2003-08-012024-05-18https://scholars.lib.ntu.edu.tw/handle/123456789/701185摘要：攝影測量之目的在於有效地測取三維空間資訊。在攝影測量流程中雖已發展高度自動化之方位求解的空中三角軟體，然而接續的物空間資訊萃取仍需要投入大量的人力。近十年來數值攝影測量借助於影像處理技術及電腦視覺之判識能力、自動化特徵物偵測及匹配技術的改良，許多於物、像空間可資利用的特徵實體，例如點、線、面之幾何資料，相當豐富。如何將這些多樣式、多維的特徵物引入自動化攝影測量作業中為本計劃研究之主旨。 本計劃為同一主題之第三階段工作，主要任務在於系統整合。從第一階段及正在進行的第二階段工作推展及初步成果顯示，利用現有物空間特徵物(例如GIS 資料庫中之向量資料、正射影像、數值地形模型等)及以影像處理及電腦視覺技術完成共軛特徵物之偵測及匹配並建立物、像空間對應影像特徵物實證上確能達到方位求解及物型重建之同步功效。基於以上初期成果，考量將各個子系統整合，建立一套以涵蓋物、像空間特徵物萃取、特徵物處理及特徵物三維重建之數值攝影測量求解系統。本系統之整合將有助於提升數值攝影測量在自動化空中三角系統效能的發揮以及即時性的物表重建任務。 <br> Abstract: The main task of photogrammetry is for efficiently measuring and collecting three-dimensional spatial information. As the revolution of technology has led to the success of highly automatic aerial-triangulation system solving for the exterior orientation on point-feature basis, making spatial information available still requires heavy labor effort by manually digitizing in a stereopsis afterwards. During the past decade, digital photogrammetry benefiting from integrating the technologies of image processing, computer vision, and digital data base provided in GISs has seen the easy and efficient way for detecting as well as utilizing versatile feature entities, including point, line and area ones both in image and object space, throughout the photogrammetric workflow. It is then interesting and challenging to think about how photogrammetry would take advantages of including such type of data sets into processing for advancing the goal of photogrammetric automation. The preliminary results of previous and on-going study shows that incorporated with features that are existed in GIS data base, including vector-map, orthoimages, and Digital Elevation Models, etc., the technologies of image processing and computer vision for automatic feature extraction and matching, the tasks of solving for orientation and object reconstruction would be performed in a quite efficient way satisfying automation to some degree. For continuing on this effort, this proposal - phase three, attempts in constituting a system inherited from the strength of photogrammetry as well as cleverly aided by the skills of image processing and computer vision for feature extraction and matching, and the versatile digital data sets in GIS for making a workable engine in automating orientation computation and object reconstruction.空間資訊特徵實體影像處理電腦視覺自動化空中三角系統Spatial informationFeature entitiesImage processingComputer visionAutomatic aerial-triangulation system