Abstract
The advent of UAVs is considered a key factor in the photogrammetric reconstruction’s evolution. However, the volumes of data produced by this acquisition method have an impact on data processing time consumed by various software and workstations. In this respect, our project aims at optimizing and automating the process of 3D photogrammetric reconstruction from large UAV image datasets, using MicMac and cloud computing environment (AWS). Thus, a fast optimized automated pipeline was proposed for the extraction of the digital surface model (DSM) and the orthophotomosaïc.
Our approach is based on parallel processing on a cloud environment, and on optimizing the commands used for 3D reconstruction in MicMac. In fact, we have proposed a method for clustering the large UAV image dataset into clusters. Each one will be handled by the proposed pipeline using MicMac in a separate machine. For this optimization, we have mainly proposed to take into account algorithms for tie points reduction as well as the improvement of the relative orientation. Finally, we have proposed a method to merge the resulting clusters’ products, so as to produce the DSM and Orthophotomosaïc.
Running the proposed solution on 662 images and comparing it to Agisoft Photoscan’s results on 262 images, we have achieved approximately a decrease of 75% in favor of our proposed pipeline and the products (6 h 17 min against 10 h), DSM and Orthophotomosaïc, were derived with 1.9 m in planimetric accuracy (1.7 for Photoscan) and 3 m in vertical accuracy for both solutions.
The automation of this process was guaranteed by creating an operational flow of combined scripts implemented with Python, to reduce the human intervention in the process and to be able to execute the reconstruction in parallel on different machines in the cloud servers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Furukawa, Y., Hernández, C.: Multi-View Stereo: A Tutorial (2015)
Pierrot-Deseilligny, M.: Micmac documentation: MicMac, apero, pastis and other beverages in a nutshell (2019)
Humbert, S.: Modèle numérique de terrain par drone photogrammétrique sur le littoral de l'Île d'Oléron (2017)
MicMac ENSG Website. https://micmac.ensg.eu/. Accessed Feb 2020
AWS. https://aws.amazon.com/what-is-aws/. Accessed May 2020
AWS EC2. https://aws.amazon.com/ec2/. Accessed May 2020
Mordvintsev, A., Abid, K.: Opencv-python tutorials documentation (2014). https://media.readthedocs.org/pdf/opencv-python-tutroals/latest/opencv-python-tutroals.pdf
Martinez-Rubi, O., Nex, F., Pierrot-Deseilligny, M., Rupnik, E.: Improving FOSS photogrammetric workflows for processing large image datasets. Open Geospat. Data Softw. Stand. 2(1), 1–13 (2017). https://doi.org/10.1186/s40965-017-0024-5
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Barraz, Z., Lamhamdi, F.B., Sebari, I., Izem, A. (2022). Cloud Computing of Large UAV Datasets for 3D Photogrammetric Reconstruction. In: Arai, K. (eds) Proceedings of the Future Technologies Conference (FTC) 2021, Volume 1. FTC 2021. Lecture Notes in Networks and Systems, vol 358. Springer, Cham. https://doi.org/10.1007/978-3-030-89906-6_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-89906-6_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89905-9
Online ISBN: 978-3-030-89906-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)