Application of Kinect-Sensor for three-dimensional body measurements of cows

Frequent monitoring of animal body growth allows early recognition of health anomalies, and accordingly can reduce occurrence of problems connected to infertility or other diseases. Optical techniques have been proposed in the last decade as a fast non-contact approach for animal body analysis, allowing reduction of stress typically induced by manual measurements and at the same time execution of fast multi-parameters analysis. The aim of this study is to validate a new automated measuring system, suitable for continuous three-dimensional reconstruction of calves and cows body, for development monitoring. The new system is based on the Microsoft Kinect™ RGB-depth camera. The Microsoft Kinect™ is already raising significant interest and growing attention in agriculture and livestock applications for its high quality and low cost. Indeed, the sensor takes advantage of an infrared laser emitter, an infrared camera and an RGB camera to provide fast reconstruction of three-dimensional bodies. In the paper it is shown how 3D data set can be successfully implemented for fast extraction and monitoring of different body parameters, such as hip and withers height, hips distance, head size, chest girth, etc. An hypothetical combination of body analysis with automatic feeding or milking phases not only offers information about animal health and welfare indicators, but can also offer a feedback response for optimization of the same phases.