The objective with this study was to analyze the body measurements of Girolando cattle, as well as measurements extracted from their images, to generate a model to understand which measures further explain the cattle body weight. Therefore, the experiment physically measured 34 Girolando cattle (two males and 32 females), for the following traits: heart girth (HG P), circumference of the abdomen, body length, occipito-ischial length, wither height, and hip height. In addition, images of the dorsum and the body lateral area of these animals allowed measurements of hip width (HW I), body length, tail distance to the neck, dorsum area (DA I), dorsum perimeter, wither height, hip height, body lateral area, perimeter of the lateral area, and rib height. The measurements extracted from the images were subjected to the stepwise regression method and regression-based machine learning algorithms. The HG p was the physical measure with stronger positive correlation with respect to body weight. In the stepwise method, the final model generated R² of 0.70 and RMSE of 42.52 kg and the equation: WEIGHT (kg) = 6.15421 * HW I (cm) + 0.01929 * DA I (cm 2) + 70.8388. The linear regression and SVM algorithms obtained the best results, followed by discretization regression with random forests. The set of rules presented in this study can be recommended for estimating body weight in Girolando cattle, at a correlation coefficient of 0.71, by measurements of hip width and dorsum area, both extracted from cattle images.

This study explores the use of a Siamese neural network architecture to enhance classification performance in few-shot learning scenarios, with a focus on bovine facial recognition. Traditional methodologies often require large datasets, which can significantly stress animals during data collection. In contrast, the proposed method aims to reduce the number of images needed, thereby minimizing animal stress. Systematic experiments conducted on datasets representing both full and few-shot learning scenarios revealed that the Siamese network consistently outperforms traditional models, such as ResNet101. It achieved notable improvements, with mean values increasing by over 6.5% and standard deviations decreasing by at least 0.010 compared to the ResNet101 baseline. These results highlight the Siamese network’s robustness and consistency, even in resource-constrained environments, and suggest that it offers a promising solution for enhancing model performance with fewer data and reduced animal stress, despite its slower training speed.

The determination of the number of termite mounds in a pasture area is a factor that can determine the stage of degradation of the same. The termite count work has been done manually which becomes costly. Our work aims to present a comparison of image filtering techniques and the best time to collect aerial images with UAV (Unmanned Aerial Vehicles) in order to count the number of termite mounds by means of computer vision. Comparisons were made between the number of mounds counted in the image by a specialist with the number of mounds in the image after being submitted to computer vision techniques. It was identified that height is the main variable and that of the five techniques used, Gaussian and Bilateral presented the best results.