DC 欄位 值 語言 DC.contributor 資訊工程學系 zh_TW DC.creator 洪梓為 zh_TW DC.creator Zi-Wei Hung en_US dc.date.accessioned 2023-7-27T07:39:07Z dc.date.available 2023-7-27T07:39:07Z dc.date.issued 2023 dc.identifier.uri http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=110522036 dc.contributor.department 資訊工程學系 zh_TW DC.description 國立中央大學 zh_TW DC.description National Central University en_US dc.description.abstract 研究土地利用有助於規劃和管理土地資源，傳統方式進行國土利用現況調查需要花費大量人力與時間成本來維護。本篇論文以區塊為單位，對台灣本島地區之 SPOT-7 衛星影像進行人工標註，收集台灣本島地區之建物道路、樹林、草地草原、農作物、水體、一般裸露地、農地裸露地七種類別的標註資料集。並應用地理物件影像分析 (GEOBIA) 的方法，將區塊化資料之影像直方圖(histogram image)作為資料輸入修改過之 ViT-B/16 模型，訓練一個基於自注意力機制 (self-attentioin) 的分類模型。本論文使用 2013 與 2021 兩年台灣本島地區的 SPOT-7 衛星影像，分別訓練兩個模型來預測各自的土地使用分類，並針對兩年的土地使用變遷進行研究與分析。 zh_TW dc.description.abstract Studying land use contributes to the planning and management of land resources. Traditional methods of conducting land use surveys require significant human and time resources for maintenance. In this paper, using the block as the unit, we manually labeled SPOT-7 satellite imagery of Taiwan, collecting labeled datasets for seven categories: buildings/roads, forests, grasslands, crops, water bodies, general bare land and agricultural bare land. By applying the method of Geographic Object-Based Image Analysis (GEOBIA), we used the histogram distribution of the block-level data as input to the modified ViT-B/16 model, which is based on self-attention mechanism, to train a classification model. Two models were trained using SPOT-7 satellite imagery of Taiwan for the years 2013 and 2021, respectively, to predict land use classifications for each year. The land use changes between the two years were studied and analyzed. en_US DC.subject 衛星影像 zh_TW DC.subject 深度學習 zh_TW DC.subject 自注意力機制 zh_TW DC.subject 分類模型 zh_TW DC.subject 土地利用 zh_TW DC.subject Satellite imagery en_US DC.subject Deep learning en_US DC.subject Self-attention mechanism en_US DC.subject Classification model en_US DC.subject Land use en_US DC.title 基於SPOT-7衛星影像之台灣土地使用分析 zh_TW dc.language.iso zh-TW zh-TW DC.title Land use analysis of Taiwan based on SPOT-7 satellite imagery en_US DC.type 博碩士論文 zh_TW DC.type thesis en_US DC.publisher National Central University en_US