Near-infrared imaging to quantify the feeding behavior of fish in aquaculture

Delaunay Triangulation was applied to the extraction of behavioral characteristics.Support Vector Machine was used to classify the reflective frame.Serious reflection frames were removed and new data were fitted.The linear correlation coefficient between FIFFB and human expert can reach 0.945. In aquaculture, fish feeding behavior under culture conditions holds important information for the aquaculturist. In this study, near-infrared imaging was used to observe feeding processes of fish as a novel method for quantifying variations in fish feeding behavior. First, images of the fish feeding activity were collected using a near-infrared industrial camera installed at the top of the tank. A binary image of the fish was obtained following a series of steps such as image enhancement, background subtraction, and target extraction. Moreover, to eliminate the effects of splash and reflection on the result, a reflective frame classification and removal method based on the Support Vector Machine and Gray-Level Gradient Co-occurrence Matrix was proposed. Second, the centroid of the fish was calculated by the order moment, and then, the centroids were used as a vertex in Delaunay Triangulation. Finally, the flocking index of fish feeding behavior (FIFFB) was calculated to quantify the feeding behavior of a fish shoal according to the results of the Delaunay Triangulation, and the FIFFB values of the removed reflective frames were fitted by the Least Squares Polynomial Fitting method. The results show that variations in fish feeding behaviors can be accurately quantified and analyzed using the FIFFB values, for which the linear correlation coefficient versus expert manual scoring reached 0.945. This method provides an effective method to quantify fish behavior, which can be used to guide practice.

[1]  Sun Guoxiang,et al.  Image segmentation algorithm for greenhouse cucumber canopy under various natural lighting conditions , 2016 .

[2]  Anders Fernö,et al.  Swimming behaviour as an indicator of low growth rate and impaired welfare in Atlantic halibut (Hippoglossus hippoglossus L.) reared at three stocking densities , 2004 .

[3]  A. H. Thiessen.  PRECIPITATION AVERAGES FOR LARGE AREAS , 1911 .

[4]  Allen B. Downey,et al.  Primitive-Based Classification of Pavement Cracking Images , 1993 .

[5]  Zhenjie Xiong,et al.  Combination of spectra and texture data of hyperspectral imaging for differentiating between free-range and broiler chicken meats , 2015 .

[6]  Daoliang Li,et al.  Fish species classification by color, texture and multi-class support vector machine using computer vision , 2012 .

[7]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[8]  Wei Fang,et al.  Development of an intelligent feeding controller for indoor intensive culturing of eel , 2005 .

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

[10]  Ying Liu,et al.  Behavioral responses of tilapia (Oreochromis niloticus) to acute fluctuations in dissolved oxygen levels as monitored by computer vision , 2006 .

[11]  T. Wyatt,et al.  Some effects of food density on the growth and behaviour of plaice larvae , 1972, Marine Biology.

[12]  S. Beucher,et al.  Watersheds of functions and picture segmentation , 1982, ICASSP.

[13]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[14]  K. J. Chen,et al.  Color grading of beef fat by using computer vision and support vector machine , 2010 .

[15]  Royann J. Petrell,et al.  Accuracy of a machine-vision pellet detection system , 2003 .

[16]  Serge Beucher,et al.  Use of watersheds in contour detection , 1979 .

[17]  Kurt E. Brassel,et al.  A Procedure to Generate Thiessen Polygons , 2010 .

[18]  B. Sturm,et al.  A new approach for categorizing pig lying behaviour based on a Delaunay triangulation method. , 2017, Animal : an international journal of animal bioscience.

[19]  R. Mallekh,et al.  An acoustic detector of turbot feeding activity , 2003 .

[20]  Boaz Zion,et al.  Ranching fish using acoustic conditioning: Has it reached a dead end? , 2012 .

[21]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[22]  Rabab K. Ward,et al.  Detection and counting of uneaten food pellets in a sea cage using image analysis , 1995 .

[23]  E. Belcher,et al.  Dual-Frequency Identification Sonar (DIDSON) , 2002, Proceedings of the 2002 Interntional Symposium on Underwater Technology (Cat. No.02EX556).

