No abstract

Predicting the live weight of cattle helps us monitor the health of animals, conduct genetic selection, and determine the optimal timing of slaughter. On large farms, accurate and expensive industrial scales are used to measure live weight. However, a promising alternative is to estimate live weight using morphometric measurements of livestock and then apply regression equations relating such measurements to live weight. Manual measurements on animals using a tape measure are time-consuming and stressful for the animals. Therefore, computer vision technologies are now increasingly used for non-contact morphometric measurements. The paper proposes a new model for predicting live weight based on augmenting three-dimensional clouds in the form of flat projections and image regression with deep learning. It is shown that on real datasets, the accuracy of weight measurement using the proposed model reaches 91.6%. We also discuss the potential applicability of the proposed approach to animal husbandry.

In this paper, we estimate the accuracy of 3D object reconstruction using multiple Kinect sensors. First, we discuss the calibration of multiple Kinect sensors, and provide an analysis of the accuracy and resolution of the depth data. Next, the precision of coordinate mapping between sensors data for registration of depth and color images is evaluated. We test a proposed system for 3D object reconstruction with four Kinect V2 sensors and present reconstruction accuracy results. Experiments and computer simulation are carried out using Matlab and Kinect V2.

In this paper, we first analyze the accuracy of 3D object reconstruction using point cloud filtering applied on data from a RGB-D sensor. Point cloud filtering algorithms carry out upsampling for defective point cloud. Various methods of point cloud filtering are tested and compared with respect to the reconstruction accuracy using real data. In order to improve the accuracy of 3D object reconstruction, an efficient method of point cloud filtering is designed. The presented results show an improvement in the accuracy of 3D object reconstruction using the proposed point cloud filtering algorithm.

Many studies have purposed in order to measure live animal body characteristics using RGB-D cameras. However, most of these studies were made only for specific body measurements in interactive manner. A deviation from the expected animal body characteristics can indicate ill thrift, diseases and vitality. Currently, the farm manager can measure the body characteristics manually. Manual measuring generally requires a lot of labor, and it is, therefore, time consuming and stressful for animals. In this work we propose a non-intrusive depth camera-based system for automatic measurement of various cattle body parameters such as linear and integral characteristics along directional lines and local areas, geodesic distances, perimeters of cross sections, etc