatic Video Object Segmentation Using Volume Growing and Hierarchical ClusteringEURASIP Journal on Advances in Signal Processing, 2004
- Motion analysis and segmentation through spatio-temporal slices processingIEEE Transactions on Image Processing, 2003
- A saliency-based search mechanism for overt and covert shifts of visual attentionPublished by Elsevier ,2000
- A model of saliency-based visual attention for rapid scene analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- The flat zone approach: A general low-level region merging segmentation methodSignal Processing, 1997
- Video shot detection and characterization for video databasesPattern Recognition, 1997
- Efficient automatic analysis of camera work and microsegmentation of video using spatiotemporal imagesSignal Processing: Image Communication, 1996
- The design and use of steerable filtersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Features and Objects in Visual ProcessingScientific American, 1986