Autor(es): Videira, João ; Gaspar, Pedro Dinis ; Soares, V.N.G.J. ; Caldeira, J.M.L.P.
Data: 2024
Identificador Persistente: http://hdl.handle.net/10400.11/8903
Origem: Repositório Científico do Instituto Politécnico de Castelo Branco
Assunto(s): Wild flowers and plants; Development stages; Computer vision; Convolutional neural networks; YOLOv4; YOLOv4-tiny; Mobile app
Wild flowers and plants appear spontaneously. They form the ecological basis on which life depends. They play a fundamental role in the regeneration of natural life and the balance of ecological systems. However, this irreplaceable natural heritage is at risk of being lost due to human activity and climate change. The work presented in this paper contributes to the conservation effort. It is based on a previous study by the same authors, which identified computer vision as a suitable technological platform for detecting and monitoring the development stages of wild flowers and plants. It describes the process of developing a mobile application that uses YOLOv4 and YOLOv4-tiny convolutional neural networks to detect the stages of development of wild flowers and plants. This application could be used by visitors in a nature park to provide information and raise awareness about the wild flowers and plants they find along the roads and trails.
