The potential of an RGB-D sensor as a tool to estimate Nellore heifers’ body mass and morphometric measurements through image analysis was evaluated. An Intel RealSense D435i depth sensor was used to acquire dorsal images of 260 animals aged between 8 and 18 months. Images were acquired from March to December 2019 in six-time points. The best quality images were selected using a multi-layer perceptron neural network (nn = 547). The images were then manually associated with each animal's electronic ear tag. Morphometric measurements were manually acquired using a hipometer and measured on the images using the OpenCV library's graphical interface. These values were acquired in pixels converted to meters. The adjusted linear regression analysis between body mass measured with a scale and estimated body volume presented a high coefficient of determination of R² = 0.97. The mean absolute percentage error was 3.13%, the absolute error was ± 8.85 kg, and the mean squared error was 10.07 kg. The mean absolute error, mean squared error and mean absolute percentage error between manually acquired and digitally acquired morphometric measurements were: 4.23 cm, 5.34 cm, and 18% for chest width (R² = 0.56); 4.4 cm, 5.1 cm, and 13.9% for croup width (R² = 0.86); 6.0 cm, 8.0 cm, and 19.3% for croup length (R² = 0.75); 4.7 cm, 6.6 cm, and 3.8% for croup height (R² = 0.9); and 3.5 cm, 5.1 cm, and 2.9% for withers height (R² = 0.92). This study showed that it is possible to estimate body mass in Nellore heifers using a depth sensor and has good potential for application on morphometric evaluations.

评估了RGB-D传感器作为通过图像分析估算Nellore小母牛的体重和形态测量结果的工具的潜力。使用英特尔实感D435i深度传感器获取260只年龄在8到18个月之间的动物的背侧图像。在2019年3月至2019年12月的六个时间点获取了图像。使用多层感知器神经网络（nn = 547）。然后将图像与每个动物的电子耳标手动关联。形态测量值是使用湿度计手动获取的，并使用OpenCV库的图形界面在图像上进行测量。这些值以转换为米的像素获取。用标尺测量的体重与估计的体重之间的调整后的线性回归分析显示出较高的测定系数R²= 0.97。平均绝对百分比误差为3.13％，绝对误差为±8.85 kg，平均平方误差为10.07 kg。手动获取和数字获取形态测量结果之间的平均绝对误差，均方误差和平均绝对百分比误差为：胸宽（R²= 0.56）为4.23 cm，5.34 cm和18％。臀部宽度（R 2 ＝ 0.86）为4.4cm，5.1cm和13.9％。6。收起长度为0 cm，8.0 cm和19.3％（R²= 0.75）；臀部高度（R²= 0.9）分别为4.7厘米，6.6厘米和3.8％；高度分别为3.5厘米，5.1厘米和2.9％（R²= 0.92）。这项研究表明，使用深度传感器可以估算内罗尔小母牛的体重，并且在形态计量学评估中具有良好的应用潜力。