English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Monitoring cow body weight is crucial to support farm management decisionsdue to its direct relationship with the growth, nutritional status, and healthof dairy cows. Cow body weight is a repeated trait, however, the majority ofprevious body weight prediction research only used data collected at a singlepoint in time. Furthermore, the utility of deep learning-based segmentation forbody weight prediction using videos remains unanswered. Therefore, theobjectives of this study were to predict cow body weight from repeatedlymeasured video data, to compare the performance of the thresholding and MaskR-CNN deep learning approaches, to evaluate the predictive ability of bodyweight regression models, and to promote open science in the animal sciencecommunity 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 10lactating Holstein cows and 2 non-lactating Jersey cows. Three approaches wereinvestigated to segment the cow's body from the background, including singlethresholding, adaptive thresholding, and Mask R-CNN. Four image-derivedbiometric features, such as dorsal length, abdominal width, height, and volume,were estimated from the segmented images. On average, the Mask-RCNN approachcombined with a linear mixed model resulted in the best prediction coefficientof determination and mean absolute percentage error of 0.98 and 2.03%,respectively, in the forecasting cross-validation. The Mask-RCNN approach wasalso the best in the leave-three-cows-out cross-validation. The predictioncoefficients of determination and mean absolute percentage error of theMask-RCNN coupled with the linear mixed model were 0.90 and 4.70%,respectively. Our results suggest that deep learning-based segmentationimproves the prediction performance of cow body weight from longitudinal depthvideo data.

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