[24]  Jianping Li,et al.  Spatial behavioral characteristics and statistics-based kinetic energy modeling in special behaviors detection of a shoal of fish in a recirculating aquaculture system , 2016, Comput. Electron. Agric..

[25]  Milan Říha,et al.  Use of high-frequency imaging sonar (DIDSON) to observe fish behaviour towards a surface trawl , 2012 .

[26]  Jia-Pu Jang,et al.  A highly sensitive underwater video system for use in turbid aquaculture ponds , 2016, Scientific Reports.

[27]  M. Kolehmainen,et al.  Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines , 2009 .

[28]  Jiunn-Ming Chen,et al.  Development of an adaptive neural-based fuzzy inference system for feeding decision-making assessment in silver perch (Bidyanus bidyanus) culture , 2015 .

[29]  Min Sun,et al.  Models for estimating feed intake in aquaculture: A review , 2016, Comput. Electron. Agric..

[30]  R. Dennis Cook,et al.  Cross-Validation of Regression Models , 1984 .

[31]  Jun-Hu Cheng,et al.  Classification of fresh and frozen-thawed pork muscles using visible and near infrared hyperspectral imaging and textural analysis. , 2015, Meat science.

[32]  Fan Liangzhong,et al.  Measuring feeding activity of fish in RAS using computer vision , 2014 .

[33]  T. Arimoto,et al.  The background adaptation of the flatfish, Paralichthys olivaceus , 1991, Physiology & Behavior.

[34]  R. S. McKinley,et al.  Can feeding status and stress level be assessed by analyzing patterns of muscle activity in free swimming rainbow trout (Oncorhynchus mykiss Walbaum) , 2004 .

[35]  Colin Hunter,et al.  A video-based movement analysis system to quantify behavioral stress responses of fish. , 2004, Water research.

[36]  Petr Císař,et al.  Infrared reflection system for indoor 3D tracking of fish , 2015 .

[37]  Md. Sumon Shahriar,et al.  Behavior classification of cows fitted with motion collars: Decomposing multi-class classification into a set of binary problems , 2016, Comput. Electron. Agric..

[38]  Joan Oca,et al.  Measurement of sole activity by digital image analysis , 2009 .

[39]  Jo Arve Alfredsen,et al.  Original papers: Development of two telemetry-based systems for monitoring the feeding behaviour of Atlantic salmon (Salmo salar L.) in aquaculture sea-cages , 2011 .

[40]  Xiaoming Liu,et al.  Automatic Feeding Control for Dense Aquaculture Fish Tanks , 2015, IEEE Signal Processing Letters.

[41]  Margarita Ruiz-Altisent,et al.  Shape determination of horticultural produce using two-dimensional computer vision – A review , 2012 .

[42]  G. Mylonakis,et al.  Effects of background color on growth performances and physiological responses of scaled carp (Cyprinus carpio L.) reared in a closed circulated system , 2000 .

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

[44]  B. F. Terjesen,et al.  The use of acoustic acceleration transmitter tags for monitoring of Atlantic salmon swimming activity in recirculating aquaculture systems (RAS) , 2016 .

[45]  Uwe Richter,et al.  Using machine vision for investigation of changes in pig group lying patterns , 2015, Comput. Electron. Agric..

[46]  Petr Císar,et al.  Automated multiple fish tracking in three-Dimension using a Structured Light Sensor , 2016, Comput. Electron. Agric..

[47]  Raymond Williams,et al.  A Computer Vision System to Analyse the Swimming Behaviour of Farmed Fish in Commercial Aquaculture Facilities: a Case Study using Cage-held Atlantic Salmon , 2011 .

[48]  Zhenbo Cheng,et al.  Water quality monitoring using abnormal tail-beat frequency of crucian carp. , 2015, Ecotoxicology and environmental safety.

[49]  Bastien Sadoul,et al.  A new method for measuring group behaviours of fish shoals from recorded videos taken in near aquaculture conditions , 2014 .

[50]  Alexios Glaropoulos,et al.  A computer-vision system and methodology for the analysis of fish behavior , 2012 .

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

[52]  Jan Flusser,et al.  Near infrared face recognition: A literature survey , 2016, Comput. Sci. Rev..