Automatic Horse Blink Detection Using Computer Vision and Deep Nets

Dimitrova, S, Orchard, W, Paudel, B, McBride, Sebastian, Hemmings, Andrew and Akanyeti, O (2024) Automatic Horse Blink Detection Using Computer Vision and Deep Nets. In: Advances in Computational Intelligence Systems: Contributions Presented at the 21st UK Workshop on Computational Intelligence, September 7-9, 2022, Sheffield, UK. Advances in Computational Intelligence Systems (1454). Springer Nature, pp. 436-447.

Text Dimitrovova Automatic horse blink detection using computer vision and deep nets.docx - Accepted Version Restricted to Repository staff only until 19 May 2025. Download (112kB) | Request a copy

Abstract

Measurements of dopaminergic activity in the central nervous system provide valuable information about animal health and welfare. In horses, it has been shown that blink rate is correlated to dopaminergic activity and can be used as a non-invasive biomarker. In this paper, we propose two new algorithms for video-based automatic blink detection in horses. The first algorithm employs an OpenCV object tracker to localize the eye and detects blinks from local color changes over successive frames. The second algorithm is based on a neural net classifier which categories each video frame into either “eye is open” or “eye is closed” categories. It then clusters “eye is closed” frames into distinct blink events. Both algorithms also run a post-processing method to improve prediction accuracy by removing outliers and merging neighboring clusters that belong to the same blink event. The test data set consisted of eight RGB video recordings from three healthy horses moving freely in outdoor environments. Our results show that the first algorithm had better accuracy (81% > 31%, p<0.01) and lower error rate (27% < 69%, p<0.01) than the second algorithm. This study is part of an ongoing work to develop an cheap, non-invasive and automated health monitoring system for horses and other bovine animals. Keywords: object tracking, automatic blink detection, eye-tracking, machine learning, image processing, deep learning

Item Type:	Book Section
Keywords:	object tracking, automatic blink detection, eye-tracking, machine learning, image processing, deep learning
Divisions:	Agriculture, Science and Practice
Depositing User:	Doctor Andrew Hemmings
Date Deposited:	02 Dec 2024 10:37
Last Modified:	02 Dec 2024 10:37
URI:	https://rau.repository.guildhe.ac.uk/id/eprint/16864

Actions (login required)

Edit Item