Accurate Road Detection from Satellite Images Using Modified U-net
| Autor: | Alexandre Constantin, Jian-Jiun Ding, Yih-Cherng Lee |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Jaccard index
010504 meteorology & atmospheric sciences Artificial neural network Computer science business.industry Binary number Pattern recognition 04 agricultural and veterinary sciences 01 natural sciences Convolutional neural network Binary classification Kernel (image processing) 040103 agronomy & agriculture 0401 agriculture forestry and fisheries Satellite Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | APCCAS |
| DOI: | 10.1109/apccas.2018.8605652 |
| Popis: | In this paper, we present an accurate neural network algorithm to detect roads in satellite images. Based on convolutional neural networks, from a 6-channel image, this model is able to transfer the road structure to the output using both the U-net and the atrous convolution architecture. To train this model, we introduce a new combination of existing loss functions including the binary cross-entropy and the Jaccard distance to avoid false positive detection and increase binary classification accuracy. In terms of precision, recall, the F-score and accuracy, experiments carried out using the Massachusetts roads dataset, provide better results than state-of-the-art road extraction models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|