| Summary: | 碩士 === 國立成功大學 === 測量及空間資訊學系碩博士班 === 100 === Clouds in satellite images can be regarded as information for measuring cloud liquid water which is useful in meteorology and hydrology or regarded as contaminations that partially obstruct surface observation of landscapes. This study addresses the latter issue in which clouds obstruct land covers, thereby resulting in missing data for passive image sensors. Cloud covers are generally present in optical remote-sensing images, which limit the usage of images and increase difficulty of data analysis. Thus, information reconstruction of could-contaminated images generally plays an important step in preprocessing of image analysis. This study aims to propose a novel method to accurately and consistently reconstruct information of cloud-contaminated pixels in multitemporal remote-sensing images. Based on the concept of utilizing temporal correlation of multitemporal images, we propose a patch-based information reconstruction algorithm that spatiotemporally segments a sequence of images into several patches with similar temporal variation, and then clones information from cloud-free and high-similarity patches to their corresponding cloud-contaminated patches. In addition, a seam passing through homogenous regions is determined for a cloud-contaminated region in order to reduce radiometric inconsistency in information reconstruction. A cloud-contaminated region is segmented into several patches and their corresponding cloud-free patches are determined by a quality assessment index, and the multi-patch information cloning is solved by an optimization process with a determined seam. These processes enable the proposed method to accurately and consistently reconstruct missing information. Qualitative analyses on sequences of images acquired by the Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor and a quantitative analysis on a simulated data with various cloud contamination conditions are conducted to evaluate the proposed method. The experimental results show a clear superiority of our method, in terms of radiometric accuracy and consistency, over related methods, especially for large clouds in a heterogeneous landscape.
|
|---|
