20, July 2025

AI-Based Fish Fingerling Counting System Using Online Repositories and a Regional Dataset: A Real-Time Monitoring Approach for Aquaculture in Madhya Pradesh

VOLUME-11; ISSUE-7; JULY-2025

Author(s): 1.Rahul Kumar Majhi 2. Navita Shrivastava

Authors Affiliations:

  1. Ph.D Scholar, Computer Science Department ,APS University, Rewa, India
  2. Professor, Computer Science Department, APS University , Rewa, India

DOIs:10.2015/IJIRMF/202507019     |     Paper ID: IJIRMF202507019


Abstract
Keywords
Cite this Article/Paper as
References

Abstract:    This research focuses on the creation and utilization of a dataset tailored for the quantification of fish fingerlings in the Madhya Pradesh region, leveraging artificial intelligence (AI) techniques. The dataset encompasses images captured from various water bodies, fish farms, and hatcheries across the region, representing diverse environmental conditions and fish species. Using this dataset, we developed and evaluated an AI-based computational framework employing object detection models such as YOLOv51 and Faster R-CNN2. The study provides valuable insights into the challenges of fingerling quantification, including occlusion and environmental variability, and highlights the potential of AI in supporting sustainable aquaculture in Madhya Pradesh.

Key Words: Fish Fingerlings, CNN, YOLOv5, Aquaculture, R-CNN, Computational Framework.

1.Rahul Kumar Majhi, 2. Navita Shrivastava (2025); AI-Based Fish Fingerling Counting System Using Online Repositories and a Regional Dataset: A Real-Time Monitoring Approach for Aquaculture in Madhya Pradesh, International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-11, Issue-7, Pp. 121-129.         Available on –   https://www.ijirmf.com/

REFERENCES:

  1. Horvat, M., Jelečević, L., & Gledec, G. (2022). A comparative study of YOLOv5 models performance for image localization and classification. In Central European Conference on Information and Intelligent Systems (pp. 349-356). Faculty of Organization and Informatics Varazdin.
  2. Liu, B., Zhao, W., & Sun, Q. (2017, October). Study of object detection based on Faster R-CNN. In 2017 Chinese automation congress (CAC) (pp. 6233-6236). IEEE.
  3. Gladju, J., Kamalam, B. S., & Kanagaraj, A. (2022). Applications of data mining and machine learning framework in aquaculture and fisheries: A review. Smart Agricultural Technology, 2, 100061.
  4. Zhao, S., Zhang, S., Liu, J., Wang, H., Zhu, J., Li, D., & Zhao, R. (2021). Application of machine learning in intelligent fish aquaculture: A review. Aquaculture, 540, 736724.
  5. Rathi, D., Awasthi, P. K., & Gupta, J. K. (2004). Profitable pisciculture production through resource management in central region of Madhya Pradesh. Indian Journal of Agricultural Economics, 59(3), 482.
  6. Flaherty, M. (2009). Coastal aquaculture in India: Poverty, environment and rural livelihood. Concept Publishing Company.
  7. Katre, N., Sharma, A., & Yadav, V. K. (2024). Augmentation of fish production from Gangulpara reservoir of Madhya Pradesh: A success story.
  8. Gulati, A., Rajkhowa, P., Roy, R., & Sharma, P. (2021). Performance of agriculture in Madhya Pradesh. Revitalizing Indian agriculture and boosting farmer incomes, 145-174.
  9. Sarma, K., Mohanty, S., Dey, A., Barari, S. K., & Bhatt, B. P. (2015). Prospects, status and challenges of aquaculture in the eastern region of India. Fishing Chimes, 35(7), 24-33.
  10. Garcia, V., Sant’Ana, D. A., Zanoni, V. A. G., Pache, M. C. B., Naka, M. H., Albuquerque, P. L. F., … & Pistori, H. (2020). A new image dataset for the evaluation of automatic fingerlings counting. Aquacultural Engineering, 89, 102064.
  11. Albuquerque, P. L. F., Garcia, V., Junior, A. D. S. O., Lewandowski, T., Detweiler, C., Gonçalves, A. B., … & Pistori, H. (2019). Automatic live fingerlings counting using computer vision. Computers and Electronics in Agriculture, 167, 105015.
  12. Zhou, J., Ye, Z., Zhao, J., Ji, D., Peng, Z., Lu, G., … & Zhu, S. (2024). Multi-detector and motion prediction-based high-speed non-intrusive fingerling counting method. Biosystems Engineering, 245, 12-23.
  13. Fernandes, M. P., Costa, A. C., França, H. F. D. C., Souza, A. S., Viadanna, P. H. D. O., Lima, L. D. C., … & Oliveira, R. F. D. (2024). Convolutional Neural Networks in the Inspection of Serrasalmids (Characiformes) Fingerlings. Animals, 14(4), 606.
  14. Cui, M., Liu, X., Liu, H., Zhao, J., Li, D., & Wang, W. (2024). Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Review. arXiv preprint arXiv:2406.17800.
  15. Tray, E., Leadbetter, A., Meaney, W., Conway, A., Kelly, C., MaoilĂ©idigh, N. Ă“., … & Brophy, D. (2020). An open-source database model and collections management system for fish scale and otolith archives. Ecological Informatics, 59, 101115.
  16. Rikhari, Y. C., Singh, A. K., Kumar, P., & Chauhan, R. S. (2020). Assessment of integrated fish farming at farmers’ fields in Bundelkhand region of Madhya Pradesh. Journal of Krishi Vigyan, 9(si), 11-14.
  17. Rikhari, Y. C., Tomar, R. K. S., Kasana, B. S., & Singh, A. K. (2014). Integration of fish culture in harvested rainwater for livlihood security in Bundelkhand region of Madhya Pradesh. Bhartiya Krishi Anusandhan Patrika, 29(1), 43-46.
  18. Gupta, P. K., Singh, S. R. K., Mishra, R. K., & Tomar, A. K. (2018). Integrated farming system for the Kymore Plateau and Satpura Hills Region of Madhya Pradesh. Journal of Community Mobilization and Sustainable Development, 13(3), 493-499.
  19. CMFRI, K. (2020). State Specific Strategies for Doubling Farmers Income-2022.
Post Views: 54

Download Full Paper

Download PDF No. of Downloads:19 | No. of Views: 58