Scene-Driven Multitask Parallel Attention Network for Building Extraction in High-Resolution Remote Sensing Images
Scene-Driven Multitask Parallel Attention Network for Building Extraction in High-Resolution Remote Sensing Images
复制标题
DOI：
10.1109/tgrs.2020.3014312
复制
发表时间：
2021-05-01
影响因子：
8.2
通讯作者：
Ding, Huaxiang
中科院分区：
文献类型：
--
作者：
Guo, Haonan;Shi, Qian;Ding, Huaxiang
卷积神经网络的应用已被证明可以显著提高从高分辨率遥感图像中提取建筑物的精度。然而，由于建筑物的类内方差较大，不同类型的建筑物之间存在所谓的语义缺口，目前的方法大多无法在覆盖不同场景的大面积范围内提取各种建筑物，例如城中村和高层建筑，因为现有的建筑物提取策略对各种场景都是相同的。随着遥感图像分辨率的提高，基于场景先验的图像解译是可行的。然而，这一思路在VHR遥感影像的建筑物提取中尚未得到充分利用。本研究提出一种场景驱动的多任务并行注意卷积网络（MTPA-Net）来解决这些限制。该方法将输入图像划分为多标签场景，并在不同场景下分别以像素级对建筑物进行映射。此外，采用一种简单的后处理方法，将建筑物提取结果与场景先验相结合。我们提出的方法不需要多模型训练，网络可以端到端学习。在包含不同景观的各种城市和农村场景的数据集上评估了我们提出的方法的性能。实验结果表明，所提出的MTPA-Net在减少误分类区域和保持改进的鲁棒性方面优于目前最先进的算法。
The application of convolutional neural networks has been shown to significantly improve the accuracy of building extraction from very high-resolution (VHR) remote sensing images. However, there exist so-called semantic gaps among different kinds of buildings due to the large intraclass variance of buildings, and most of the present-day methods are ineffective in extracting various buildings in large areas that cover different scenes, for example, urban villages and high-rise buildings, because existing building extraction strategies are the same for various scenes. With the improvement of the resolution of remote sensing images, it is feasible to improve the image interpretation based on the scene prior. However, this idea has not been fully utilized in building extraction from VHR remote sensing imagery. This study proposes a scene-driven multitask parallel attention convolutional network (MTPA-Net) to resolve these limitations. The proposed approach classifies the input image into multilabel scenes and further separately maps the buildings in pixel level under different scenes. In addition, a simple postprocessing method is applied to integrate the building extraction results and scene prior. Our proposed method does not require multimodel training and the network can learn in an end-to-end manner. The performance of our proposed method is evaluated on a data set that includes various urban and rural scenes with diverse landscapes. The experimental results show that the proposed MTPA-Net outperforms state-of-the-art algorithms by reducing misclassification areas and maintaining improved robustness.