Cloud removal for remotely sensed images by similar pixel replacement guided with a spatio-temporal MRF model |
| |
| Institution: | 1. School of Resources and Environment, University of Electronic Science and Technology of China (UESTC), 2006 Xiyuan Avenue, West Hi-tech Zone, Chengdu, Sichuan 611731, China;2. Department of Geography, Planning, and Environment, East Carolina University, Greenville, NC 27858, USA;3. Institute of Remote Sensing Big Data, Big Data Research Center of UESTC, 2006 Xiyuan Avenue, West Hi-tech Zone, Chengdu, Sichuan 611731, China;1. Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong;2. International Institute of Tropical Forestry, USDA Forest Service, Río Piedras, Puerto Rico, 00926, USA;1. School of Resource and Environmental Sciences, Wuhan University, Wuhan, China;2. Collaborative Innovation Center for Geospatial Technology, Wuhan, China;3. Key Laboratory of Geographic Information System, Ministry of Education, Wuhan University, Wuhan, China;4. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China;5. Department of Electronics, University of Pavia, Pavia, Italy |
| |
| Abstract: | Cloud cover is generally present in remotely sensed images, which limits the potential of the images for ground information extraction. Therefore, removing the clouds and recovering the ground information for the cloud-contaminated images is often necessary in many applications. In this paper, an effective method based on similar pixel replacement is developed to solve this task. A missing pixel is filled using an appropriate similar pixel within the remaining region of the target image. A multitemporal image is used as the guidance to locate the similar pixels. A pixel-offset based spatio-temporal Markov random fields (MRF) global function is built to find the most suitable similar pixel. The proposed method was tested on MODIS and Landsat images and their land surface temperature products, and the experiments verify that the proposed method can achieve highly accurate results and is effective at dealing with the obvious atmospheric and seasonal differences between multitemporal images. |
| |
| Keywords: | Cloud removal Information reconstruction Spatio-temporal MRF Similar pixel replacement Multitemporal Remotely sensed image |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
