Automated computer vision system to predict body weight and average daily gain in beef cattle during growing and finishing phases

• Published in: Livestock science Vol. 232; p. 103904
• Main Authors: Cominotte, A., Fernandes, A.F.A., Dorea, J.R.R., Rosa, G.J.M., Ladeira, M.M., van Cleef, E.H.C.B., Pereira, G.L., Baldassini, W.A., Machado Neto, O.R.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.02.2020
• Subjects: Beef cattle; Computer vision; Image analysis; Kinect; Kinect; Beef cattle; Computer vision; Image analysis
• ISSN: 1871-1413; 1878-0490
• DOI: 10.1016/j.livsci.2019.103904

•Computer vision system can be used to predict body weight with good accuracy and precision in Nellore cattle.•The main difference in this study are the absence of manual feature extraction.•Artificial Neural Networks increase accuracy and precision of body weight prediction. Frequent measurements of body weight (BW) in livestock systems are very important because they allow assessing growth. However, real-time monitoring of animal growth through traditional weighing scales is stressful for animals, costly and labor-intensive. Thus, the objectives of this study were to: 1) assess the predictive quality of an automated computer vision system used to predict BW and average daily gain (ADG) in beef cattle; and 2) compare different predictive approaches, including Multiple Linear Regression (MLR), Least Absolute Shrinkage and Selection Operator (LASSO), Partial Least Squares (PLS), and Artificial Neutral Networks (ANN). A total of 234 images of Nellore beef cattle were collected during the weaning, stocker and feedlot phases. First, biometric body measurements of each animal, such as body volume, area, length, and others, were performed using three-dimensional images captured with the Kinect® sensor, and their respective BW were acquired using an electronic scale. Next, the biometric measurements were used as explanatory variables in the four predictive approaches (MLR, LASSO, PLS, and ANN). To evaluate prediction quality, a leave-one-out cross-validation was adopted. The ANN was the best prediction approach in terms of Root Mean Square Error of Prediction (RMSEP) and squared predictive correlation (r2). The results for Weaning were RMSEP = 8.6 kg and r2 = 0.91; for Stocker phase, RMSEP = 11.4 kg and r2 = 0.79; and for Beginning of feedlot, RMSEP = 7.7 kg and r2 = 0.92. The ANN was also the best method for prediction of ADG, with RMSEP = 0.02 kg/d and r2 = 0.67 for the period between Weaning and Stocker, RMSEP = 0.02 kg/d and r2 = 0.85 for the Weaning and Beginning of Feedlot phase, RMSEP = 0.03 kg/d and r2 = 0.80 for Weaning and Final of Feedlot phase, RMSEP = 0.10 kg/d and r2 = 0.51 for Stocker and Beginning of feedlot phase, and RMSEP = 0.09 kg/d and r2 = 0.82 for the Beginning and Final of feedlot phase. Overall, the results indicate that the proposed automated computer vision system can be successfully used to predict BW and ADG in real-time in beef cattle.