房屋模型面與空載影像之套合

Spatial Registration between Building Facets and Aerial Images

陳良健(Liang-Chien Chen) ； 江孟璁(Meng-Tsung Chiang)

《航測及遙測學刊》 14卷4期 (2009/12) Pp. 255-275

https://doi.org/10.6574/JPRS.2009.14(4).2

摘要

本研究利用傳統空照影像與傾斜攝影直升機影像，對現有房屋模型之牆面及屋頂面進行套合。處理重點除幾何對位外，並偵測牆面及屋頂面之遮蔽區，且對遮蔽區域以多視角影像及影像修補技術加以補償。牆面部分所使用之影像，是基於影像傾斜攝影概念。對欲處理之目標牆面，應以影像傾斜攝影角度最大為優先，如此可得到影像解析度較佳之牆面影像，但相對的，牆面被其他建築物遮蔽的情況也較嚴重；本研究的重點，即為於這些影像中，找到最佳化的組合。屋頂面部分，則以垂直攝影影像，可得解析度較佳之屋頂面，在此以真實正射之概念進行影像套合。成果顯示於套合幾何對位上滿足視覺化之要求。

關鍵字

空照影像 ； 房屋模型 ； 遮蔽區 ； 傾斜攝影 ； 影像套合

並列摘要

This research registers aerial photos and oblique helicopter images onto building facades. In which, building roofs and walls are to be treated. In addition to geometric registration, the proposed method detects hidden areas for roofs and walls, then compensates them with multi-view images and inpainting techniques. The wall images that we choose are based on oblique photography. For the target wall, we should select the largest oblique angle for the prior image in order to get better resolution. However, the occlusion problem by neighboring buildings is more serious. It is the major task of this study to select the optimal combination of images. For the roof, we use the vertical photos to obtain better resolution. The essence of the step is to register the roof surface with images. The results show high fidelity in visualization.

並列關鍵字

Aerial images ； Building models ； Occlusion detection ； Oblique photogrammetry ； Image registration