Abstrakt

Automatic robot inspections of sewer systems are progressively becoming more used for extending the lifetime of sewers and lowering the costs of maintenance. These automatic systems rely on machine learning and the acquisition of varied training data is therefore necessary. Capturing such data can be a costly and time consuming process. This paper proposes a system for generation and acquisition of synthetic training data from sewer systems. The system utilizes Structured Domain Randomization (SDR) for the generation of the sewer systems and an approximated model of a Pico Flexx Time-of-Flight camera for capturing depth and point cloud data from the generated sewer network. We evaluate the proposed system by comparing its output to ground truth data acquired from a Pico Flexx sensor in sewer pipes. We demonstrate that on average our system provides an absolute error of 5.78 ± 8.92 and 7.58 ± 8.68 mm, between data captured from real life and our proposed system, for two different scenarios. These results prove satisfactory for capturing training data. The code is publicly available at https://​bitbucket.​org/​aauvap/​syntheticsewerpi​pes/​src/​master/​.
OriginalsprogEngelsk
TitelAugmented Reality, Virtual Reality, and Computer Graphics : 7th International Conference, AVR 2017, Lecce, Italy, September 7-10, 2020, Proceedings, Part II
RedaktørerLucio Tommaso De Paolis, Patrick Bourdot
Antal sider10
Vol/bind12243
ForlagSpringer
Publikationsdato2020
Sider364-373
ISBN (Trykt)978-3-030-58467-2
ISBN (Elektronisk)978-3-030-58468-9
DOI
StatusUdgivet - 2020
Begivenhed7th International Conference on Augmented Reality, Virtual Reality and Computer Graphics, SALENTO AVR 2020 - Lecce, Italien
Varighed: 7 sep. 202010 sep. 2020

Konference

Konference7th International Conference on Augmented Reality, Virtual Reality and Computer Graphics, SALENTO AVR 2020
LandItalien
ByLecce
Periode07/09/202010/09/2020
NavnLecture Notes in Computer Science
Vol/bind12243 LNCS
ISSN0302-9743

Fingeraftryk Dyk ned i forskningsemnerne om 'Generating Synthetic Point Clouds of Sewer Networks: An Initial Investigation'. Sammen danner de et unikt fingeraftryk.

  • Projekter

    • 1 Igangværende

    ASIR: Automated Sewer Inspection Robot

    Moeslund, T. B., Haurum, J. B., Bahnsen, C. H. & Hansen, B. D.

    01/11/201830/04/2022

    Projekter: ProjektForskning

    Citationsformater

    Henriksen, K. S., Lynge, M. S., D.B.Jeppesen, M., Allahham, M. M. J., Nikolov, I. A., Haurum, J. B., & Moeslund, T. B. (2020). Generating Synthetic Point Clouds of Sewer Networks: An Initial Investigation. I L. T. De Paolis, & P. Bourdot (red.), Augmented Reality, Virtual Reality, and Computer Graphics: 7th International Conference, AVR 2017, Lecce, Italy, September 7-10, 2020, Proceedings, Part II (Bind 12243, s. 364-373). Springer. Lecture Notes in Computer Science Bind 12243 LNCS https://doi.org/10.1007/978-3-030-58468-9_26