Exploring a combined multispectral multitemporal approach as an effective method to retrieve cloudless multispectral imagery

Colaninno, Nicola; Marambio, Alejandro; Roca, Josep

doi:10.1117/1.jrs.13.024505

Cited by 2 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The M2CTool, as experimented on Landsat imagery (Colaninno et al, 2019), relies on different steps. After data pre-processing, an algorithm is designed for masking clouds and cloud shadows.…”

Section: Methodsmentioning

confidence: 99%

“…Consequently, as indicated by Lymburner (2010), if clouds are present in a stack of multitemporal images, blue band pixel with values smaller than the mean of all pixels at the same point along the stack, is plausibly clouds-free. While, if shadows are present in a multitemporal stack, NIR band pixel greater than the mean less the standard deviation of all pixels at the same point along the stack, is reasonably shadows-free (Colaninno et al, 2019;Lymburner, 2010). Based on such an assumption, an algorithm for automatically masking clouds and cloud-shadows has been set up.…”

Section: The Masking Algorithmmentioning

confidence: 99%

“…Such an assumption allows identifying those pixels that are covered by clouds and cloud-shadows by comparing the covered pixels with same pixels at different time period. In other words, significant difference in terms of mean, and standard deviation, allow effectively identifying and masking clouds-and cloud-shadows contaminated pixels (Colaninno et al, 2019). The masking algorithm has been implemented as a script model in QGIS, setup on Sentinel-2 data, thus providing an automatic tool for masking clouds and cloud-shadow for optical imagery.…”

Section: The Masking Algorithmmentioning

confidence: 99%

“…Clouds, cloud shadows, and haze generally strongly contaminate optical remote-sensing images. Hence, for EO purposes, such contamination is intended as missing data and should be replaced or at least reduced (Colaninno, Marambio, & Roca, 2019). Different algorithms are available for automatically detect and mask clouds, and cloud shadows.…”

Section: Introductionmentioning

confidence: 99%

“…Then, cloudless (uncontaminated) optical satellite images is obtained based on a multitemporal stack along one scene. We tested the suitability of the multispectral multitemporal cloud-free tool (M2CTool), as suggested by Colaninno, Marambio, & Roca (2019), and previously explored for Landsat data, for different mid-resolution satellite information. Here the test is assessed for Sentinel-2 MSI derived imagery.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Testing a Combined Multispectral-Multitemporal Approach for Getting Cloudless Imagery for Sentinel-2

Colaninno

Marambio

Cladera

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Earth observation and land cover monitoring are among major applications for satellite data. However, the use of primary satellite information is often limited by clouds, cloud shadows, and haze, which generally contaminate optical imagery. For purposes of hazard assessment, for instance, such as flooding, drought, or seismic events, the availability of uncontaminated optical data is required. Different approaches exist for masking and replacing cloud/haze related contamination. However, most common algorithms take advantage by employing thermal data. Hence, we tested an algorithm suitable for optical imagery only. The approach combines a multispectral-multitemporal strategy to retrieve daytime cloudless and shadow-free imagery. While the approach has been explored for Landsat information, namely Landsat 5 TM and Landsat 8 OLI, here we aim at testing the suitability of the method for Sentinel-2 Multi-Spectral Instrument. A multitemporal stack, for the same image scene, is employed to retrieve a composite uncontaminated image over a temporal period of few months. Besides, in order to emphasize the effectiveness of optical imagery for monitoring post-disaster events, two temporal stages have been processed, before and after a critical seismic event occurred in Lombok Island, Indonesia, in summer 2018. The approach relies on a clouds and cloud shadows masking algorithm, based on spectral features, and a data reconstruction phase based on automatic selection of the most suitable pixels from a multitemporal stack. Results have been tested with uncontaminated image samples for the same scene. High accuracy is achieved.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: The Masking Algorithmmentioning

confidence: 99%

Section: The Masking Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Testing a Combined Multispectral-Multitemporal Approach for Getting Cloudless Imagery for Sentinel-2

Colaninno

Marambio

Cladera

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

Variational mode decomposition-enhanced thin cloud removal using UNet vision transformer cycle-consistent generative adversarial network

Baskar,

Parambalath,

Krishnanunni

2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Cloud cover is a persistent challenge in remote sensing imagery, hindering accurate interpretation and analysis. Existing research focuses on supervised approaches to removing clouds from satellite images. Due to the highly challenging task of acquiring paired data for the area of interest with and without obstructions, we propose an unsupervised approach for thin cloud removal using the latest image-to-image translation generative adversarial network (GAN) called the UNet vision transformer cycle-consistent GAN (UVCGAN), enhanced with variational mode decomposition (VMD). Thin cloud removal from satellite images is adopted as an image-to-image translation task in this approach. VMD is used to enhance the cloud-covered input image by retaining most of the image-specific features by reconstructing the enhanced image from modes that have the most image-specific features, quantitatively identified by modes with the highest entropy, contrast, and energy. The enhanced image is taken as input by the UVCGAN model to generate an image without thin clouds. The proposed methodology is compared against the latest methods, and quantitative evaluations indicate superior performances in terms of both full-and no-reference metrics, affirming the reliability and robustness of our approach.

show abstract

Exploring a combined multispectral multitemporal approach as an effective method to retrieve cloudless multispectral imagery

Cited by 2 publications

References 25 publications

Testing a Combined Multispectral-Multitemporal Approach for Getting Cloudless Imagery for Sentinel-2

Testing a Combined Multispectral-Multitemporal Approach for Getting Cloudless Imagery for Sentinel-2

Variational mode decomposition-enhanced thin cloud removal using UNet vision transformer cycle-consistent generative adversarial network

Contact Info

Product

Resources

About