ABSTRACT
For an optimal fish raising under captivity conditions, biomass calculation is usually an essential factor to estimate the ideal amount of food required. Usually, this process implies human-animal interaction, however, fish manipulation can affect their correct growth or even cause their death. In particular, some fish species like Senegalese sole, can easily be stressed when they are manipulated out from their environment. The advances on image recognition systems have opened a new range of possibilities to avoid any kind of human-animal interaction. With a lowest estimation of 0.8 centimeters, and around 95% of accuracy detection, our novel prototype can successfully provide a highly accurate fish measuring estimation based on an image, which can be provided by any kind of device, such as mobile phone.
- JJ Allaire, Dirk Eddelbuettel, Nick Golding, and Yuan Tang. 2016. TensorFlow for R. https://tensorflow.rstudio.com/Google Scholar
- APROMAR. 2018. (2018).Google Scholar
- Paul J. Ashley. 2007. Fish welfare: Current issues in aquaculture. Applied Animal Behaviour Science 104, 3 (2007), 199 -- 235.Google ScholarCross Ref
- Murat O. Balaban, Gülgün F. Unal Sengör, Mario Gil Soriano, and Elena Guillén Ruiz. 2010. Using Image Analysis to Predict the Weight of Alaskan Salmon of Different Species. Journal of Food Science 75, 3 (2010), E157--E162.Google ScholarCross Ref
- Toni A. Beddow, Lindsay G. Ross, and John A. Marchant. 1996. Predicting salmon biomass remotely using a digital stereo-imaging technique. Aquaculture 146, 3 (1996), 189 -- 203.Google ScholarCross Ref
- Corrado Costa, Michele Scardi, Valerio Vitalini, and Stefano Cataudella. 2009. 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. Aquaculture 291, 3 (2009), 161 -- 167.Google ScholarCross Ref
- Geoffrey French, Mark Fisher, Michal Mackiewicz, and Coby Needle. 2015. Convolutional Neural Networks for Counting Fish in Fisheries Surveillance Video.Google Scholar
- Joyee Ghosh, Yingbo Li, Robin Mitra, et al. 2018. On the use of Cauchy prior distributions for Bayesian logistic regression. Bayesian Analysis 13, 2 (2018), 359--383.Google ScholarCross Ref
- Kaiming He et al. 2016. Identity mappings in deep residual networks. In ECCV '16.Google Scholar
- S.J. Helland, B. Grisdale-Helland, and S. Nerland. 1996. A simple method for the measurement of daily feed intake of groups of fish in tanks". Aquaculture 139, 1 (1996), 157 -- 163.Google ScholarCross Ref
- Andrew G. Howard et al. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).Google Scholar
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML '15.Google ScholarDigital Library
- J.A. Lines, R.D. Tillett, L.G. Ross, D. Chan, S. Hockaday, and N.J.B. McFarlane. 2001. An automatic image-based system for estimating the mass of free-swimming fish. Computers and Electronics in Agriculture 31, 2 (2001), 151 -- 168.Google ScholarCross Ref
- Md. Moniruzzaman, Syed Mohammed Shamsul Islam, Mohammed Bennamoun, and Paul Lavery. 2017. Deep Learning on Underwater Marine Object Detection: A Survey. In Advanced Concepts for Intelligent Vision Systems". Springer International Publishing, Cham, 150--160.Google Scholar
- Mehdi Saberioon, Asa Gholizadeh, Petr Cisar, Aliaksandr Pautsina, and Jan Urban. 2017. Application of Machine Vision Systems in Aquaculture with Emphasis on Fish: State-of-the-Art and Key Issues. Aquaculture 9 (12 2017), 369âĂŞ387.Google Scholar
- Ahmad Salman, Shoaib Siddiqui, Faisal Shafait, Ajmal Mian, Mark Shortis, Khawar Khurshid, Adrian Ulges, and Ulrich Schwanecke. 2019. Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning system. ICES Journal of Marine Science (02 2019).Google Scholar
- M. Sung, S. Yu, and Y. Girdhar. 2017. Vision based real-time fish detection using convolutional neural network. In OCEANS 2017 - Aberdeen. 1--6.Google Scholar
- Pablo SÃąnchez, Pedro Pablo Ambrosio, and Rosa Flos. 2010. Stocking density and sex influence individual growth of Senegalese sole (Solea senegalensis). Aquaculture 300, 1 (2010), 93 -- 101.Google ScholarCross Ref
- Pablo SÃąnchez, Pedro Pablo Ambrosio, and Rosa Flos. 2013. Stocking density affects Senegalese sole (Solea senegalensis, Kaup) growth independently of size dispersion, evaluated using an individual photo-identification technique. Aquaculture Research 44, 2 (2013), 231--241.Google ScholarCross Ref
- Torisawa, Shinsuke, Kadota, Minoru, Komeyama, Kazuyoshi, Suzuki, Katsuya, and Takagi, Tsutomu. 2011. A digital stereo-video camera system for three-dimensional monitoring of free-swimming Pacific bluefin tuna, Thunnus orientalis, cultured in a net cage. Aquat. Living Resour. 24, 2 (2011), 107--112.Google ScholarCross Ref
- Yi Wang, Xin Tao, Xiaoyong Shen, and Jiaya Jia. 2019. Wide-Context Semantic Image Extrapolation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1399--1408.Google ScholarCross Ref
- Kresimir Williams, Nathan Lauffenburger, Meng-Che Chuang, Jenq-Neng Hwang, and Rick Towler. 2016. Automated measurements of fish within a trawl using stereo images from a Camera-Trawl device (CamTrawl). Methods in Oceanography 17 (2016), 138 -- 152. Special section on Novel instrumentation in Oceanography: a dedication to Rob Pinkel.Google ScholarCross Ref
- Bing Xu, Naiyan Wang, Tianqi Chen, and Mu Li. 2015. Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015).Google Scholar
- Boaz Zion. 2012. The use of computer vision technologies in aquaculture âĂŞ A review. Computers and Electronics in Agriculture 88 (2012), 125 -- 132.Google ScholarDigital Library
Index Terms
- Low-cost automatic fish measuring estimation
Recommendations
A unified approach to coding and interpreting face images
ICCV '95: Proceedings of the Fifth International Conference on Computer VisionFace images are difficult to interpret because they are highly variable. Sources of variability include individual appearance, 3D pose, facial expression and lighting. We describe a compact parametrised model of facial appearance which takes into ...
Facial Expression Recognition in the Encrypted Domain Based on Local Fisher Discriminant Analysis
Facial expression recognition forms a critical capability desired by human-interacting systems that aim to be responsive to variations in the human's emotional state. Recent trends toward cloud computing and outsourcing has led to the requirement for ...
Facial expression recognition using a dynamic model and motion energy
ICCV '95: Proceedings of the Fifth International Conference on Computer VisionPrevious efforts at facial expression recognition have been based on the Facial Action Coding System (FACS), a representation developed in order to allow human psychologists to code expression from static facial "mugshots." We develop new more accurate ...
Comments