DocumentCode
2315233
Title
Detecting fish in underwater video using the EM algorithm
Author
Evans, Fiona H.
Author_Institution
Sch. of Math. & Stat., Western Australia Univ., WA, Australia
Volume
3
fYear
2003
fDate
14-17 Sept. 2003
Abstract
We consider the problem of detecting fish in underwater video. We adopt a modeling framework, where the shape of each fish is assumed to be multivariate Gaussian. Mixture modeling is used to classify noise and varying numbers of fish. The mixture parameters are estimated using an EM algorithm that incorporates an Akaike information criterion to simultaneously estimate the number of components in the mixture. In addition, the algorithm does not require careful initialization.
Keywords
Gaussian processes; parameter estimation; video signal processing; zoology; Akaike information criterion; EM algorithm; Gaussian mixture modeling; fish detection; multivariate Gaussian; parameter estimation; underwater video; Cameras; Distortion measurement; Marine animals; Monitoring; Optical imaging; Parameter estimation; Sea measurements; Shape; Stress; Underwater tracking;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on
ISSN
1522-4880
Print_ISBN
0-7803-7750-8
Type
conf
DOI
10.1109/ICIP.2003.1247423
Filename
1247423
Link To Document