Super-Resolution Integrated Building Semantic Segmentation for Multi-Source Remote Sensing Imagery
Super-Resolution Integrated Building Semantic Segmentation for Multi-Source Remote Sensing Imagery
复制标题
DOI：
10.1109/access.2019.2928646
复制
发表时间：
2019
期刊：
影响因子：
3.9
通讯作者：
Zhiling Guo;Guangming Wu;Xiaoya Song;W. Yuan;Qi Chen;H. Zhang;Xiaodan Shi;Mingzhou Xu-;Yongwei Xu;R. Shibasaki;Xiaowei Shao
中科院分区：
文献类型：
--
作者：
Zhiling Guo;Guangming Wu;Xiaoya Song;W. Yuan;Qi Chen;H. Zhang;Xiaodan Shi;Mingzhou Xu-;Yongwei Xu;R. Shibasaki;Xiaowei Shao
由于数据采集系统的发展，多源遥感图像已变得广泛可用。在本文中，我们解决了具有挑战性的任务，语义分割的建筑物，通过多源遥感图像具有不同的空间分辨率。与以往的工作，主要集中在优化分割模型，这并没有使训练和测试数据之间的不对齐的分辨率所造成的严重问题，从根本上解决，我们建议将SR技术与现有的框架，以提高分割性能。利用具有代表性的多源研究材料：高分辨率（HR）航空和低分辨率（LR）全色卫星图像分别作为训练和测试数据，对所提出方法的可行性进行了评估。首先采用基于深度学习的超分辨率（SR）模型将LR图像超分辨率化到SR空间，而不是使用HR图像训练的模型直接从LR图像进行建筑物分割，这可以减轻训练和测试数据之间分辨率差异的影响。从日本东京的测试区获得的实验结果表明，所提出的SR集成方法显着优于没有SR，提高Jaccard指数和kappa分别约19.01%和19.10%，。结果证实，所提出的方法是一个可行的工具，建立语义分割，特别是当分辨率是不对齐的。
Multi-source remote sensing imagery has become widely accessible owing to the development of data acquisition systems. In this paper, we address the challenging task of the semantic segmentation of buildings via multi-source remote sensing imagery with different spatial resolutions. Unlike previous works that mainly focused on optimizing the segmentation model, which did not enable the severe problems caused by the unaligned resolution between the training and testing data to be fundamentally solved, we propose to integrate SR techniques with the existing framework to enhance the segmentation performance. The feasibility of the proposed method was evaluated by utilizing representative multi-source study materials: high-resolution (HR) aerial and low-resolution (LR) panchromatic satellite imagery as the training and testing data, respectively. Instead of directly conducting building segmentation from the LR imagery by using the model trained using the HR imagery, the deep learning-based super-resolution (SR) model was first adopted to super-resolved LR imagery into SR space, which could mitigate the influence of the difference in resolution between the training and testing data. The experimental results obtained from the test area in Tokyo, Japan, demonstrate that the proposed SR-integrated method significantly outperforms that without SR, improving the Jaccard index and kappa by approximately 19.01% and 19.10%, respectively. The results confirmed that the proposed method is a viable tool for building semantic segmentation, especially when the resolution is unaligned.