Automated event detection in underwater video
Authors:
- 1 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5, P2749
Abstract
We present an attentional selection system for processing video streams from remotely operated underwater vehicles (ROVs). The system identifies potentially interesting visual events spanning multiple frames based on low-level spatial properties of salient tokens, which are associated with those events and tracked over time. If video frames contain interesting events, they are labeled "interesting", otherwise they are labeled "boring". By marking the interesting events and omitting "boring" frames in the output stream, we augment the productivity of human video annotators, or, alternatively, provide input for a subsequent object classification algorithm.Keywords
This publication has 8 references indexed in Scilit:
- Tiburon: development of an ROV for ocean science research2002
- Distributed multiplexers for an ROV control and data system2002
- Seasonal abundance and vertical distribution of mesopelagic calycophoran siphonophores in Monterey Bay, CAJournal of Plankton Research, 2000
- Marine ecological research in seashore and seafloor systems:accomplishments and future directionsMarine Ecology Progress Series, 2000
- The Coevolution of Undersea Vehicles and Deep-Sea ResearchMarine Technology Society Journal, 1999
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Seasonal abundance of the siphonophore, Nanomia bijuga, in Monterey BayDeep Sea Research Part II: Topical Studies in Oceanography, 1998
- The importance of long time-series in understanding the variability of natural systemsHelgoland Marine Research, 1995