TY - GEN
T1 - Robust Frequency-Based Structure Extraction
AU - Kucner, Tomasz Piotr
AU - Luperto, Matteo
AU - Lowry, Stephanie
AU - Magnusson, Martin
AU - Lilienthal, Achim J.
N1 - Funding Information:
Fig. 1. Example of structure scoring applied for clutter removal. The input map (top) contains structure elements as well as clutter. Our structure detection method identifies the 10 dominant directions in the map from the 20 symmetric peaks in the frequency spectrum. Then, each map cell is scored according to its agreement with a reconstructed structural map, brighter parts of the map have a higher structure score. The score can be automatically thresholded to extract the structural parts of the map (green in the bottom images), after which clutter can be removed. (The symbols are discussed in section III.) Tomasz Piotr Kucner, Stephanie Lowry, Martin Magnusson, Achim J. Lilienthal are with the MRO lab of the AASS research centre at Örebro University, Sweden. e-mail [email protected] Matteo Luperto is with the Applied Intelligent System lab (AISLab), Università degli Studi di Milano, Milano, Italy ([email protected]) This work has received funding from the European Union’s Horizon 2020 research and innovation programme under GA No 732737 (ILIAD). 1https://ifr.org/downloads/press2018/Presentation WR 2020.pdf
Funding Information:
This work has received funding from the European Union's Horizon 2020 research and innovation programme under GA No 732737 (ILIAD).
Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - State of the art mapping algorithms can produce high-quality maps. However, they are still vulnerable to clutter and outliers which can affect map quality and in consequence hinder the performance of a robot, and further map processing for semantic understanding of the environment. This paper presents ROSE, a method for building-level structure detection in robotic maps. ROSE exploits the fact that indoor environments usually contain walls and straight-line elements along a limited set of orientations. Therefore metric maps often have a set of dominant directions. ROSE extracts these directions and uses this information to segment the map into structure and clutter through filtering the map in the frequency domain (an approach substantially underutilised in the mapping applications). Removing the clutter in this way makes wall detection (e.g. using the Hough transform) more robust. Our experiments demonstrate that (1) the application of ROSE for decluttering can substantially improve structural feature retrieval (e.g., walls) in cluttered environments, (2) ROSE can successfully distinguish between clutter and structure in the map even with substantial amount of noise and (3) ROSE can numerically assess the amount of structure in the map.
AB - State of the art mapping algorithms can produce high-quality maps. However, they are still vulnerable to clutter and outliers which can affect map quality and in consequence hinder the performance of a robot, and further map processing for semantic understanding of the environment. This paper presents ROSE, a method for building-level structure detection in robotic maps. ROSE exploits the fact that indoor environments usually contain walls and straight-line elements along a limited set of orientations. Therefore metric maps often have a set of dominant directions. ROSE extracts these directions and uses this information to segment the map into structure and clutter through filtering the map in the frequency domain (an approach substantially underutilised in the mapping applications). Removing the clutter in this way makes wall detection (e.g. using the Hough transform) more robust. Our experiments demonstrate that (1) the application of ROSE for decluttering can substantially improve structural feature retrieval (e.g., walls) in cluttered environments, (2) ROSE can successfully distinguish between clutter and structure in the map even with substantial amount of noise and (3) ROSE can numerically assess the amount of structure in the map.
UR - http://www.scopus.com/inward/record.url?scp=85118997794&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9561381
DO - 10.1109/ICRA48506.2021.9561381
M3 - Conference article in proceedings
AN - SCOPUS:85118997794
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 1715
EP - 1721
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - IEEE
T2 - IEEE International Conference on Robotics and Automation
Y2 - 30 May 2021 through 5 June 2021
ER -