Cattle monitoring using drone images.

• Grant number: 23/03870-8
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: August 01, 2023
• End date: July 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Jayme Garcia Arnal Barbedo
• Grantee: Everton Castelão Tetila
• Host Institution: Embrapa Agricultura Digital. Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA). Campinas , SP, Brazil
• Associated research grant: 22/09319-9 - Center of Science for Development in Digital Agriculture - CCD-AD/SemeAr, AP.CCD

Abstract

The management of large areas dedicated to cattle farming is difficult and, in many cases, it is flawed, especially in the case of extensive production systems. With the popularization of unmanned aerial vehicles (UAVs, also known as drones), high-resolution aerial images can be obtained at relatively low costs. Although this is a promising technology, it is difficult to achieve its full potential due to the challenges involved in the extraction of relevant information from the images obtained. In the specific case of cattle monitoring, difficulties come from animal movement, terrain variety (exposed soil, dry pasture, vigorous pasture, etc.), from occlusions by obstacles such as trees and buildings, and from the tendency of animals to group together.One of the most basic applications in herd management is the estimation of the number of animals using digital images. A project on this theme was recently financed by Fapesp (2018/12845-9 - Cattle detection and counting using unmanned aerial vehicles), which generated many relevant results reported in some articles published in international journals. Despite the advancements achieved, the technology is not yet developed and validated enough for practical use. This project will employ artificial intelligence and deep learning techniques, deep learning platforms like tersorflow, and will demand knowledge on agricultural applications, and cattle production in particular. The objective is that the models already developed for animal counting be perfected and new models dedicated to applications such as anomaly detection (sick animals, calf births, etc.) and estimation of corporal dimensions be developed. (AU)

Scientific publications

(The scientific publications listed on this page originate from the Web of Science or SciELO databases. Their authors have cited FAPESP grant or fellowship project numbers awarded to Principal Investigators or Fellowship Recipients, whether or not they are among the authors. This information is collected automatically and retrieved directly from those bibliometric databases.)

TETILA, EVERTON CASTELAO; MORO, BARBARA LOPES; ASTOLFI, GILBERTO; COSTA, ANDERSON BESSA DA; AMORIM, WILLIAN PARAGUASSU; BELETE, NICOLAS ALESSANDRO DE SOUZA; PISTORI, HEMERSON; BARBEDO, JAYME GARCIA ARNAL. Real-time detection of weeds by species in soybean using UAV images. CROP PROTECTION, v. 184, p. 9-pg., 2024-07-22. (23/03870-8, 22/09319-9)

TETILA, EVERTON CASTELAO; WIRTI JUNIOR, GELSON; HIGA, GABRIEL TOSHIO HIROKAWA; DA COSTA, ANDERSON BESSA; AMORIM, WILLIAN PARAGUASSU; PISTORI, HEMERSON; BARBEDO, JAYME GARCIA ARNAL. Deep learning models for detection and recognition of weed species in corn crop. CROP PROTECTION, v. 195, p. 8-pg., 2025-04-24. (23/03870-8, 22/09319-9)

TETILA, EVERTON CASTELAO; DA SILVEIRA, FABIO AMARAL GODOY; COSTA, ANDERSON BESSA DA; AMORIM, WILLIAN PARAGUASSU; ASTOLFI, GILBERTO; PISTORI, HEMERSON; BARBEDO, JAYME GARCIA ARNAL. YOLO performance analysis for real-time detection of soybean pests. SMART AGRICULTURAL TECHNOLOGY, v. 7, p. 10-pg., 2024-02-05. (23/03870-8, 22/09319-9)