Object-based cloud and cloud shadow detection in Landsat imagery

By Zhe Zhu, Curtis E. Woodcock. 2012

2,139 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/3971c7213dd5221de0cd9fb5e899f527f951dddf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Environmental Engineering

Citations in the corpus

Change detection using landsat time series: A review of frequencies, preprocessing, algorithms, and applications (2017, methodology): “Zhu and Woodcock (2012) and Zhu et al. (2015b) proposed a method called Fmask (Function of mask) to detect cloud, cloud shadow, and snow in Landsats 4–8 images based on the spectral and spatial information in the Landsat data.”
Exploring Google Earth Engine Platform for Big Data Processing: Classification of Multi-Temporal Satellite Imagery for Crop Mapping (2017, methodology): “Detection of clouds and shadows were done using Fmask algorithm (Zhu and Woodcock, 2012).”
Self-Attention for Raw Optical Satellite Time Series Classification (2019, methodology): “The FMask [28] algorithm itself is a functionally designed decision tree that exploits the physical properties of Landsat bands to identify cloud coverage and was later extended to more satellites [29].”
Current status of Landsat program, science, and applications (2019, methodology): “Besides utility for ET mapping, Landsat thermal imagery have been demonstrated to substantially improve cloud and shadow detection and mapping (Zhu and Woodcock, 2012; Zhu et al., 2015b).”
How Similar Are Forest Disturbance Maps Derived from Different Landsat Time Series Algorithms (2017, methodology): “ Accompanying each image was a LEDAPS‐derived cloud mask, and an additional cloud mask derived for each image with Fmask [27].”
Urban heat island impacts on plant phenology: intra-urban variability and response to land cover (2016, methodology): “Each image was atmospherically corrected using the LEDAPS toolchain (Masek et al 2006), cloud-masked using the FMASK utility (Zhu and Woodcock 2012), and clipped to the boundaries ofDaneCounty.”
Remote sensing for wetland classification: a comprehensive review (2018, background): “However, optical sensors provide poor information regarding the vegetation’s physical characteristics, such as morphology and height (Gallant 2015), and are hindered by the inability to penetrate through clouds (Zhu and Woodcock 2012; Amin et al. 2013; Amani and Mobasheri 2015).”
Interactions between urban vegetation and surface urban heat islands: a case study in the Boston metropolitan region (2016, methodology): “…numbers were converted to surface reflectance using the Landsat Ecosystem Disturbance Adaptive Processing System algorithm (Masek et al 2006), and observations contaminated by clouds, cloud shadows, and snow and ice were identified and removed using the Fmask algorithm (Zhu and Woodcock 2012).”
A cloud detection algorithm for satellite imagery based on deep learning (2019, methodology): “The optimal method is found to be the Fmask algorithm (Zhu and Woodcock, 2012; Zhu et al., 2015), which they then implement in the C programming language to obtain a 90% reduction in runtime.”
Continuous change detection and classification of land cover using all available Landsat data (2014, methodology): “For observations acquired after model initialization, only the Fmask algorithm is used. where, x Julian date ρ ( i , x ) Observed value for the ith Landsat Band at Julian date x. ^ ρ i ; x ð Þ RIRLS Predicted value for the ith Landsat Band at Julian date x based on RIRLS ﬁ tting (Eq.”