文章基本信息

标题：IMAGE SELECTION FOR 3D MEASUREMENT BASED ON NETWORK DESIGN
本地全文：下载
作者：T. Fuse ; R. Harada
期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2015
卷号：XL-4/W5
页码：205-209
DOI：10.5194/isprsarchives-XL-4-W5-205-2015
出版社：Copernicus Publications
摘要：3D models have been widely used by spread of many available free-software. On the other hand, enormous images can be easily acquired, and images are utilized for creating the 3D models recently. However, the creation of 3D models by using huge amount of images takes a lot of time and effort, and then efficiency for 3D measurement are required. In the efficiency strategy, the accuracy of the measurement is also required. This paper develops an image selection method based on network design that means surveying network construction. The proposed method uses image connectivity graph. By this, the image selection problem is regarded as combinatorial optimization problem and the graph cuts technique can be applied. Additionally, in the process of 3D reconstruction, low quality images and similarity images are extracted and removed. Through the experiments, the significance of the proposed method is confirmed. Potential to efficient and accurate 3D measurement is implied
关键词：Image Selection; Bundle Adjustment; Network Design; Visualization; Graph cut