Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study

Sensors

Raoof Naushad¹  Tarunpreet Kaur²  Ebrahim Ghaderpour³ 

[1] Accubits Invent—Artificial Intelligence R&D Lab, Accubits Technologies Inc., Trivandrum 695581, India;Department of Biomedical Science, Acharya Narendra Dev College, University of Delhi, Delhi 110019, India;Department of Geomatics Engineering, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada;

关键词: land use classification;    land cover classification;    remote sensing;    satellite imagery;    EuroSAT;    earth observation;   

DOI  :  10.3390/s21238083

来源: DOAJ

【 摘 要 】

Efficiently implementing remote sensing image classification with high spatial resolution imagery can provide significant value in land use and land cover (LULC) classification. The new advances in remote sensing and deep learning technologies have facilitated the extraction of spatiotemporal information for LULC classification. Moreover, diverse disciplines of science, including remote sensing, have utilised tremendous improvements in image classification involving convolutional neural networks (CNNs) with transfer learning. In this study, instead of training CNNs from scratch, the transfer learning was applied to fine-tune pre-trained networks Visual Geometry Group (VGG16) and Wide Residual Networks (WRNs), by replacing the final layers with additional layers, for LULC classification using the red–green–blue version of the EuroSAT dataset. Moreover, the performance and computational time are compared and optimised with techniques such as early stopping, gradient clipping, adaptive learning rates, and data augmentation. The proposed approaches have addressed the limited-data problem, and very good accuracies were achieved. The results show that the proposed method based on WRNs outperformed the previous best results in terms of computational efficiency and accuracy, by achieving 99.17%.

【 授权许可】

Unknown