Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Lightweight Fish Classification Model for Sustainable Marine Management: Indonesian Case (2401.02278v1)

Published 4 Jan 2024 in cs.CV and cs.LG

Abstract: The enormous demand for seafood products has led to exploitation of marine resources and near-extinction of some species. In particular, overfishing is one the main issues in sustainable marine development. In alignment with the protection of marine resources and sustainable fishing, this study proposes to advance fish classification techniques that support identifying protected fish species using state-of-the-art machine learning. We use a custom modification of the MobileNet model to design a lightweight classifier called M-MobileNet that is capable of running on limited hardware. As part of the study, we compiled a labeled dataset of 37,462 images of fish found in the waters of the Indonesian archipelago. The proposed model is trained on the dataset to classify images of the captured fish into their species and give recommendations on whether they are consumable or not. Our modified MobileNet model uses only 50\% of the top layer parameters with about 42% GTX 860M utility and achieves up to 97% accuracy in fish classification and determining its consumability. Given the limited computing capacity available on many fishing vessels, the proposed model provides a practical solution to on-site fish classification. In addition, synchronized implementation of the proposed model on multiple vessels can supply valuable information about the movement and location of different species of fish.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. A survey on fish classification techniques. Journal of King Saud University - Computer and Information Sciences, 2020.
  2. Image-based, unsupervised estimation of fish size from commercial landings using deep learning. ICES Journal of Marine Science, 77(4):1330–1339, 2020.
  3. Vision applications in the fishing and fish product industries. International Journal of Pattern Recognition and Artificial Intelligence, 2(04):657–671, 1988.
  4. Internet of ships: A survey on architectures, emerging applications, and challenges. IEEE Internet of Things Journal, 7(10):9714–9727, 2020.
  5. M. Ayi and M. El-Sharkawy. Rmnv2: Reduced mobilenet v2 for cifar10. In 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), pages 0287–0292, 2020.
  6. Mini-grid power system optimization design and economic analysis of solar powered sea water desalination plant for rural communities and emergency relief conditions. In 2012 IEEE International Power Engineering and Optimization Conference Melaka, Malaysia, pages 465–469, 2012.
  7. Faster r-cnn implementation method for multi-fruit detection using tensorflow platform. In 2018 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), pages 337–340, 2018.
  8. An automatic traffic density estimation using single shot detection (ssd) and mobilenet-ssd. Physics and Chemistry of the Earth, Parts A/B/C, 110:176–184, 2019.
  9. Intelligent system for automated fish sorting and counting. In Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113), volume 2, pages 1279–1284. IEEE, 2000.
  10. Automatic fish classification system using deep learning. In 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI), pages 24–29. IEEE, 2017.
  11. François Chollet. Xception: Deep learning with depthwise separable convolutions. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1800–1807. IEEE, 2017.
  12. Global adoption of novel aquaculture feeds could substantially reduce forage fish demand by 2030. Nature Food, 1(5):301–308, 2020.
  13. Fish detection using deep learning. Applied Computational Intelligence and Soft Computing, 2020, 2020.
  14. Autonomous systems in remote areas of the ocean using bluecom+ communication network. In OCEANS 2017 - Anchorage, pages 1–6, 2017.
  15. Effnet: An efficient structure for convolutional neural networks. In 2018 25th IEEE International Conference on Image Processing (ICIP), pages 6–10. IEEE, 2018.
  16. R. Froese and D. Pauly. Editors. 2020.FishBase. Fishbase, December 2020.
  17. Automatic segmentation of fish using deep learning with application to fish size measurement. ICES Journal of Marine Science, 77(4):1354–1366, 10 2019.
  18. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778. IEEE, 2016.
  19. A. Heredia and G. Barros-Gavilanes. Video processing inside embedded devices using ssd-mobilenet to count mobility actors. In 2019 IEEE Colombian Conference on Applications in Computational Intelligence (ColCACI), pages 1–6, 2019.
  20. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
  21. Distributed resource allocation for general energy efficiency maximization in offshore maritime device-to-device communication. IEEE Wireless Communications Letters, pages 1–1, 2021.
  22. Gpu-accelerated compression and visualization of large-scale vessel trajectories in maritime iot industries. IEEE Internet of Things Journal, 7(11):10794–10812, 2020.
  23. Ssd-mobilenet implementation for classifying fish species. In Pandian Vasant, Ivan Zelinka, and Gerhard-Wilhelm Weber, editors, Intelligent Computing and Optimization, pages 399–408, Cham, 2020. Springer International Publishing.
  24. Automatic fish species classification using deep convolutional neural networks. Wireless Personal Communications, pages 1–11, 2019.
