Dense Dilated Convolutions Merging Network for Semantic Mapping of Remote Sensing Images
This addresses the problem of recognizing multi-scale and complex objects in remote sensing for applications like urban planning, but it is incremental as it builds on existing deep learning approaches.
The paper tackled semantic mapping of remote sensing images by proposing DDCM-Net, which achieved 92.3% F1-score and 86.0% mIoU on the ISPRS Potsdam dataset and outperformed previous methods on the ISPRS Vaihingen dataset with 89.8% F1-score.
We propose a network for semantic mapping called the Dense Dilated Convolutions Merging Network (DDCM-Net) to provide a deep learning approach that can recognize multi-scale and complex shaped objects with similar color and textures, such as buildings, surfaces/roads, and trees in very high resolution remote sensing images. The proposed DDCM-Net consists of dense dilated convolutions merged with varying dilation rates. This can effectively enlarge the kernels' receptive fields, and, more importantly, obtain fused local and global context information to promote surrounding discriminative capability. We demonstrate the effectiveness of the proposed DDCM-Net on the publicly available ISPRS Potsdam dataset and achieve a performance of 92.3% F1-score and 86.0% mean intersection over union accuracy by only using the RGB bands, without any post-processing. We also show results on the ISPRS Vaihingen dataset, where the DDCM-Net trained with IRRG bands, also obtained better mapping accuracy (89.8% F1-score) than previous state-of-the-art approaches.