Responsive image
Universidade Federal de Santa catarina (UFSC)
Programa de Pós-graduação em Engenharia, Gestão e Mídia do Conhecimento (PPGEGC)
Detalhes do Documento Analisado

Centro: Tecnológico

Departamento: Informática e Estatística/INE

Dimensão Institucional: Pesquisa

Dimensão ODS: Econômica

Tipo do Documento: Projeto de Pesquisa

Título: INCORPORATION OF ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL VISION TOOLS FOR YIELD PREDICTION IN VITIS VINIFERA CV TANNAT

Coordenador
  • JÔNATA TYSKA CARVALHO
Participante
  • JÔNATA TYSKA CARVALHO (D)
  • VITOR DIAS JAVORNIK

Conteúdo

Agricultural activity increasingly shows more a...agricultural activity increasingly shows more automation and information analysis that allows better monitoring and management, in what is called digital agriculture. in viticulture, visual inspection of the fruits is common in order to make appropriate management decisions by growers and even by other subsequent actors in the industry. this production is highly dependent on the growing conditions, so predicting the yield of a crop early and adapting crop management measures in time is essential. inspection is traditionally a manual task, but in recent years it has been identified as a target for automation. this project is organized into three lines of action. the first deals with the design and manufacture of a low-cost device for the automated capture of images of vineyards, thereby generating a database with annotated images for subsequent processing using machine learning techniques. the second line will seek to evaluate different methods in order to obtain a tool capable of detecting inflorescences and bunches of grapes, with the ultimate goal of predicting vineyard yields. the third line of work will create a network of researchers combined from the areas of plant biology and artificial intelligence, in order to promote the development of digital viticulture in our region. for this, dissemination activities will be carried out aimed at researchers, students and producers about the benefits of incorporating this type of tool.

Pós-processamento: Índice de Shannon: 3.43122

ODS 1 ODS 2 ODS 3 ODS 4 ODS 5 ODS 6 ODS 7 ODS 8 ODS 9 ODS 10 ODS 11 ODS 12 ODS 13 ODS 14 ODS 15 ODS 16
2,12% 16,02% 2,52% 3,77% 2,42% 5,83% 4,28% 4,30% 29,99% 1,73% 5,03% 4,18% 3,98% 5,67% 5,57% 2,60%
ODS Predominates
ODS 9
ODS 1

2,12%

ODS 2

16,02%

ODS 3

2,52%

ODS 4

3,77%

ODS 5

2,42%

ODS 6

5,83%

ODS 7

4,28%

ODS 8

4,30%

ODS 9

29,99%

ODS 10

1,73%

ODS 11

5,03%

ODS 12

4,18%

ODS 13

3,98%

ODS 14

5,67%

ODS 15

5,57%

ODS 16

2,60%