Abstract
Building segmentation is an important step in urban planning and development. In this work, we propose a new deep learning model, namely Multidimension Attention U-Net (MDAU-Net), to accurately segment building pixels and nonbuilding pixels in remote sensing images. Furthermore, we introduce a novel Multidimension Modified Efficient Channel Attention (MD-MECA) model to enhance the network discriminative ability through considering the interdependence between feature maps. Through deepening the U-Net model to a seven-story structure, the ability to identify the building is enhanced. We apply MD-MECA to the “skip connections” in traditional U-Net, instead of simply copying the feature mapping of the contraction path to the matching extension path, to optimize the feature transfer more efficiently. The obtained results show that our proposed MDAU-Net framework achieves the most advanced performance on publicly available building data sets (i.e. the precision over the Massachusetts buildings data set and WHU data set are 97.04% and 95.68%, respectively). Furthermore, we observed that the proposed framework outperforms several state-of-the-art approaches.
Highlights
With the rapid development of China’s remote sensing satellite industry, building segmentation in remote sensing image is an important research field in the image interpretation problems
We propose a new Multidimension Channel Attention Network model, called MDAU-Net, based on deep learning, which has achieved the latest performance in remote sensing image building
Erefore, a unit is discarded, its adjacent elements can still keep the semantic information of this location, and the information can still circulate in the convolutional neural network. erefore, to solve this problem, this paper introduces a structural form of the dropout method, i.e., DropBlock. e DropBlock technology is a regularization technology used in convolutional neural network proposed by researchers of Google Brain in 2018
Summary
With the rapid development of China’s remote sensing satellite industry, building segmentation in remote sensing image is an important research field in the image interpretation problems. We introduce a multidimensional channel attention, which uses the average pool and the maximum pool features in multidimensional channel to further improve the performance of building segmentation in remote sensing images. We propose a new Multidimension Channel Attention Network model, called MDAU-Net, based on deep learning, which has achieved the latest performance in remote sensing image building.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.