Assessment of UAV-Based Deep Learning for Corn Crop Analysis in Midwest Brazil
José Augusto Correa Martins,
Alberto Yoshiriki Hisano Higuti,
Aiesca Oliveira Pellegrin,
Raquel Soares Juliano,
Adriana Mello de Araújo,
Luiz Alberto Pellegrin,
Veraldo Liesenberg,
Ana Paula Marques Ramos,
Wesley Nunes Gonçalves,
Diego André Sant’Ana,
Hemerson Pistori,
José Marcato Junior
Affiliations
José Augusto Correa Martins
Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Cidade Universitária, Av. Costa e Silva, Pioneiros 79070-900, MS, Brazil
Alberto Yoshiriki Hisano Higuti
Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Cidade Universitária, Av. Costa e Silva, Pioneiros 79070-900, MS, Brazil
Aiesca Oliveira Pellegrin
Embrapa Pantanal, Rua 21 de Setembro, 1880, Corumbá, MS, 79320-900, Brazil
Raquel Soares Juliano
Embrapa Pantanal, Rua 21 de Setembro, 1880, Corumbá, MS, 79320-900, Brazil
Adriana Mello de Araújo
Embrapa Pantanal, Rua 21 de Setembro, 1880, Corumbá, MS, 79320-900, Brazil
Luiz Alberto Pellegrin
Embrapa Pantanal, Rua 21 de Setembro, 1880, Corumbá, MS, 79320-900, Brazil
Veraldo Liesenberg
Forest Engineering Department, Santa Catarina State University, Avenida Luiz de Camões 2090, Lages 88520-000, SC, Brazil
Ana Paula Marques Ramos
Environment and Regional Development Program, University of Western São Paulo, Rodovia Raposo Tavares, km 572, Bairro Limoeiro 19067-175, SP, Brazil
Wesley Nunes Gonçalves
Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Cidade Universitária, Av. Costa e Silva, Pioneiros 79070-900, MS, Brazil
Diego André Sant’Ana
Instituto Federal de Mato Grosso do Sul, Campus Aquidauana, Street Amelia Arima, 222, Aquidauana 79200-000, MS, Brazil
Hemerson Pistori
Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Cidade Universitária, Av. Costa e Silva, Pioneiros 79070-900, MS, Brazil
José Marcato Junior
Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Cidade Universitária, Av. Costa e Silva, Pioneiros 79070-900, MS, Brazil
Crop segmentation, the process of identifying and delineating agricultural fields or specific crops within an image, plays a crucial role in precision agriculture, enabling farmers and public managers to make informed decisions regarding crop health, yield estimation, and resource allocation in Midwest Brazil. The crops (corn) in this region are being damaged by wild pigs and other diseases. For the quantification of corn fields, this paper applies novel computer-vision techniques and a new dataset of corn imagery composed of 1416 256 × 256 images and corresponding labels. We flew nine drone missions and classified wild pig damage in ten orthomosaics in different stages of growth using semi-automatic digitizing and deep-learning techniques. The period of crop-development analysis will range from early sprouting to the start of the drying phase. The objective of segmentation is to transform or simplify the representation of an image, making it more meaningful and easier to interpret. For the objective class, corn achieved an IoU of 77.92%, and for background 83.25%, using DeepLabV3+ architecture, 78.81% for corn, and 83.73% for background using SegFormer architecture. For the objective class, the accuracy metrics were achieved at 86.88% and for background 91.41% using DeepLabV3+, 88.14% for the objective, and 91.15% for background using SegFormer.
