Automatic Bluefin Tuna Sizing with a Combined Acoustic and Optical Sensor

A proposal is described for an underwater sensor combining an acoustic device with an optical one to automatically size juvenile bluefin tuna from a ventral perspective. Acoustic and optical information is acquired when the tuna are swimming freely and the fish cross our combined sensor’s field of view. Image processing techniques are used to identify and classify fish traces in acoustic data (echogram), while the video frames are processed by fitting a deformable model of the fishes’ ventral silhouette. Finally, the fish are sized combining the processed acoustic and optical data, once the correspondence between the two kinds of data is verified. The proposed system is able to automatically give accurate measurements of the tuna’s Snout-Fork Length (SFL) and width. In comparison with our previously validated automatic sizing procedure with stereoscopic vision, this proposal improves the samples per hour of computing time by 7.2 times in a tank with 77 juveniles of Atlantic bluefin tuna (Thunnus thynnus), without compromising the accuracy of the measurements. This work validates the procedure for combining acoustic and optical data for fish sizing and is the first step towards an embedded sensor, whose electronics and processing capabilities should be optimized to be autonomous in terms of the power supply and to enable real-time processing.

[1]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  Gabriela Andreu García,et al.  Enhanced fish bending model for automatic tuna sizing using computer vision , 2018, Comput. Electron. Agric..

[3]  Huimin Lu,et al.  Underwater image dehazing using joint trilateral filter , 2014, Comput. Electr. Eng..

[4]  Jan Urban,et al.  Application of machine vision systems in aquaculture with emphasis on fish: state-of-the-art and key issues , 2017 .

[5]  Pau Muñoz-Benavent,et al.  Automatic Bluefin Tuna (Thunnus thynnus) biomass estimation during transfers using acoustic and computer vision techniques , 2019, Aquacultural Engineering.

[6]  Ling Qin,et al.  Three-Dimensional Indoor Mobile Mapping With Fusion of Two-Dimensional Laser Scanner and RGB-D Camera Data , 2014, IEEE Geoscience and Remote Sensing Letters.

[7]  Rudy J. Kloser,et al.  In situ measurements of target strength with optical and model verification: a case study for blue grenadier, Macruronus novaezelandiae , 2011 .

[8]  Gareth F. Difford,et al.  Validating non-invasive growth measurements on individual Atlantic salmon in sea cages using diode frames , 2020, Comput. Electron. Agric..

[9]  Rudy J. Kloser,et al.  Measurement and visual verification of fish target strength using an acoustic-optical system attached to a trawlnet , 2009 .

[10]  Maria Petrou,et al.  Image Segmentation and Edge Detection , 2001 .

[11]  Robert P. Mueller,et al.  Video and acoustic camera techniques for studying fish under ice: a review and comparison , 2006, Reviews in Fish Biology and Fisheries.

[12]  Alex De Robertis,et al.  Assessing habitat utilization and rockfish (Sebastes spp.) biomass on an isolated rocky ridge using acoustics and stereo image analysis , 2010 .

[13]  K. Sawada,et al.  Development of an acoustic-optical system to estimate target-strengths and tilt angles from fish aggregations , 2004, Oceans '04 MTS/IEEE Techno-Ocean '04 (IEEE Cat. No.04CH37600).

[14]  Hermann J. Enzenhofer,et al.  Fixed-location riverine hydroacoustics as a method of enumerating migrating adult Pacific salmon: comparison of split-beam acoustics vs. visual counting , 1998 .

[15]  Nikolaos Doulamis,et al.  Deep Learning for Computer Vision: A Brief Review , 2018, Comput. Intell. Neurosci..

[16]  K. Phillips,et al.  Assessing the operational feasibility of stereo-video and evaluating monitoring options for the Southern Bluefin Tuna Fishery ranch sector , 2008 .

[17]  Philip Culverhouse,et al.  Towards automating underwater measurement of fish length: a comparison of semi-automatic and manual stereo–video measurements , 2017 .

[18]  Akira Asada,et al.  Application of a high-resolution acoustic video camera to fish classification: An experimental study , 2015, 2015 IEEE Underwater Technology (UT).

[19]  Hsueh-Jung Lu,et al.  Ex situ and in situ measurements of juvenile yellowfin tuna Thunnus albacares target strength , 2011, Fisheries Science.

[20]  J. Lines,et al.  An automatic image-based system for estimating the mass of free-swimming fish , 2001 .

[21]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[22]  J. L. Cort,et al.  Relationship between weight and linear dimensions of Bluefin tuna (Thunnus thynnus) following fattening on western Mediterranean farms , 2018, PloS one.

[23]  Michele Scardi,et al.  A dual camera system for counting and sizing northern bluefin tuna (Thunnus thynnus; Linnaeus, 1758) stock, during transfer to aquaculture cages, with a semi automatic Artificial Neural Network tool. , 2009 .

[24]  Kang Lee,et al.  IEEE 1588 standard for a precision clock synchronization protocol for networked measurement and control systems , 2002, 2nd ISA/IEEE Sensors for Industry Conference,.

[25]  Fernando López-García,et al.  Vision-based discrimination of tuna individuals in grow-out cages through a fish bending model , 2016, Comput. Electron. Agric..

[26]  L. Stien,et al.  Sea caged Atlantic salmon display size-dependent swimming depth , 2012 .

[27]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[28]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Janne Heikkilä,et al.  A four-step camera calibration procedure with implicit image correction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[30]  Pau Muñoz-Benavent,et al.  Automatic Bluefin Tuna sizing using a stereoscopic vision system , 2018 .

[31]  Stuart Robson,et al.  The accuracy and precision of underwater measurements of length and maximum body depth of southern bluefin tuna (Thunnus maccoyii) with a stereo-video camera system , 2003 .

[32]  Faisal Shafait,et al.  Progress in the Automated Identification, Measurement, and Counting of Fish in Underwater Image Sequences , 2016 .

[33]  Mark Underwood,et al.  A combined acoustic and optical instrument for industry managed fisheries studies , 2014, 2014 Oceans - St. John's.

[34]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[35]  Boaz Zion,et al.  Review: The use of computer vision technologies in aquaculture - A review , 2012 .

[36]  Kiho Kwak,et al.  Indirect Correspondence-Based Robust Extrinsic Calibration of LiDAR and Camera , 2016, Sensors.

[37]  Pablo Carrera,et al.  Comparison of airborne lidar with echosounders: a case study in the coastal Atlantic waters of southern Europe , 2006 .

[38]  Michael S. Lew,et al.  Deep learning for visual understanding: A review , 2016, Neurocomputing.

[39]  Kouichi Sawada,et al.  Target-strength, length, and tilt-angle measurements of Pacific saury (Cololabis saira) and Japanese anchovy (Engraulis japonicus) using an acoustic-optical system , 2009 .

[40]  Felipe Aguado-Giménez,et al.  Growth, food intake and feed conversion rates in captive Atlantic bluefin tuna (Thunnus thynnus Linnaeus, 1758) under fattening conditions , 2005 .

[41]  Aníbal Ollero,et al.  Computer vision and robotics techniques in fish farms , 2003, Robotica.

[42]  Royann J. Petrell,et al.  Measurement of fish size in atlantic salmon (salmo salar l.) cages using stereographic video techniques , 1998 .

[43]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[44]  Jie Shan,et al.  Extrinsic Calibration between a Camera and a 2D Laser Rangefinder using a Photogrammetric Control Field , 2019, Sensors.