A computer vision approach based on deep learning for the detection of dairy cows in free stall barn

10 Precision Livestock Farming relies on several technological approaches to acquire in the most efficient way 11 precise and up-to-date data concerning individual animals. In dairy farming, particular attention is paid to the 12 automatic cow detection and tracking, as such information is closely related to animal welfare and thus to 13 possible health issues. Computer vision represents a suitable and promising method for this purpose. 14 This paper describes the first step for the development of a computer vision system, based on deep learning, 15 aiming to recognize in real-time the individual cows, detect their positions, actions and movements and record 16 the time history outputs for each animal. 17 Specifically, a neural network based on deep learning techniques has been trained and validated on a case 18 study farm, for the automatic recognition of individual cows in videos recorded in the barn. Four cows were 19 selected to train and validate a YOLO neural network able to recognize a cow starting from the coat pattern. 20 Then, precision-recall curves of the identification of individual cows were elaborated for both the specific 21 target classes and the whole dataset in order to assess the performances of the network. 22 By means of data augmentation techniques, an enlarged dataset has been created and considered in order to 23 improve the performance of the network and to provide indications to increase detection efficiency in those 24 cases where data acquisition is not easy to be carried out for long periods. The mean average precision of the 25 detection, ranging from 0.64 to 0.66, showed that it is possible to properly identify individual cows based on