An Application of Shape-Based Level Sets to Fish Detection in Underwater Images

Ravanbakhsh, M.; Shortis, M.; Shaifat, F.; Mian, A.; Harvey, Euan; Seager, J.

Access Status

Fulltext not available

Authors

Ravanbakhsh, M.

Shortis, M.

Shaifat, F.

Mian, A.

Harvey, Euan

Seager, J.

Date

2014

Type

Conference Paper

Metadata

Show full item record

Citation

Ravanbakhsh, M. and Shortis, M. and Shaifat, F. and Mian, A. and Harvey, E. and Seager, J. 2014. An Application of Shape-Based Level Sets to Fish Detection in Underwater Images, in C. Arrowsmith, C. Bellman, W. Cartwright, M. Shortis (ed), Proceedings of the Geospatial Science Research 3 Symposium, Dec 2 2014. Melbourne, Australia: CEUR Workshop Proceedings.

Source Title

Proceedings of the Geospatial Science Research 3 Symposium

Source Conference

Geospatial Science Research 3 Symposium

Additional URLs

http://ceur-ws.org/Vol-1307/paper6.pdf

ISSN

16130073

School

Department of Environment and Agriculture

Remarks

URI

http://hdl.handle.net/20.500.11937/25769

Collection

Curtin Research Publications

Abstract

Underwater stereo-video technology systems are used widely for measurement of fish. However the effectiveness of the stereo-video measurement has been limited because most operational systems still rely on a human operator. In this paper, an automated approach for fish detection using a shape-based level sets framework is presented. Shape knowledge of fish is modelled by Principal Component Analysis (PCA). The Haar classifier is used for precise position of the fish head and snout in the image, which is vital information for close proximity initialisation of the shape model. The approach has been tested on under-water images representing a variety of challenging situations typical of the underwater environment, such as background interference and poor contrast boundaries. The results obtained demonstrate that the approach is capable ofovercoming these limitations and capturing the fish outline at sub-pixel accuracy.