2011-08-012024-05-13https://scholars.lib.ntu.edu.tw/handle/123456789/652587摘要：在利用光學式衛星影像進行土地利用判釋或農作物產量估測時，雲層覆蓋是無法避免的干擾之一。為降低雲層的影響並提升地物判釋的正確性，本研究以區域增長 (region growing) 之方式偵測並切除無法還原地物資訊的厚雲層，並以傅利葉 (Fourier) 分析建立薄雲模型，並以此模型薄雲並還原薄雲底下的地物光譜資訊。 以往研究的瓶頸在於多數去雲流程皆需要另外的無雲參考區域或是多時期影像，然而真實世界中，這些參考資訊可能難以取得；再者，對於去雲結果的優劣，通常是以質化而非量化的方式來進行視覺化評估，因此欠缺客觀性；最重要的是，去雲過程通常也會破壞原本的地物資訊，然而去雲後影像能否用來進行自動化地物判釋也欠缺探討。為解決以上瓶頸，本研究在厚雲層方面，以標準差延伸加強 (standard deviation stretch enhancement) 進行影像處理，再以區域增長進行偵測。薄雲方面，則以分析建立薄雲的數學模式，以此進行薄雲底下地物資訊還原。以上的去雲流程雖在模式建立階段仍需兩時期影像，但建立後的模式在對其它影像進行去雲處理時則僅需單時期資訊。而去雲結果的量化評估，厚雲方面以專家法評估偵測去除的範圍準確性，薄雲方面則以影像分類法評估雲下地物資訊還原的程度以及非雲下地物資訊的被破壞程度。本研究之成果預期可應用在土地利用判釋和農作物產量估測中的影像前處理程序，除能減少人工判釋和去除雲層的人力，也可增加衛星影像的利用度。 <br> Abstract: Cloud cover is an inevitable interference when mapping land use/cover with optical satellite imagery. In this study, we apply region growing processing to delineate unrecoverable thick cloud and use Fourier analysis to recover ground information from hazy areas. Several methodologies across literature successfully solve cloud problems, but most methods require additional cloud-free reference areas or imagery, which may be unavailable in the real world. Moreover, visual methods rather than quantitative methods are used for assessing results, which can be subjective and arbitrary. Most importantly, the feasibility of applying haze-off imagery to image classification is seldom discussed. To overcome the existing limits, this study revises the image enhancement and region growing algorithm to delineate unrecoverable thick cloud. For hazy areas, Fourier analysis is used to reduce haze interference and recover ground information. Both thick cloud and hazy areas processing can be achieved with no cloud-free area or reference imagery required. Concerning quantitative verification for results, expert method is applied to assess the thick cloud delineation and image classification is used to evaluate the recovery degree of ground information after the haze-off processing. Future applications include preprocessing of satellite imagery in land use/cover mapping, which can decrease the manpower to interpret and remove cloud areas and increase the usability of the satellite imagery.去雲地物判釋區域增長傅利葉分析Cloud RemovalLand Features InterpretationRegion GrowingFourier Analysis