A Novel Method For Remote Sensing Image Cloud Detection

Cloud is one of the most common influences in remote sensing imagery. Because of cloud interference, much important and useful information covered by cloud cannot be recovered well. How to detect and remove cloud is an important issue for wide application of remote sensing data. A novel and effective method is proposed in this paper to detect cloud in remote sensing image using light transmittance. Light transmittance is employed to detect the cloud and also determine its corresponding thickness distribution. First, a cloud optical model is defined based on the airlight-albedo model. Second, preliminary cloud light transmittance is estimated using dark channel prior and then refine the result through guided filtering algorithm. Finally, we use light transmittance to detect cloud region by thresholding and obtain detailed information about the distribution of cloud thickness through mapping light transmittance of the cloud region into a gray image. Our method has been tested on real remote sensing images with clouds. Compared with the existing methods, experimental results have proved the better efficiency of our method in cloud detection.