Skip to Main content Skip to Navigation
Master Thesis

Utilisation de l'imagerie 3D pour estimer la note d'état corporel des vaches laitières

Abstract : Body condition is known to affect reproduction and health in dairy cows. On-farm it is usually measured with the body condition score (BCS) which is not expensive but remains subjective and not very sensitive. The aim of the current work was to develop and to validate a method, nec3D, working on estimating BCS with 3D pictures of dairy cattle's back, from the pins to the hooks. A 57 3D-shapes dataset, transformed with a principal component analysis, was built for calibration. The principal components were performed on BCS with multiple linear regressions. Four anatomical points had to be identified manually to normalise the pictures. Influence of two different ways of points' identification and of the picture's resolution on methods quality was analysed. Moreover, external validation was evaluated on two additional datasets: one with cows used for calibration, but with different stages in milking (valididem) and one with cows not used for calibration (validdiff). Both ways of points' identification had quite good results in terms of calibration (R² = 1) and differed slightly on validation quality (RMSE= 0.34 vs. 0.32). Nec3d was 2.8 times more reproducible than BCS (σ = 0.1 vs. 0.28). The lowest resolution implied a loss of reproducibility but did not increase the error of prediction. A simplified acquisition system, implying low resolution, could therefore be developed. As error of reproducibility incorporates error due to the manual point's identification, automation of points' identification would improve repeatability and consequently reproducibility. Assessing body condition thanks to 3D pictures appears as a promising tool which can improve phenotyping of this trait.
Document type :
Master Thesis
Complete list of metadata

Cited literature [5 references]  Display  Hide  Download
Contributor : Agrocampus Ouest <>
Submitted on : Wednesday, February 5, 2014 - 11:37:00 AM
Last modification on : Monday, July 6, 2020 - 3:38:21 PM
Long-term archiving on: : Sunday, April 9, 2017 - 5:54:14 AM


  • HAL Id : dumas-00940939, version 1



Amélie Fischer. Utilisation de l'imagerie 3D pour estimer la note d'état corporel des vaches laitières. Sciences agricoles. 2013. ⟨dumas-00940939⟩



Record views


Files downloads