The integration of cameras and data science has great potential to revolutionize livestock production systems, making them more efficient and sustainable by replacing human-based management with real-time individualized animal care. However, applying these digital tools to animal data presents challenges that require computer programming and data analysis skills, as well as access to computing resources. Additionally, there is a growing need to train animal science students to analyze image or video data using data science algorithms. However, teaching computer programming to all types of students from the ground up can prove complicated and challenging. Therefore, the objective of this study was to develop ShinyAnimalCV, a user-friendly online web application that supports users to learn the application of data science to analyze animal digital video data, without the need for complex coding. The application includes nine pre-trained models for detecting and segmenting animals in image data and can be easily accessed through a web browser. We have also made the source code and detailed documentation available online for advanced users who wish to use the application locally. This software tool facilitates the teaching of digital animal data analysis in the animal science community, with potential benefits to livestock production systems.

Read the full article in the Journal of Animal Science.