# AnimalAI: An Open-Source Web Platform for Automated Animal Activity Index Calculation Using Interactive Deep Learning Segmentation

## TL;DR

A new web tool uses deep learning to track animal movement in videos, making it easier and more accurate for researchers to assess animal activity and behavior.

## Contribution

The novel contribution is an open-source web platform that uses interactive deep learning segmentation to automatically calculate animal activity indices with high accuracy.

## Key findings

- The platform achieved a 100% success rate in tracking broiler chickens across seven weeks with high precision and recall.
- Tracking 40-80% of birds in different weeks was sufficient to represent group activity accurately.
- The system outperforms traditional methods by focusing only on animals and ignoring background interference.

## Abstract

Understanding how animals move is important for ensuring their health and well-being. However, traditional methods used to measure animal activity are often inaccurate, difficult to use, and not accessible to those without technical skills. In this study, we developed a free, easy-to-use online tool that allows researchers to measure animal activity using video footage. Users can simply upload a video and click on the animals they want to track. Then the system automatically follows the animals and calculates how active they are. This tool was tested on broiler chickens and showed very accurate results, even when the animals were at different ages or in varied lighting conditions. Unlike older methods, this tool focuses only on the animals and ignores interference in the background, such as moving people or equipment, which improves accuracy. It also works without requiring any programming knowledge or complicated setup. By making movement tracking more accurate and accessible, this tool can help researchers, farmers, and animal care professionals monitor animals more effectively and make better decisions to support automatic animal behavior analytics.

Monitoring the activity index of animals is crucial for assessing their welfare and behavior patterns. However, traditional methods for calculating the activity index, such as pixel intensity differencing of entire frames, are found to suffer from significant interference and noise, leading to inaccurate results. These classical approaches also do not support group or individual tracking in a user-friendly way, and no open-access platform exists for non-technical researchers. This study introduces an open-source web-based platform that allows researchers to calculate the activity index from top-view videos by selecting individual or group animals. It integrates Segment Anything Model2 (SAM2), a promptable deep learning segmentation model, to track animals without additional training or annotation. The platform accurately tracked Cobb 500 male broilers from weeks 1 to 7 with a 100% success rate, IoU of 92.21% ± 0.012, precision of 93.87% ± 0.019, recall of 98.15% ± 0.011, and F1 score of 95.94% ± 0.006, based on 1157 chickens. Statistical analysis showed that tracking 80% of birds in week 1, 60% in week 4, and 40% in week 7 was sufficient (r ≥ 0.90; p ≤ 0.048) to represent the group activity in respective ages. This platform offers a practical, accessible solution for activity tracking, supporting animal behavior analytics with minimal effort.