Robust Frequency-Based Structure Extraction

被引:3
|
作者
Kucner, Tomasz Piotr [1 ]
Luperto, Matteo [2 ]
Lowry, Stephanie [1 ]
Magnusson, Martin [1 ]
Lilienthal, Achim J. [1 ]
机构
[1] Orebro Univ, AASS Res Ctr, MRO Lab, Orebro, Sweden
[2] Univ Milan, Appl Intelligent Syst Lab AISLab, Milan, Italy
关键词
D O I
10.1109/ICRA48506.2021.9561381
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:1715 / 1721
页数:7
相关论文
共 50 条
  • [1] ROBUST FREQUENCY-BASED AUDIO FINGERPRINTING
    Dupraz, Elsa
    Richard, Gael
    2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 281 - 284
  • [2] Lane-mark Extraction by Frequency-based Saliency Visual Attention
    Le Ngo, Anh Cat
    Ang, Li-Minn
    Seng, Kah Phooi
    Qiu, Guoping
    PROCEEDINGS OF 2010 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, VOL 9 (ICCSIT 2010), 2010, : 55 - 59
  • [3] Aspect Extraction in Domain Lexicon Generation: A New Frequency-Based Approach
    Zayet, Tasnim M. A.
    Ismail, Maizatul Akmar
    Varathan, Kasturi Dewi
    IEEE ACCESS, 2024, 12 : 138972 - 138984
  • [4] Frequency-Based Robust Control for Micro Quadrotors Flying in Narrow Vertical Spaces
    Asignacion Jr, Abner
    Suzuki, Satoshi
    IEEE ACCESS, 2024, 12 : 141742 - 141751
  • [5] A Frequency-Based Stray Parameter Extraction Method Based on Oscillation in SiC MOSFET Dynamics
    Hu, Sideng
    Wang, Mingyang
    Liang, Zipeng
    He, Xiangning
    IEEE TRANSACTIONS ON POWER ELECTRONICS, 2021, 36 (06) : 6153 - 6157
  • [6] Robust Resonant Frequency-Based Contact Detection With Applications in Robotic Reaching and Grasping
    Backus, Spencer B.
    Dollar, Aaron M.
    IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2014, 19 (05) : 1552 - 1561
  • [7] Frequency-based environment matting
    Zhu, JY
    Yang, YH
    12TH PACIFIC CONFERENCE ON COMPUTER GRAPHICS AND APPLICATIONS, PROCEEDINGS, 2004, : 402 - 410
  • [8] Frequency changes in frequency-based damage identification
    Ralbovsky, Marian
    Deix, Stefan
    Flesch, Rainer
    STRUCTURE AND INFRASTRUCTURE ENGINEERING, 2010, 6 (05) : 611 - 619
  • [9] Improving aspect extraction by augmenting a frequency-based method with web-based similarity measures
    Li, Shi
    Zhou, Lina
    Li, Yijun
    INFORMATION PROCESSING & MANAGEMENT, 2015, 51 (01) : 58 - 67
  • [10] A frequency-based gene selection method to identify robust biomarkers for radiation dose prediction
    Boldt, Sonja
    Knops, Katja
    Kriehuber, Ralf
    Wolkenhauer, Olaf
    INTERNATIONAL JOURNAL OF RADIATION BIOLOGY, 2012, 88 (03) : 267 - 276