期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 59, 期 6, 页码 4673-4688出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.3016086
关键词
Roads; Image segmentation; Feature extraction; Adaptation models; Task analysis; Training; Generators; Adversarial network; domain adaptation; feature pyramid (FP); remote sensing (RS) images; road segmentation
类别
资金
- NSFC [61806125, 61977046]
A new model is introduced to apply structured domain adaption for synthetic image generation and road segmentation, incorporating a feature pyramid network into generative adversarial networks to minimize the difference between the source and target domains and improve road extraction accuracy and completeness.
Road extraction in remote sensing images is of great importance for a wide range of applications. Because of the complex background, and high density, most of the existing methods fail to accurately extract a road network that appears correct and complete. Moreover, they suffer from either insufficient training data or high costs of manual annotation. To address these problems, we introduce a new model to apply structured domain adaption for synthetic image generation and road segmentation. We incorporate a feature pyramid (FP) network into generative adversarial networks to minimize the difference between the source and target domains. A generator is learned to produce quality synthetic images, and the discriminator attempts to distinguish them. We also propose a FP network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales' objects. Indeed, a novel scale-wise architecture is introduced to learn from the multilevel feature maps and improve the semantics of the features. For optimization, the model is trained by a joint reconstruction loss function, which minimizes the difference between the fake images and the real ones. A wide range of experiments on three data sets prove the superior performance of the proposed approach in terms of accuracy and efficiency. In particular, our model achieves stateof-the-art 78.86 IOU on the Massachusetts data set with 14.89M parameters and 86.78B FLOPs, with 4x fewer FLOPs but higher accuracy (+3.47% IOU) than the top performer among state-ofthe-art approaches used in the evaluation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据