Depth video data-enabled predictions of longitudinal dairy cow body weight using thresholding and Mask R-CNN algorithms

TL;DR

This study demonstrates that deep learning-based segmentation, especially Mask R-CNN, significantly improves the accuracy of predicting dairy cow body weight from longitudinal depth video data, outperforming traditional thresholding methods.

Contribution

The paper introduces a novel application of Mask R-CNN for segmenting cows in depth videos and predicting their body weight over time, providing a comparative analysis with thresholding methods.

Findings

Mask R-CNN with linear mixed models achieved R^2 of 0.98 and 2.03% error.

Deep learning segmentation outperformed traditional thresholding methods.

Open-source code for video-based cow weight prediction is provided.

Abstract

Monitoring cow body weight is crucial to support farm management decisions due to its direct relationship with the growth, nutritional status, and health of dairy cows. Cow body weight is a repeated trait, however, the majority of previous body weight prediction research only used data collected at a single point in time. Furthermore, the utility of deep learning-based segmentation for body weight prediction using videos remains unanswered. Therefore, the objectives of this study were to predict cow body weight from repeatedly measured video data, to compare the performance of the thresholding and Mask R-CNN deep learning approaches, to evaluate the predictive ability of body weight regression models, and to promote open science in the animal science community by releasing the source code for video-based body weight prediction. A total of 40,405 depth images and depth map files were obtained from 10 lactating Holstein cows and 2 non-lactating Jersey cows. Three approaches were investigated to segment the cow's body from the background, including single thresholding, adaptive thresholding, and Mask R-CNN. Four image-derived biometric features, such as dorsal length, abdominal width, height, and volume, were estimated from the segmented images. On average, the Mask-RCNN approach combined with a linear mixed model resulted in the best prediction coefficient of determination and mean absolute percentage error of 0.98 and 2.03%, respectively, in the forecasting cross-validation. The Mask-RCNN approach was also the best in the leave-three-cows-out cross-validation. The prediction coefficients of determination and mean absolute percentage error of the Mask-RCNN coupled with the linear mixed model were 0.90 and 4.70%, respectively. Our results suggest that deep learning-based segmentation improves the prediction performance of cow body weight from longitudinal depth video data.