Animal Detection in Farms Using Opencv

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 13 | 02 | Page :
    By

    Shivay Vimal,

  • Anshul Yadav,

  • Romil Patel,

  • Manoj Kumar Dixit,

  1. Students, Dept. of Computer Science and Engineering, Galgotias College of Engineering & Technology Greater Noida – 201306, Uttar Pradesh, India
  2. Students, Dept. of Computer Science and Engineering, Galgotias College of Engineering & Technology Greater Noida – 201306, Uttar Pradesh, India
  3. Students, Dept. of Computer Science and Engineering, Galgotias College of Engineering & Technology Greater Noida – 201306, Uttar Pradesh, India
  4. Professor, Dept. of Computer Science and Engineering, Galgotias College of Engineering & Technology Greater Noida – 201306, Uttar Pradesh, India

Abstract

Agriculture plays a fundamental role in sustaining the Indian economy, providing employment and livelihood to a large portion of the population. Despite advancements in farming techniques, one of the persistent challenges faced by farmers is the intrusion of wild animals into agricultural fields. Such intrusions often lead to large-scale crop damage, financial loss, and emotional distress for farmers. Traditional animal deterrent methods, such as manual patrolling, fences, or scarecrows, have shown limited effectiveness and are not scalable for large areas. These techniques either require continuous human intervention or fail to adapt to the changing behavior of animals over time. To address this issue, this paper proposes an intelligent and automated solution using computer vision and OpenCV for real-time animal detection in farmlands. The system leverages a pre-trained deep learning model—MobileNet SSD (Single Shot Detector)— for identifying and classifying animals captured through surveillance cameras installed in the field. Once an animal is detected, the system activates an alert mechanism such as a loud siren or flashing light to scare away the intruder and notify the farmer instantly, either through a local alarm or via a remote communication system. This approach not only reduces the dependency on manual supervision but also offers a scalable, cost-effective, and energy-efficient solution for small and large farms alike. The use of MobileNet SSD ensures that the model runs efficiently on edge devices like Raspberry Pi or low-cost processors, making it accessible to farmers in rural areas without the need for expensive hardware. The system can be further enhanced by integrating night vision cameras, thermal sensors, or connecting with IoT devices for better monitoring and data logging. Through this study, we aim to demonstrate that a well-structured computer vision system can help mitigate crop losses caused by animal intrusion, enhance farm productivity, and empower farmers with modern technological tools.

Keywords: Computer vision, OpenCV, MobileNet SSD, animal intrusion, smart farming, agriculture monitoring, deep learning.

How to cite this article:
Shivay Vimal, Anshul Yadav, Romil Patel, Manoj Kumar Dixit. Animal Detection in Farms Using Opencv. Research & Reviews: A Journal of Embedded System & Applications. 2025; 13(02):-.
How to cite this URL:
Shivay Vimal, Anshul Yadav, Romil Patel, Manoj Kumar Dixit. Animal Detection in Farms Using Opencv. Research & Reviews: A Journal of Embedded System & Applications. 2025; 13(02):-. Available from: https://journals.stmjournals.com/rrjoesa/article=2025/view=211559


References

  1. Andavarapu N, Vatsavayi VK. Wild-animal recognition in agriculture farms using W-COHOG for agrosecurity. Int. J. Computational Intelligence Research. 2017 Nov 9;13(9):2247-57.
  2. Yadahalli S, Parmar A, Deshpande A. Smart intrusion detection system for crop protection by using Arduino. In2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA) 2020 Jul 15 (pp. 405-408). IEEE.
  3. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861. 2017 Apr 17.
  4. Deshpande AV. Design and implementation of an intelligent security system for farm protection from wild animals. International journal of science and research. 2016 Feb:2319-7064.
  5. Gogoi M. Protection of crops from animals using intelligent surveillance system. Journal of Applied and Fundamental Sciences. 2015 Nov 22;1(2):200.
  6. Pandey S, Bajracharya SB. Crop protection and its effectiveness against wildlife: A case study of two villages of Shivapuri National Park, Nepal. Nepal Journal of Science and Technology. 2015;16(1):1-0.
  7. Bavane V, Raut A, Sonune S, Bawane AP, Jawandhiya PM. Protection of crops from wild animals using Intelligent Surveillance System. International Journal of Research in Advent Technology (IJRAT). 2018 Apr:2321-9637.
  8. Rodelas NC, Ballera MA. Intruder detection and recognition using different image processing techniques for a proactive surveillance. Indonesian Journal of Electrical Engineering and Computer Science. 2021 Nov;24(2):843-52.
  9. Antunes RM, Grilo FL. Intruder alarm systems-the road ahead. InAdvanced Technologies 2009 Oct 1. IntechOpen.
  10. Rathor S, Kumari S, Singh R, Gupta P. Two layers machine learning architecture for animal classification using hog and lbp. InProceedings of International Conference on Communication and Artificial Intelligence: ICCAI 2020 2021 (pp. 445-453). Springer Singapore.
Ahead of Print Subscription Original Research
Volume 13
02
Received 14/04/2025
Accepted 28/04/2025
Published 27/05/2025
Publication Time 43 Days
471

Login


My IP

PlumX Metrics