8 October 2015 An automated 3D reconstruction method of UAV images
Author Affiliations +
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
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.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jun Liu, Jun Liu, He Wang, He Wang, Xiaoyang Liu, Xiaoyang Liu, Feng Li, Feng Li, Guangtong Sun, Guangtong Sun, Ping Song, Ping Song, } "An automated 3D reconstruction method of UAV images", Proc. SPIE 9678, AOPC 2015: Telescope and Space Optical Instrumentation, 96780S (8 October 2015); doi: 10.1117/12.2199631; https://doi.org/10.1117/12.2199631

Back to Top