An Improved Fmask Algorithm In Tropical Regions For Landsat Images

Optical data plays an important role in various remote sensing applications. However, cloud and cloud shadow contamination reduce the availability of optical data, especially in tropical regions. Accurate identification of cloud and cloud shadow is an essential step in optical image preprocessing. The Function of Mask (FMASK) [1] is one of the most widely used cloud and cloud shadow detection methods. In view of the problems of some thin clouds and cloud shadows omission errors in tropical regions of FMASK, we develop an improved FMASK algorithm in tropical regions from the following two aspects: (1) Cloud detection: Firstly, the parameters and thresholds of FMASK are adjusted to generate the basic cloud layer; Secondly, the cloud index layer is calculated based on the bright features of clouds; Then, combining the temporal randomness and spectral characteristics of cloud, other bright objects are excluded and thin clouds are retained. (2) Cloud shadow detection: Firstly, the dark features of cloud shadows are mainly used to detect the basic cloud shadow layer; Secondly, combining the spectral and randomness characteristics of cloud shadow to avoid the interference of other dark objects. We randomly selected three experimental areas in tropical regions to verify the proposed algorithm developed in this paper. Through comparing and evaluating the accuracy of the clouds and cloud shadows mask generated based on the method in this paper with real samples drawn manually, the experiment results show that the average overall precision of clouds and cloud shadows mask generated based on the algorithm in this paper exceeding 80%. This improved FMASK algorithm improves the accuracy of clouds and cloud shadows detection in several tropical regions for Landsat images.