Body condition estimation on cows from depth images using Convolutional Neural Networks

J. RODRIGUEZ ALVAREZ; M. ARROQUI; P. MANGUDO; J TOLOZA; D. JATIP; J. M. RODRIGUEZ; ALFREDO TEYSEYRE; CARLOS SANZ; A. ZUNINO; C. MACHADO; C. MATEOS

COMPUTERS AND ELETRONICS IN AGRICULTURE

ELSEVIER SCI LTD

Lugar: Amsterdam; Año: 2018

0168-1699

BCS (?Body Condition Score?) is a method used to estimate body fat reserves and accumulated energy balance of cows. BCSheavily influences milk production, reproduction, and health of cows. Therefore, it is important to monitor BCS to achieve betteranimal response, but this is a time-consuming and subjective task performed visually by expert scorers. Several studies have triedto automate BCS of dairy cows by applying image analysis and machine learning techniques. This work analyzes these studiesand proposes a system based on Convolutional Neural Networks (CNNs) to improve overall automatic BCS estimation, whose usemight be extended beyond dairy production.The developed system has achieved good estimation results in comparison with other systems in the area. Overall accuracyof BCS estimations within 0.25 units of difference from true values was 78%, while overall accuracy within 0.50 units was 94%.Similarly, weighted precision and recall, which took into account imbalance BCS distribution in the built dataset, show similarvalues considering those error ranges.