Conference paper
Detecting fish in underwater video using the EM algorithm
Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429), Vol.2
2003 International Conference on Image Processing (Barcelona, Spain, 14/09/2003–17/09/2003)
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.
Details
- Title
- Detecting fish in underwater video using the EM algorithm
- Authors/Creators
- F.H. Evans (Author/Creator) - The University of Western Australia
- Publication Details
- Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429), Vol.2
- Conference
- 2003 International Conference on Image Processing (Barcelona, Spain, 14/09/2003–17/09/2003)
- Identifiers
- 991005543602407891
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
75 File views/ downloads
69 Record Views