Título:	Cattle monitoring with drones for weight estimation in confinement.
Autoria:	TETILA, E. C. GONÇALVES, R. C. OLIVEIRA, J. L. de BARBEDO, J. G. A.
Afiliação:	EVERTON CASTELÃO TETILA, UNIVERSIDADE FEDERAL DA GRANDE DOURADOS; RIAN CARRASCO GONÇALVES; JOSEMAR LOURENÇO DE OLIVEIRA, FACULDADE ANHANGUERA DE DOURADOS; JAYME GARCIA ARNAL BARBEDO, CNPTIA.
Ano de publicação:	2025
Referência:	In: WORKSHOP CIENTÍFICO DO CENTRO DE CIÊNCIA PARA O DESENVOLVIMENTO EM AGRICULTURA DIGITAL – SEMEAR DIGITAL, 2., 2025, Campinas. Anais [...]. Piracicaba: ESALQ/USP, 2025. p. 131-136.
Conteúdo:	Determining the optimal slaughter point for beef cattle is a critical challenge for maximizing production efficiency and profitability in the livestock sector. This study proposes an innovative approach for the automated monitoring of growth and fattening in Nelore cattle under feedlot conditions, using unmanned aerial vehicles (UAVs) and artificial intelligence techniques. Between July and October 2024, thirteen flight operations were conducted at the Campanário Farm feedlot (Laguna Carapã-MS), resulting in the collection of approximately 10,000 aerial images of 110 individually identified animals through hot-iron branding. The images were processed using semantic segmentation techniques to extract body measurements and estimate the weight of each individual. The system aims not only to accurately predict weight but also to detect anomalous behaviors and conditions that may impact zootechnical performance, such as bovine sodomy, weakness, and inadequate feed distribution. As an additional contribution, the NelloreBeefCattleDataset, containing approximately 10,000 annotated samples, was developed and made publicly available. Various deep learning models implemented in PyTorch and TensorFlow were evaluated. The expected outcomes include improved decision-making in feedlot management, reduced animal stress, and increased accuracy in determining the ideal slaughter time. The work is currently ongoing.
NAL Thesaurus:	Unmanned aerial vehicles Artificial intelligence
Palavras-chave:	Inteligência artificial Monitoramento de gado Veículo aéreo não tripulado Segmentação semântica Estimativa de peso Cattle monitoring Semantic segmentation Weight estimation
ISBN:	978-85-86481-94-9
Notas:	Organização: Silvia Maria Fonseca Silveira Massruhá, Durval Dourado Neto, Luciana Alvim Santos Romani, Jayme Garcia Arnal Barbedo, Édson Luis Bolfe, Ivan Bergier, Maria Angelica de Andrade Leite, Vitor Del Alamo Guarda, Catarina Barbosa Careta.
Tipo do material:	Artigo em anais e proceedings
Acesso:	openAccess
Aparece nas coleções:	Artigo em anais de congresso (CNPTIA)