论文信息 - Detecting fish in underwater video using the EM algorithm

Detecting fish in underwater video using the EM algorithm

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.

Fiona F. Evans

[1] Rabab K. Ward,et al. Determining fish size and swimming speed in cages and tanks using simple video techniques , 1997 .

[2] J. A. Marchant,et al. Fish sizing and monitoring using a stereo image analysis system applied to fish farming , 1995 .

[3] H. Bozdogan. Model selection and Akaike's Information Criterion (AIC): The general theory and its analytical extensions , 1987 .

[4] Euan S. Harvey,et al. A comparison of the precision and accuracy of estimates of reef-fish lengths determined visually by divers with estimates produced by a stereo-video system. , 2001 .

[5] R. Boyce,et al. Simple scale determination on underwater stereo pairs , 1964 .

[6] Anil K. Jain,et al. Unsupervised Learning of Finite Mixture Models , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[7] John A. Marchant,et al. Predicting salmon biomass remotely using a digital stereo-imaging technique , 1996 .

[8] Jeff A. Bilmes,et al. A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[9] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .