Development of an AI-Based Animal Intrusion Detection System for Agricultural Lands Using ESP32-CAM and TinyML

B. A. Anand *

Department of FMPE, COAE, UAS, Bangalore, India.

R. Manoj

COAE, UAS, Bangalore, India.

V. S. Mokshitha

COAE, UAS, Bangalore, India.

Monika. M. Chowhan

COAE, UAS, Bangalore, India.

K. J. Moulya

COAE, UAS, Bangalore, India.

Nanda Gopal Achyutha

COAE, UAS, Bangalore, India.

*Author to whom correspondence should be addressed.


Abstract

Animal invasion is one of the major threats observed recent times in the agricultural lands. This is due to the extension of farm lands to feed the increasing population. There is a need to control this animal invasion without harming the living animals. Hence, the study was undertaken to develop an Artificial Intelligence based image detection using ESP32-CAM and Neural Network for protection of agricultural land by invasion of wild animals, resulting in crop damage and financial losses. The goal of the study is to develop a simple yet effective system for detecting wild animals. The model, FOMO (Faster Objects, More Objects) MobileNetV2 0.35, has been trained to detect cows, elephants, and deers to safeguard farmlands effectively. The deployment involves object detection capabilities, on-device optimization, and real-time performance for practical implementation.

Keywords: Animal invasion, agricultural lands, Artificial intelligence, object detection, neural network


How to Cite

Anand, B. A., R. Manoj, V. S. Mokshitha, Monika. M. Chowhan, K. J. Moulya, and Nanda Gopal Achyutha. 2026. “Development of an AI-Based Animal Intrusion Detection System for Agricultural Lands Using ESP32-CAM and TinyML”. Journal of Scientific Research and Reports 32 (6):145-53. https://doi.org/10.9734/jsrr/2026/v32i64235.

Downloads

Download data is not yet available.