Automated Fish Detection in Underwater Images Using Shape-Based level Sets

Abstract

Underwater stereo-video systems are widely used for the measurement of fish. However, the effectiveness of 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. Knowledge of the shape of fish is modelled by principal component analysis (PCA). The Haar classifier is used for precise localisation 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 underwater 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 of overcoming these difficulties and capturing the fish outline to sub-pixel accuracy.