Mapping Areas Invaded by Pinus sp. from Geographic Object-Based Image Analysis (GEOBIA) Applied on RPAS (Drone) Color Images

Abstract

Invasive alien species reduce biodiversity. In southern Brazil, the genus Pinus is considered invasive, and its dispersal by humans has resulted in this species reaching ecosystems that are more sensitive and less suitable for cultivation, as is the case for the restingas on the island of Santa Catarina. Invasion control requires persistent efforts to identify and treat each new invasion case as a priority. In this study, areas invaded by Pinus sp. in restingas were mapped using images taken by a remotely piloted aircraft system (RPAS, or drone) to identify the invasion areas in great detail, enabling management to be planned for the most recently invaded areas, where management is simpler, more effective, and less costly. Geographic object-based image analysis (GEOBIA) was applied on images taken from a conventional RGB camera embedded in an RPAS, which resulted in a global accuracy of 89.56%, a mean kappa index of 0.86, and an F-score of 0.90 for Pinus sp. Processing was conducted with open-source software to reduce operational costs.

Opções para a gestão e o manejo de espécies exóticas invasoras

“…O monitoramento com uso de drones para fins de detecção precoce em ambientes abertos como campos e restingas é promissor especialmente para espécies arbóreas como acácias (Acacia mangium), pinheiros-americanos (Pinus spp.) e casuarina (Casuarina equisetifolia) (Lehmann et al 2017, Gonçalves et al 2022, Simberloff 2022. Adicionalmente, constelações de nanosatélites, assim como satélites gerando imagens de alta resolução, podem vir a substituir drones para uso na detecção precoce de espécies invasoras (Simberloff 2022).…”

Relatório temático sobre espécies exóticas invasoras, biodiversidade e serviços ecossistêmicos

“…O monitoramento com uso de drones para fins de detecção precoce em ambientes abertos como campos e restingas é promissor especialmente para espécies arbóreas como acácias (Acacia mangium), pinheiros-americanos (Pinus spp.) e casuarina (Casuarina equisetifolia) (Lehmann et al 2017, Gonçalves et al 2022, Simberloff 2022. Adicionalmente, constelações de nanosatélites, assim como satélites gerando imagens de alta resolução, podem vir a substituir drones para uso na detecção precoce de espécies invasoras (Simberloff 2022).…”

Performance evaluation of classifiers for the COVID-19 symptom-based dataset using different feature selection methods

“…It uses a specific classifier to estimate the merit of a set of attributes. WrapperSubsetEval does the internal cross-validation technique to evaluate the classification accuracy of a specific group of attributes [42,43]. It is generally considered to be more computationally expensive than other feature selection methods, but it can also be more effective at selecting the best features, because it considers the interaction between the features and the model.…”