Andmebaasi logo

Sirvi Autor "Oliveira, F.M." järgi

Nüüd näidatakse 1 - 2 2
  • Pisipilt
    Kirje
    Evaluation of chest circumference in 3D lateral images of dairy cattle farming for body mass prediction
    (Estonian University of Life Sciences, 2025) Oliveira, F.M.; Ferraz, P.F.P.; Ferraz, G.A.S.; Cecchin, D.; Stopatto, A.F.S.; Becciolini, V.; Barbari, M.
    The advancement of precision livestock farming has underscored the importance of developing innovative and non-invasive methods for monitoring animal health and productivity. In this context, this study evaluated the application of computer vision to estimate the body mass (BM) of Holstein-Friesian dairy cows using 3D images captured laterally with the Intel RealSense D435i depth camera. The methodology involved correlating chest circumference (CC) measurements obtained in the field with those derived from lateral 3D images. A total of 250 animals were analyzed, with BM ranging from 420 to 855 kg, and the relationship between CC and BM was modeled using regression techniques. The results indicated a coefficient of determination (R² = 0.88) and a mean absolute percentage error (MAPE) of 3.94% for CC measured in the field. For CC derived from 3D images, R² was 0.847, with an MAPE of 5.29%. Although the 3D image-based method showed a slight reduction in accuracy, it demonstrated significant potential as a non-invasive and efficient alternative for estimating BM in dairy cows. Furthermore, the study highlights the role of 3D imaging technologies in acquiring detailed morphological data, enabling a more comprehensive understanding of body composition dynamics over time. These findings reinforce the potential of integrating digital technologies into dairy farming, promoting sustainable, precise, and labor-efficient management practices.
  • Pisipilt
    Kirje
    Spatial variability of methane and carbon dioxide gases in a Compost-Bedded Pack Barn system
    (Estonian University of Life Sciences, 2024) Ferreira, J.C.; Ferraz, P.F.P.; Ferraz, G.A.S.; Oliveira, F.M.; Cadavid, V.G.; Rossi, G.; Becciolini, V.
    The dairy sector significantly contributes to global food production, however, it is closely associated with environmental concerns, specifically the emission of greenhouse gases such as methane (CH4) and carbon dioxide (CO2). The research problem focuses on the environmental impact of livestock farming, particularly in relation to the emission of greenhouse gases (GHG) such as methane (CH4) and carbon dioxide (CO2). Therefore, the objective of this paper was to assess the spatial variability of CH4 and CO2, as well as the thermal environment through the Temperature and Humidity Index (THI) and of air velocity (V, m s-1) in a Compost Bedded Pack (CBP). The experiment was carried out in October 2023, in a commercial dairy cattle facility measuring 54×22×4.5 m (length×width×height) that housed 80 lactating cows. Measurements were collected at 75 points, 0.25 m above the bedding, for one minute in each point. To characterize the distribution of gases and the thermal environment, the data were underwent geostatistical techniques and kriging maps. THI values ranged from 72.4 to 78.4, categorizing the animals into two environments within the facility, comfort and alert to thermal conditions. The maximum recorded for CO2 was 713.60 ppm in the region with a low ventilation incidence. CH4 reached a ranging from 103.38 to 196.73 ppm in areas with low ventilation and higher temperatures. The use of geostatistics enabled the characterization of spatial variability of greenhouse gases CH4 and CO2, as well as THI and V. Analyzing these variables is crucial for implementing mitigation actions and developing an increasingly sustainable production system.