Portal de Periódicos da CAPES

Artigo Produção Nacional Revisado por pares

BIBTEX RIS

Combined weightless neural network FPGA architecture for deforestation surveillance and visual navigation of UAVs

2019; Elsevier BV; Volume: 87; Linguagem: Inglês

10.1016/j.engappai.2019.08.021

1873-6769

Vitor Ferreira Torres, Brayan René Acevedo Jaimes, Eduardo S. Ribeiro, Mateus T. Braga, Elcio Hideiti Shiguemori, Haroldo Fraga de Campos Velho, Luiz C. B. Torres, Antônio P. Braga,

Advanced Image and Video Retrieval Techniques

This work presents a combined weightless neural network architecture for deforestation surveillance and visual navigation of Unmanned Aerial Vehicles (UAVs). Binary images, which are required for position estimation and UAV navigation, are provided by the deforestation surveillance circuit. Learned models are evaluated in a real UAV flight over a green countryside area, while deforestation surveillance is assessed with an Amazon forest benchmarking image data. Small utilization percentage of Field Programmable Gate Arrays (FPGAs) allows for a higher degree of parallelization and block processing of larger regions of input images.