ChloroScanner: portable equipment for early detection of plant diseases

• Grant number: 23/03571-0
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: August 01, 2023
• End date: April 30, 2024
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Montcharles da Silva Pontes
• Grantee: Montcharles da Silva Pontes
• Company: Agroptica Instrumentação e Serviços Ltda
• CNAE: Fabricação de aparelhos e equipamentos de medida, teste e controle ; Desenvolvimento e licenciamento de programas de computador não-customizáveis ; Testes e análises técnicas
• Associated researchers: Anderson Rodrigues Lima Caires ; Jean-Claude Mpeko ; KAREL NEGRIN NAPOLES ; Samuel Leite de Oliveira
• Associated scholarship(s): 23/11112-6 - ChloroScanner: portable equipment for early detection of plant diseases, BP.PIPE

Abstract

The project proposes the development of a functional device for pulsed modulated fluorescence imaging that is portable, easy to handle, and relatively low in manufacturing cost, enabling the early detection of diseases in plants through in vivo leaf analysis. To achieve this, in this first phase, a functional prototype will be constructed through the development of suitable hardware and software components for the device. Portable devices currently used to obtain fluorescence images of photosynthetic activity in plants, aimed at detecting anomalies, are primarily characterized by the use of a CCD-type sensor in combination with a high-power LED array as the excitation source. This combination requires (i) a high energy consumption to power the high-power LEDs, necessitating the use of costly and large batteries, and (ii) the use of expensive optical elements, impacting the size and final cost of the equipment. Typically, these devices consist of multiple components (computer, batteries, camera, etc.), making their use in the field (in loco) difficult or even unfeasible. Consequently, this situation also contributes to the unavailability of databases of chlorophyll fluorescence images obtained directly in the fields, an issue that this project intends to address in the future, along with machine learning algorithms, to assist in the early diagnosis of diseases. (AU)