DTHNet: Dual-Stream Network Based on Transformer and High-Resolution Representation for Shadow Extraction from Remote Sensing Imagery
- 28 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
Abstract
Shadow extraction from remote sensing images is critical work. However, the inter-class similarity of shadows with dark water, trees, and roads and the dependence on other objects make accurate shadow extraction still challenging. This letter proposes a dual-stream network based on the transformer and high-resolution representation (DTHNet) for multi-scale shadow extraction. The DTHNet utilizes two streams: the high-resolution representation stream extracts deep features while maintaining detail information, and the clustering representation stream provides clustering feature constraints to enhance the ability to distinguish between foreground and background. Additionally, the designed multi-scale auxiliary predictor and hybrid loss aid in extracting multi-scale shadows. We evaluated our proposed method on the AISD dataset and compared it against six state-of-the-art generic semantic segmentation models and shadow extraction methods. The experimental results demonstrate that the DTHNet outperforms the existing methods.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFC3005703)
- National Natural Science Foundation of China (41771451)
- Natural Science Foundation of Sichuan, China (2022NSFSC0409)
This publication has 20 references indexed in Scilit:
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Cast Shadow Detection to Quantify the Aerosol Optical Thickness for Atmospheric Correction of High Spatial Resolution Optical ImageryRemote Sensing, 2018
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Automatic Feature Learning for Robust Shadow Detection2014
- Shadow detection in very high spatial resolution aerial images: A comparative studyISPRS Journal of Photogrammetry and Remote Sensing, 2013
- Object-Based Shadow Extraction and Correction of High-Resolution Optical Satellite ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012
- Shadow detection: A survey and comparative evaluation of recent methodsPattern Recognition, 2012
- A shadow detection method for remote sensing images using VHR hyperspectral and LIDAR data2011
- Detection of vehicles in shadow areas2011