Thin Cloud Removal for Multispectral Remote Sensing Images Using Convolutional Neural Networks Combined With an Imaging Model

Zi, Yue; Xie, Fengying; Zhang, Ning; Jiang, Zhiguo; Zhu, Wentao; Zhang, Haopeng

doi:10.1109/jstars.2021.3068166

Cited by 41 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with thick cloud removal, thin cloud removal methods usually focus on suppressing the cloud influence instead of replacing the cloudy pixels. Therefore the thin cloud removal methods based on CNN can directly obtain the cloud-free images from the cloudcover images without additional auxiliary data [22], [23]. In addition, because different wavelengths of the spectrum are affected differently by clouds, the spectral-based method is also promising for thin clouds removal.…”

Section: A Convolutional Neural Network For Cloud Removalmentioning

confidence: 99%

Cloud Removal Based on SAR-Optical Remote Sensing Data Fusion via a Two-Flow Network

Mao

Yin

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Optical remote sensing imagery plays an important role in observing the Earth's surface today. However, it is not easy to obtain complete multi-temporal optical remote sensing images because of the cloud cover, how reconstructing cloudfree optical images has become a big challenge task in recent years. Inspired by the remote sensing fusion methods based on the convolutional neural network model, we propose a twoflow network to remove clouds from optical images. And in the proposed method, synthetic aperture radar (SAR) images are used as auxiliary data to guide optical image reconstruction, which is not influenced by cloud cover. Additionally, a novel loss function called content loss is introduced to improve image quality. The ablation experiment of the loss function also proves that content loss is indeed effective. To more in line with real situation, the network is trained, tested and validated on the SEN12MS-CR dataset, which is a global real cloud-removal dataset. The experimental results show that the proposed method is better than other the-state-of-art (SOTA) methods in many indicators (RMSE, SSIM, SAM, PSNR).

show abstract

Section: A Convolutional Neural Network For Cloud Removalmentioning

confidence: 99%

Cloud Removal Based on SAR-Optical Remote Sensing Data Fusion via a Two-Flow Network

Mao

Yin

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The network proposed by Yang [16] contains three generators: the generator for the cloudless image, the generator for the atmospheric light, and the generator for transmission map. Zi [17] proposed a method to remove thin cloud from multispectral images, which combines the traditional method with the deep learning method. Firstly, Convolution Neural Network is used to estimate the thickness of thin cloud in different bands.…”

Section: Deep Learning-generative Adversarial Networkmentioning

confidence: 99%

Algorithm Development of Cloud Removal from Solar Images Based on Pix2Pix Network

Wu¹,

Song²,

Zhang³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Sky clouds affect solar observations significantly. Their shadows obscure the details of solar features in observed images. Cloud-covered solar images are difficult to be used for further research without pre-processing. In this paper, the solar image cloud removing problem is converted to an image-to-image translation problem, with a used algorithm of the Pixel to Pixel Network (Pix2Pix), which generates a cloudless solar image without relying on the physical scattering model. Pix2Pix is consists of a generator and a discriminator. The generator is a well-designed U-Net. The discriminator uses PatchGAN structure to improve the details of the generated solar image, which guides the generator to create a pseudo realistic solar image. The image generation model and the training process are optimized, and the generator is jointly trained with the discriminator. So the generation model which can stably generate cloudless solar image is obtained. Extensive experiment results on Huairou Solar Observing Station, National Astronomical Observatories, and Chinese Academy of Sciences (HSOS, NAOC and CAS) datasets show that Pix2Pix is superior to the traditional methods based on physical prior knowledge in peak signal-to-noise ratio, structural similarity, perceptual index, and subjective visual effect. The result of the PSNR, SSIM and PI are 27.2121 dB, 0.8601 and 3.3341.

show abstract

“…Since 66-70% of the surface of the Earth is cloudcovered at any given time [28,32], dealing with clouds in EO data is essential. Two major goals are: • Cloud detection, where typically the location and extent cloud coverage in a data cube is estimated; • Cloud removal [34,45,66], where the values in the spatial locations occluded by clouds are restored. Since our work relates to the former category, the rest of this subsection is devoted to cloud detection.…”

Section: Cloud Detection In Eo Datamentioning

confidence: 99%

“…Dealing with cloud cover is part-and-parcel of practical EO processing pipelines [33,42,50,58,63]. Cloud mitigation strategies include segmenting and masking out the portion of the data that is affected by clouds [24,26], and restoring the cloud-affected regions [34,45,66] as a form of data enhancement. Increasingly, deep learning forms the basis of the cloud mitigation routines [9,33,56,60].…”

Section: Introductionmentioning

confidence: 99%

Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector

Du¹,

Law²,

Sasdelli³

et al. 2021

Preprint

View full text Add to dashboard Cite

Data collected by Earth-observing (EO) satellites are often afflicted by cloud cover. Detecting the presence of clouds-which is increasingly done using deep learning-is crucial preprocessing in EO applications. In fact, advanced EO satellites perform deep learning-based cloud detection on board the satellites and downlink only clear-sky data to save precious bandwidth. In this paper, we highlight the vulnerability of deep learning-based cloud detection towards adversarial attacks. By optimising an adversarial pattern and superimposing it into a cloudless scene, we bias the neural network into detecting clouds in the scene. Since the input spectra of cloud detectors include the nonvisible bands, we generated our attacks in the multispectral domain. This opens up the potential of multi-objective attacks, specifically, adversarial biasing in the cloud-sensitive bands and visual camouflage in the visible bands. We also investigated mitigation strategies against the adversarial attacks. We hope our work further builds awareness of the potential of adversarial attacks in the EO community.

show abstract

Thin Cloud Removal for Multispectral Remote Sensing Images Using Convolutional Neural Networks Combined With an Imaging Model

Cited by 41 publications

References 26 publications

Cloud Removal Based on SAR-Optical Remote Sensing Data Fusion via a Two-Flow Network

Cloud Removal Based on SAR-Optical Remote Sensing Data Fusion via a Two-Flow Network

Algorithm Development of Cloud Removal from Solar Images Based on Pix2Pix Network

Adversarial Attacks against a Satellite-borne Multispectral Cloud Detector

Contact Info

Product

Resources

About