AnimalAI: An Open-Source Web Platform for Automated Animal Activity Index Calculation Using Interactive Deep Learning Segmentation
AnimalAI: An Open-Source Web Platform for Automated Animal Activity Index Calculation Using Interactive Deep Learning Segmentation
Mahtab Saeidifar,Guoming Li,2 Authors,Ehsan Asali
TLDR
A free, easy-to-use online tool that allows researchers to measure animal activity using video footage and focuses only on the animals and ignores interference in the background, such as moving people or equipment, which improves accuracy.
Abstract
Simple Summary 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.
