An automated 3D reconstruction method of UAV images

Jun Liu; He Wang; Xiaoyang Liu; Feng Li; Guangtong Sun; Ping Song

doi:10.1117/12.2199631

8 October 2015 An automated 3D reconstruction method of UAV images

Jun Liu, He Wang, Xiaoyang Liu, Feng Li, Guangtong Sun, Ping Song

Proceedings Volume 9678, AOPC 2015: Telescope and Space Optical Instrumentation; 96780S (2015) https://doi.org/10.1117/12.2199631
Event: Applied Optics and Photonics China (AOPC2015), 2015, Beijing, China

Abstract

In this paper a novel fully automated 3D reconstruction approach based on low-altitude unmanned aerial vehicle system (UAVs) images will be presented, which does not require previous camera calibration or any other external prior knowledge. Dense 3D point clouds are generated by integrating orderly feature extraction, image matching, structure from motion (SfM) and multi-view stereo (MVS) algorithms, overcoming many of the cost, time limitations of rigorous photogrammetry techniques. An image topology analysis strategy is introduced to speed up large scene reconstruction by taking advantage of the flight-control data acquired by UAV. Image topology map can significantly reduce the running time of feature matching by limiting the combination of images. A high-resolution digital surface model of the study area is produced base on UAV point clouds by constructing the triangular irregular network. Experimental results show that the proposed approach is robust and feasible for automatic 3D reconstruction of low-altitude UAV images, and has great potential for the acquisition of spatial information at large scales mapping, especially suitable for rapid response and precise modelling in disaster emergency.

Citation Download Citation

Jun Liu, He Wang, Xiaoyang Liu, Feng Li, Guangtong Sun, and Ping Song "An automated 3D reconstruction method of UAV images", Proc. SPIE 9678, AOPC 2015: Telescope and Space Optical Instrumentation, 96780S (8 October 2015); https://doi.org/10.1117/12.2199631

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available