An Improved Cloud Detection Method for GF-4 Imagery

Ming Lu,Huachao Xiao,Bangcheng Zhan,Xiaotian Lu,Feng Li,He Li,Xue Yang

doi:10.3390/rs12091525

Abstract

Clouds are significant barriers to the application of optical remote sensing images. Accurate cloud detection can help to remove contaminated pixels and improve image quality. Many cloud detection methods have been developed. However, traditional methods either rely heavily on thermal infrared bands or clear-sky images. When traditional cloud detection methods are used with Gaofen 4 (GF-4) imagery, it is very difficult to separate objects with similar spectra, such as ice, snow, and bright sand, from clouds. In this paper, we propose a new method, named Real-Time-Difference (RTD), to detect clouds using a pair of images obtained by the GF-4 satellite. The RTD method has four main steps: (1) data preprocessing, including transforming digital value (DN) to Top of Atmosphere (TOA) reflectance, and orthographic and geometric correction; (2) the computation of a series of cloud indexes for a single image to highlight clouds; (3) the calculation of the difference between a pair of real-time images in order to obtain moved clouds; and (4) confirming the clouds and background by analyzing their physical and dynamic features. The RTD method was validated in three sites located in the Hainan, Liaoning, and Xinjiang areas of China. The results were compared with those of a popular classifier, Support Vector Machine (SVM). The results showed that RTD outperformed SVM; for the Hainan, Liaoning, and Xinjiang areas, respectively, the overall accuracy of RTD reached 95.9%, 94.1%, and 93.9%, and its Kappa coefficient reached 0.92, 0.88, and 0.88. In the future, we expect RTD to be developed into an important means for the rapid detection of clouds that can be used on images from geostationary orbit satellites.

Highlights

The Gaofen 4 (GF-4) satellite was launched on 29 December 2015 and is the first Chinese optical remote sensing satellite in geostationary orbit that was designed for civil use [1]
The Hainan area was first used to demonstrate the effect of the cloud detection ability of the RTD method
Some dikes around the coastline and some buildings were wrongly classified as clouds by the Support Vector Machine (SVM) method, since they are very bright and have similar spectral features to clouds in the visible and NIR bands

Summary

Introduction

The Gaofen 4 (GF-4) satellite (gaofen is the Chinese for “high resolution”) was launched on 29 December 2015 and is the first Chinese optical remote sensing satellite in geostationary orbit that was designed for civil use [1]. A panchromatic multispectral sensor (PMS) and an infrared sensor (IRS) are on board the GF-4 satellite. An individual GF-4 scene can cover an area of 400 km × 400 km, with a spatial resolution of about 50 m and 400 m for the PMS and IRS, respectively [2]. GF-4 was designed to operate in gazing image mode, and the revisit period can reach 20 s [3]. GF-4 can obtain a series of time-continuous images over the same area, which provides an ideal observation approach for the detection of changing and moving targets. Many applications have been performed based on GF-4 imagery, such as radiometric cross-calibration [6], the acquisition of super-resolution images [2], ship tracking [7], and the recognition of residential areas [8]

Methods

Results

Discussion

Conclusion