A Method of Observing Acoustic Scattering and Absorption By Fish Schools Using Autonomous Underwater Vehicles

2017 ◽  
Vol 42 (1) ◽  
pp. 29-36 ◽  
Author(s):  
Arthur E. Newhall ◽  
Ying-Tsong Lin ◽  
Thomas M. Grothues ◽  
James F. Lynch ◽  
Glen G. Gawarkiewicz
Keyword(s):  
Autonomous Underwater Vehicles ◽  
Acoustic Scattering ◽  
Underwater Vehicles ◽  
Fish Schools

Modeling the Stability of Fish Schools: Exchange of Individual Fish between Schools of Skipjack Tuna (Katsuwonus pelamis)

1991 ◽  
Vol 48 (6) ◽  
pp. 1081-1091 ◽  
Author(s):  
Ray Hilborn
Keyword(s):  
Maximum Likelihood ◽  
Exchange Model ◽  
Maximum Likelihood Estimates ◽  
Data Sets ◽  
Skipjack Tuna ◽  
Katsuwonus Pelamis ◽  
Fish Schools ◽  
Individual Fish ◽  
The Stability

Three data sets that involve intensive mark and recapture of schools of skipjack tuna (Katsuwonus pelamis) are examined for information about exchange of individuals between schools. A formal exchange model is proposed, and maximum likelihood estimates of the parameters are found. It appears that individuals exchange quite rapidly between schools of skipjack; 16–63% of individuals apparently leave a school each day to join other schools. It is possible, however, that what are operationally defined as schools by fishermen consist of smaller more stable subunits.

Modeling the acoustic scattering from large fish schools using the Bloch-Floquet theorem

2013 ◽  
Vol 133 (5) ◽  
pp. 3538-3538
Author(s):  
Jason A. Kulpe ◽  
Michael J. Leamy ◽  
Karim G. Sabra
Keyword(s):  
Acoustic Scattering ◽  
Large Fish ◽  
Fish Schools ◽  
Floquet Theorem

scholarly journals Automatic segmentation of fish using deep learning with application to fish size measurement

2019 ◽  
Vol 77 (4) ◽  
pp. 1354-1366 ◽  
Author(s):  
Rafael Garcia ◽  
Ricard Prados ◽  
Josep Quintana ◽  
Alexander Tempelaar ◽  
Nuno Gracias ◽  
...  
Keyword(s):  
Imaging System ◽  
Automatic Segmentation ◽  
Accurate Estimate ◽  
Commercial Fishing ◽  
Fish Schools ◽  
Individual Fish ◽  
Time Operation ◽  
Artificial Illumination ◽  
Real Time Operation ◽  
Fish Detection

Abstract One of the leading causes of overfishing is the catch of unwanted fish and marine life in commercial fishing gears. Echosounders are nowadays routinely used to detect fish schools and make qualitative estimates of the amount of fish and species present. However, the problem of estimating sizes using acoustic systems is still largely unsolved, with only a few attempts at real-time operation and only at demonstration level. This paper proposes a novel image-based method for individual fish detection, targeted at drastically reducing catches of undersized fish in commercial trawling. The proposal is based on the processing of stereo images acquired by the Deep Vision imaging system, directly placed in the trawl. The images are pre-processed to correct for nonlinearities of the camera response. Then, a Mask R-CNN architecture is used to localize and segment each individual fish in the images. This segmentation is subsequently refined using local gradients to obtain an accurate estimate of the boundary of every fish. Testing was conducted with two representative datasets, containing in excess of 2600 manually annotated individual fish, and acquired using distinct artificial illumination setups. A distinctive advantage of this proposal is the ability to successfully deal with cluttered images containing overlapping fish.

Sign in / Sign up

Export Citation Format

Share Document