Detection of Pathologies in Eucalyptus Crops Using UAVs (Unmanned Aerial Vehicles) and Supervised Learning

• Grant number: 13/20645-6
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: April 01, 2014
• End date: January 26, 2015
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Denis Fernando Wolf
• Grantee: Jefferson Rodrigo de Souza
• Host 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.