An Improved Single Shot Multibox Detector Method Applied in Body Condition Score for Dairy Cows

Simple Summary Body condition score (BCS) is an important work for feeding management and cow welfare on the farm. The aim of our study is to assess the BCS automatically and replace the traditional manual method. In this study, we firstly built a non-contact and no-stress platform with a network camera, which can monitor the BCS of dairy cow remotely, and the back-view images of the cows were collected and the data set labeled by veterinary experts was built. Secondly, the improved Sing Shot multi-box Detector (SSD) algorithm was introduced to assess the BCS of each image. Finally, the experiments were carried out and the results showed the improved SSD had advantages of higher detecting speed and smaller model size compared with the original SSD. Abstract Body condition scores (BCS) is an important parameter, which is in high correlation with the health status of a dairy cow, metabolic disorder and milk composition during the production period. To evaluate BCS, the traditional methods rely on veterinary experts or skilled staff to look at a cow and touch it. These methods have low efficiency especially on large-scale farms. Computer vision methods are widely used but there are some improvements to increase BCS accuracy. In this study, a low cost BCS evaluation method based on deep learning and machine vision is proposed. Firstly, the back-view images of the cows are captured by network cameras, resulting in 8972 images that constituted the sample data set. The camera is a common 2D camera, which is cheaper and easier to install compared with 3D cameras. Secondly, the key body parts such as tails, pins and rump in the images were labeled manually, the Sing Shot multi-box Detector (SSD) method was used to detect the tail and evaluate the BCS. Inspired by DenseNet and Inception-v4, a new SSD was introduced by changing the network connection method of the original SSD. Finally, the experiments show that the improved SSD method can achieve 98.46% classification accuracy and 89.63% location accuracy, and it has: (1) faster detection speed with 115 fps; (2) smaller model size with 23.1 MB compared to original SSD and YOLO-v3, these are significant advantages for reducing hardware costs.