Efficient Structure from Motion on Large Scenes using UAV with Position and Pose Information

被引：0

作者：

Teng, Xichao ^{[1
]}

Yu, Qifeng ^{[1
]}

Shang, Yang ^{[1
]}

Luo, Jing ^{[1
]}

Wang, Gang ^{[1
]}

机构：

[1] Natl Univ Def Technol, Hunan Prov Key Lab Image Measurement & Vis Nav, Changsha, Hunan, Peoples R China

来源：

NINTH INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2017) | 2018年 / 10615卷

关键词：

image based reconstruction; pose information; unmanned aerial vehicle; projective transform; view selection; 3D;

D O I：

10.1117/12.2304782

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

In this paper, we exploit prior information from global positioning systems and inertial measurement units to speed up the process of large scene reconstruction from images acquired by Unmanned Aerial Vehicles. We utilize weak pose information and intrinsic parameter to obtain the projection matrix for each view. As compared to unmanned aerial vehicles' flight altitude, topographic relief can usually be ignored, we assume that the scene is flat and use weak perspective camera to get projective transformations between two views. Furthermore, we propose an overlap criterion and select potentially matching view pairs between projective transformed views. A robust global structure from motion method is used for image based reconstruction. Our real world experiments show that the approach is accurate, scalable and computationally efficient. Moreover, projective transformations between views can also be used to eliminate false matching.

引用

页数：8