Supervised Learning Model for Key Frame Identification from Cow Teat Videos

TL;DR

This paper introduces a neural network-based method for identifying key frames in cow teat videos to enhance mastitis risk assessment accuracy, addressing environmental and positional challenges with a fusion distance and ensemble model.

Contribution

It presents a novel neural network approach combined with fusion distance and ensemble modeling for more accurate key frame detection in cow teat videos.

Findings

Improved F-score in key frame identification.

Fusion distance enhances model performance.

Ensemble model outperforms single models.

Abstract

This paper proposes a method for improving the accuracy of mastitis risk assessment in cows using neural networks and video analysis. Mastitis, an infection of the udder tissue, is a critical health problem for cows and can be detected by examining the cow's teat. Traditionally, veterinarians assess the health of a cow's teat during the milking process, but this process is limited in time and can weaken the accuracy of the assessment. In commercial farms, cows are recorded by cameras when they are milked in the milking parlor. This paper uses a neural network to identify key frames in the recorded video where the cow's udder appears intact. These key frames allow veterinarians to have more flexible time to perform health assessments on the teat, increasing their efficiency and accuracy. However, there are challenges in using cow teat video for mastitis risk assessment, such as complex environments, changing cow positions and postures, and difficulty in identifying the udder from the video. To address these challenges, a fusion distance and an ensemble model are proposed to improve the performance (F-score) of identifying key frames from cow teat videos. The results show that these two approaches improve performance compared to using a single distance measure or model.