Image-based body mass prediction of heifers using deep neural networks

Dohmen, Roel; Catal, Cagatay; Liu, Qingzhi


Manual weighing of heifers is time-consuming, labour-intensive, expensive, and can be dangerous and risky for both humans and animals because it requires the animal to be stationary. To overcome this problem, automated approaches have been developed using computer vision techniques. In this research, the aim was to design a novel mass prediction model using deep learning algorithms for youngstock on dairy farms. The Mask-RCNN segmentation algorithm was used to segment the images of heifers and remove the background. A convolutional neural networks (CNN) model was developed on the Keras platform to predict the body mass of heifers. For the case study, a new dataset based on images of 63 heifers was built. Animals were between the age of 0 and 365 days and lived on the same farm in the Netherlands. The range of body mass of the heifers was between 37 kg and 370 kg. The side-view model had a coefficient of determination (R2) of 0.91 and a Root Mean Squared Error (RMSE) of 27 kg, the top-view model had an R2 of 0.96 and an RMSE of 20 kg. The experimental results demonstrated that our proposed mass prediction model using the Mask-RCNN segmentation algorithm, together with a novel CNN-based model, provided remarkable results, and that the top view was more suitable than the side view for predicting the body mass of youngstock in dairy farms.