Neural networks and computational vision application in feature recognition at agricultural fields

• Grant number: 20/11262-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): December 01, 2020
• Status: Discontinued
• Field of knowledge: Agronomical Sciences - Agricultural Engineering
• Principal Investigator: Marcelo Becker
• Grantee: Lucas Toschi de Oliveira
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated scholarship(s): 22/13040-0 - Detection module development for Visual Simultaneous Localization and Mapping for agricultural environments using the commercial robot TerraSentia in partnership with the University of Illinois (Urbana-Champaign), BE.EP.IC

Abstract

The global population growth demands that the methods and technologies applied to food production must be even more efficient, making more with less space. The autonomous robotics is a trending research area to help with this problem. However, the development of an autonomous navigation system, capable of driving a robot inside a plantation by itself, is still a challenge. In this context, SLAM (Simultaneous Localization And Mapping) technology, which can generate an environment local map, is a potential study subject. In dynamic places, like the agricultural one, this method is more susceptible to errors because of the typical assumption of static surroundings. In the search for better results, the use of neural networks in the identification of mobile objects, which eliminates them from the mapping process, is a promising alternative and is the main focus of this project. The data utilized was taken by TerraSentia, an agricultural mobile robot equipped with a monocular camera.