U-Net Convolutional Networks for Mining Land Cover Classification Based on High-Resolution UAV Imagery

• Published in: IEEE access Vol. 8; pp. 186257 - 186273
• Main Authors: Giang, Tuan Linh, Dang, Kinh Bac, Toan Le, Quang, Nguyen, Vu Giang, Tong, Si Son, Pham, Van-Manh
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computational modeling; Daknong; Data mining; Deep learning; Deforestation; Grasslands; High resolution; Image classification; Image resolution; Land cover; Land use; loss function; Monitoring; open-cast mining; optimization; permanent cropland; Real-time systems; segmentation; Soil; Soil water; U-Net convolutional network; unmanned aerial vehicle; Unmanned aerial vehicles; Water pollution; Vietnam
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.3030112

Mining activities are the leading cause of deforestation, land-use changes, and pollution. Land use/cover mapping in Vietnam every five years is not useful to monitor land covers in mining areas, especially in the Central Highland region. It is necessary to equip managers with a better tool to monitor and map land cover using high-resolution images. Therefore, the authors proposed using the U-Net convolutional network for land-cover classification based on multispectral Unmanned aerial vehicle (UAV) image in a mining area of Daknong province, Vietnam. An area of 0.5kmx0.8km was used for training and testing seven U-Net models using seven optimizer function types. The final U-Net model can interpret six land cover types: (1) open-case mining lands, (2) old permanent croplands, (3) young permanent croplands, (4) grasslands, (5) bare soils, (6) water bodies. As a result, two models using Nadam and Adadelta optimizer function can be used to classify six land cover types with accuracy higher than 83%, especially in open-case mining lands and polluted streams flowed out from the mining areas. The trained U-Net models can potentially update new land cover types in other mining areas towards monitoring land cover changes in real-time in the future.