MRPFA-Net for Shadow Detection in Remote-Sensing Images
- 5 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-11
Abstract
The presence of shadows in high-resolution (HR) remote-sensing images reduces object detection accuracy. To address this problem, in this paper, we proposed a deep neural network algorithm for shadow detection by using the AISD and SSAD remote-sensing shadow image datasets. To improve the ability to extract spatial information from feature maps, we developed a cross-spatial attention module that focuses on semantic information in the horizontal and vertical directions at each position point on the remote-sensing image. This module overcomes the limitations of existing technologies in accurately judging small areas and suspected shadow areas and in missing or incorrectly detected shadow areas. In addition, to improve the ability to extract shadow features and the accuracy of shadow detection in remote-sensing images, we developed a channel attention module that assigns more attention to channels that conform to the shadow color characteristics. The network architecture comprises an encoder – decoder structure, with ResNeXt50 used as the backbone for the encoder and a multi resolution parallel fusion (MRPF) designed for the decoder; cross-spatial and channel attention were incorporated into the decoder unit. Experimental results demonstrated the superior performance of the proposed algorithm, with an F1 score of 92.6% for the shadow category on the test set, thus, outperforming other algorithms and making the proposed method an effective solution for shadow detection in HR remote-sensing images.Keywords
Funding Information
- Spark funding (HHJJ-2022-0101)
- General Project of Key Research and Development Plan of Shaanxi (2022GY-060)
- Wuhu and Xidian University Special Fund for Industry–University–Research Cooperation (XWYCXY012021019)
This publication has 38 references indexed in Scilit:
- A Review on Various Shadow Detection and Compensation Techniques in Remote Sensing ImagesCanadian Journal of Remote Sensing, 2017
- Extended Random Walker for Shadow Detection in Very High Resolution Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2017
- Leave-One-Out Kernel Optimization for Shadow Detection and RemovalIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imageryRemote Sensing of Environment, 2017
- Joint Model and Observation Cues for Single-Image Shadow DetectionRemote Sensing, 2016
- Deep Residual Learning for Image Recognition2016
- A novel water index for urban high-resolution eight-band WorldView-2 imageryInternational Journal of Digital Earth, 2016
- New spectrum ratio properties and features for shadow detectionPattern Recognition, 2016
- Fully convolutional networks for semantic segmentation2015
- A modified Gaussian mixture background model via spatiotemporal distribution with shadow detectionSignal, Image and Video Processing, 2015