Title
Vision-based discrimination of tuna individuals in grow-out cages through a fish bending model.
Abstract
•A robust deformable 2D model that adapts to tuna movements is proposed.•Fish shape, size, orientation and swimming flexion are automatically obtained.•Success of the fitting process is computed with a proposed Fitting Error Index (FEI).•Experiments found a FEI threshold of 2.2 for optimum discrimination of individuals.•The model contributes to a near-future application to automatic biomass estimation.
Year
DOI
Venue
2016
10.1016/j.compag.2016.10.009
Computers and Electronics in Agriculture
Keywords
Field
DocType
Shape modelling,Fish detection,Underwater video processing,Computer vision,Image segmentation,Automatic biomass estimation
Computer vision,Stereoscopy,Silhouette,Segmentation,Bending,Image segmentation,Artificial intelligence,Tuna,Engineering,Fishing industry,Biometrics
Journal
Volume
ISSN
Citations 
130
0168-1699
1
PageRank 
References 
Authors
0.35
0
5