  25. Fish detection and species classification in underwater environments using deep learning with temporal information. Ecological Informatics, 57:101088, 2020.
  26. Shipping 4.0: Security requirements for the cyber-enabled ship. IEEE Transactions on Industrial Informatics, 16(10):6617–6625, 2020.
  27. Hidden harvest: The global contribution of capture fisheries. Worldbank; WorldFish, 2012.
  28. Oceana. Ocean fishes, Agustus 2020.
  29. High Level Panel of Experts on Food Security and Nutrition. Sustainable fisheries and aquaculture for food security and nutrition. A report by the High Level Panel of Experts on Food Security and Nutrition, 2014.
  30. A lorawan network infrastructure for the remote monitoring of offshore sea farms. In 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), pages 1–6, 2020.
  31. The effectiveness of data augmentation in image classification using deep learning. arXiv preprint arXiv:1712.04621, 2017.
  32. David MW Powers. Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061, 2020.
  33. Underwater fish species classification using convolutional neural network and deep learning. In 2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR), pages 1–6. IEEE, 2017.
  34. Visual features based automated identification of fish species using deep convolutional neural networks. Computers and Electronics in Agriculture, 167:105075, 2019.
  35. Life cycle assessment of fish and seafood processed products–a review of methodologies and new challenges. Science of the Total Environment, page 144094, 2020.
  36. Dynamic routing between capsules. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30, pages 3856–3866. Curran Associates, Inc., 2017.
  37. Convolutional neural networks using mobilenet for skin lesion classification. In 2019 16th International Joint Conference on Computer Science and Software Engineering (JCSSE), pages 242–247, 2019.
  38. Fish species classification in unconstrained underwater environments based on deep learning. Limnology and Oceanography: Methods, 14(9):570–585, 2016.
  39. Mobilenetv2: Inverted residuals and linear bottlenecks. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4510–4520. IEEE, 2018.
  40. N. S. Sanjay and A. Ahmadinia. Mobilenet-tiny: A deep neural network-based real-time object detection for rasberry pi. In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), pages 647–652, 2019.
  41. Optimizing video sampling for juvenile fish surveys: Using deep learning and evaluation of assumptions to produce critical fisheries parameters. Fish and Fisheries, 21(6):1259–1276, 2020.
  42. Yulan Shen. Accelerating cnn on fpga : An implementation of mobilenet on fpga. Master’s thesis, KTH, School of Electrical Engineering and Computer Science (EECS), 2019.
  43. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  44. NJC Strachan. Length measurement of fish by computer vision. Computers and electronics in agriculture, 8(2):93–104, 1993.
  45. NJC Strachan. Sea trials of a computer vision based fish species sorting and size grading machine. Mechatronics, 4(8):773–783, 1994.
  46. Redundancy-reduced mobilenet acceleration on reconfigurable logic for imagenet classification. In International Symposium on Applied Reconfigurable Computing, pages 16–28. Springer, 2018.
  47. Smart deep learning-based approach for non-destructive freshness diagnosis of common carp fish. Journal of Food Engineering, 278:109930, 2020.
  48. Mnasnet: Platform-aware neural architecture search for mobile. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2815–2823, Los Alamitos, CA, USA, jun 2019. IEEE Computer Society.
  49. Hyperspectral anomaly detection by fractional fourier entropy. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(12):4920–4929, 2019.
  50. Fish species sensitivity classification for environmental impact assessment, conservation and restoration planning. Science of The Total Environment, 708:135173, 2020.
  51. Consumable fish classification using k-nearest neighbor. In IOP Conference Series: Materials Science and Engineering, volume 821, page 012039. IOP Publishing, 2020.
  52. WWF. Why is sustainable seafood good for developing contries?, December 2020.
  53. Underwater fish detection using deep learning for water power applications. In 2018 International Conference on Computational Science and Computational Intelligence (CSCI), pages 313–318. IEEE, 2018.
  54. Ai-empowered maritime internet of things: A parallel-network-driven approach. IEEE Network, 34(5):54–59, 2020.
  55. Task allocation with unmanned surface vehicles in smart ocean iot. IEEE Internet of Things Journal, 7(10):9702–9713, 2020.
  56. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6848–6856. IEEE, 2018.
  57. Joint classification of hyperspectral and lidar data using hierarchical random walk and deep cnn architecture. IEEE Transactions on Geoscience and Remote Sensing, 58(10):7355–7370, 2020.
  58. Evaluation of fish feeding intensity in aquaculture using a convolutional neural network and machine vision. Aquaculture, 507:457 – 465, 2019.
  59. Image-based, unsupervised estimation of fish size from commercial landings using deep learning. ICES Journal of Marine Science, 77(4):1330–1339, 11 2019.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets