AI tracks Mithun behaviour in real time at ICAR farm. (Morung File Photo)
Kohima, September 9 (MExN): Researchers at the ICAR-National Research Centre on Mithun (ICAR-NRC on Mithun), Nagaland, have developed an artificial intelligence-based system to detect and track Mithun behaviour in real time, potentially aiding animal health, welfare, breeding and reproductive management.
The study, published in Engineering Research Express, uses 12 high-definition CCTV cameras installed across two farm sheds to provide continuous day-and-night surveillance, including infrared coverage.
Researchers developed a dataset of 3,000 manually annotated images covering four behaviours -- feeding, standing, lying and mounting.
The system combines the YOLOv8n model for behaviour detection with DeepSORT technology to track individual animals and assign persistent identities.
The YOLOv8n model achieved 99.5 per cent mean average precision at mAP@0.5 and 99.6 per cent recall, while processing about 31 frames per second on an NVIDIA RTX 3060 GPU.
The system was tested under challenging conditions, including partial occlusion, background clutter, uneven and wet ground, shadows, motion blur and nighttime infrared footage.
In one instance, lying and feeding behaviours were detected and tracked with unique IDs at 96 per cent confidence, while mounting behaviour was detected through infrared night vision at 97 per cent confidence.
Researchers said changes in feeding, standing and lying patterns could provide insights into an animal's health, comfort, nutrition and physiological condition, while mounting behaviour could support reproductive and oestrus management.
However, the system has so far been evaluated at a single farm and requires further validation across farms, regions, seasons, stocking densities and camera arrangements. Severe occlusion can also affect detection and tracking performance.
The researchers plan to expand the system to detect behaviours such as aggression, grooming and disease-related inactivity. Future work may include temporal AI models, edge-device deployment and larger datasets covering different farms and seasons.
Mithun (Bos frontalis), popularly known as the "Cattle of the Hills", has significant social, cultural and economic importance for tribal communities across Northeast India and contributes to regional livelihoods and food security.
The study was conducted by researchers from ICAR-NRC on Mithun, Nagaland, in collaboration with NIT Nagaland, Nagaland University and CHRIST (Deemed to be University). It was published in Engineering Research Express, Volume 8 (2026), Article 175213.
