Advanced search
Start date
Betweenand

Detection of pathologies in eucalyptus crops using UAVs (unmanned aerial vehicles) and supervised learning

Grant number: 13/20645-6
Support type:Scholarships in Brazil - Post-Doctorate
Effective date (Start): April 01, 2014
Effective date (End): January 26, 2015
Field of knowledge:Physical Sciences and Mathematics - Computer Science
Principal Investigator:Denis Fernando Wolf
Grantee:Jefferson Rodrigo de Souza
Home Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The detection of pathologies in eucalyptus crops is a highly relevant problem for Brazilian agriculture. This issue has been researched in this area for decades and still has great potential for scientific research. Eucalyptus has many benefits, as rapid growth, high productivity, wide diversity of species and great capacity to adapt. In Brazil, in 2012, the state of Mato Grosso do Sul was evidenced by the increase 22.5% of the area planted of Pinus and Eucalyptus compared to the previous year. As a result, the Brazilian forest crops have a fundamental highlight in the national and international scenario. Due to the influence that the eucalyptusproduction have in these scenarios, and the size occupied by their planting areas, as the possibility for a significant increase in production, this research plan proposes the development of detection of pathologies in eucalyptus crops for aircraft. Aim to use aerialimages obtained by UAVs (Unmanned Aerial Vehicles) for detecting pathologies found in eucalyptus. The supervised learning algorithms will be used to correlate the information obtained from sensors on the UAV with its aerial images. Initially, the system will have a learning step, where a pilot will conduct the UAVs and provide data for the learning algorithms. After that, the system will be able of use the acquired knowledge to detect pathologies in eucalyptus.