A Cloud Detection Method Using Convolutional Neural Network Based on Gabor Transform and Attention Mechanism with Dark Channel Subnet for Remote Sensing Image

Jing Zhang,Hui Wang,Jun Wu,Yunsong Li,Yuchen Wang,Yuzhou Chai,Qin Zhou,Yang Liu

doi:10.3390/rs12193261

Jing Zhang, Hui Wang + Show 6 more

Open Access

https://doi.org/10.3390/rs12193261

Copy DOI

Abstract

Cloud detection, as a crucial step, has always been a hot topic in the field of optical remote sensing image processing. In this paper, we propose a deep learning cloud detection Network that is based on the Gabor transform and Attention modules with Dark channel subnet (NGAD). This network is based on the encoder-decoder framework. The information on texture is an important feature that is often used in traditional cloud detection methods. The NGAD enhances the attention of the network towards important texture features in the remote sensing images through the proposed Gabor feature extraction module. The channel attention module that is based on the larger scale features and spatial attention module that is based on the dark channel subnet have been introduced in NGAD. The channel attention module highlights the important information in a feature map from the channel dimensions, weakens the useless information, and helps the network to filter this information. A dark channel subnet with spatial attention module has been designed in order to further reduce the influence of the redundant information in the extracted features. By introducing a “dark channel”, the information in the feature map is reconstructed from the spatial dimension. The NGAD is validated while using the Gaofen-1 WFV imagery in four spectral bands. The experimental results show that the overall accuracy of NGAD reaches 97.42% and the false alarm rate reaches 2.22%. The efficiency of cloud detection using NGAD exceeds the state-of-art image segmentation network model and remote sensing image cloud detection model.

Highlights

With the rapid development of remote sensing satellite technology, satellite images are increasingly being used in daily lives
We have proposed a network for cloud detection in remote sensing images, based on Gabor transform and spatial and channel attention mechanism, named NGAD, which is built on the encoder-decoder structure
Inspired by the attention mechanism, we have introduced a spatial attention module that is based on Dark channel subnet and Channel attention module based on the higher-level features of the encoder to assist the decoder to enhance the key information, thereby improving the recognition ability of the decoder

Summary

Introduction

With the rapid development of remote sensing satellite technology, satellite images are increasingly being used in daily lives. An increasing amount of remote sensing data is being used in environmental protection, agricultural engineering, and others [1]. Cloud-covered areas will inevitably appear in remote sensing satellite images. Thick clouds sometimes cover the ground completely, and this affects the subsequent ground recognition and environmental monitoring. The ground features are not completely blocked, the ground features and the thin cloud information are mixed together, which results in blurred or missing ground feature information. This greatly reduces the quality of the remote sensing images and affects their subsequent recognition. Cloud detection is a hot topic in the preprocessing of remote sensing images

Methods

Results

Discussion

Conclusion