Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization
Natural landmarks are the main features in the next step of the research in localization of mobile robot platforms. The identification and recognition of these landmarks are crucial to better localize a robot. To help solving this problem, this work proposes an approach for the identification and re...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/17/8/1824 |
_version_ | 1811278180435099648 |
---|---|
author | Leonardo A. V. Souto André Castro Luiz Marcos Garcia Gonçalves Tiago P. Nascimento |
author_facet | Leonardo A. V. Souto André Castro Luiz Marcos Garcia Gonçalves Tiago P. Nascimento |
author_sort | Leonardo A. V. Souto |
collection | DOAJ |
description | Natural landmarks are the main features in the next step of the research in localization of mobile robot platforms. The identification and recognition of these landmarks are crucial to better localize a robot. To help solving this problem, this work proposes an approach for the identification and recognition of natural marks included in the environment using images from RGB-D (Red, Green, Blue, Depth) sensors. In the identification step, a structural analysis of the natural landmarks that are present in the environment is performed. The extraction of edge points of these landmarks is done using the 3D point cloud obtained from the RGB-D sensor. These edge points are smoothed through the S l 0 algorithm, which minimizes the standard deviation of the normals at each point. Then, the second step of the proposed algorithm begins, which is the proper recognition of the natural landmarks. This recognition step is done as a real-time algorithm that extracts the points referring to the filtered edges and determines to which structure they belong to in the current scenario: stairs or doors. Finally, the geometrical characteristics that are intrinsic to the doors and stairs are identified. The approach proposed here has been validated with real robot experiments. The performed tests verify the efficacy of our proposed approach. |
first_indexed | 2024-04-13T00:30:01Z |
format | Article |
id | doaj.art-79e57ea2e92e4707bd35e74367dffba8 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-13T00:30:01Z |
publishDate | 2017-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-79e57ea2e92e4707bd35e74367dffba82022-12-22T03:10:29ZengMDPI AGSensors1424-82202017-08-01178182410.3390/s17081824s17081824Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot LocalizationLeonardo A. V. Souto0André Castro1Luiz Marcos Garcia Gonçalves2Tiago P. Nascimento3Natalnet Labs, Universidade Federal do Rio Grande do Norte (UFRN), 59078-970 Natal, RN, BrazilLaSER-Embedded Systems and Robotics Lab, Universidade Federal da Paraiba (UFPB), 58058-600 João Pessoa, PB, BrazilNatalnet Labs, Universidade Federal do Rio Grande do Norte (UFRN), 59078-970 Natal, RN, BrazilLaSER-Embedded Systems and Robotics Lab, Universidade Federal da Paraiba (UFPB), 58058-600 João Pessoa, PB, BrazilNatural landmarks are the main features in the next step of the research in localization of mobile robot platforms. The identification and recognition of these landmarks are crucial to better localize a robot. To help solving this problem, this work proposes an approach for the identification and recognition of natural marks included in the environment using images from RGB-D (Red, Green, Blue, Depth) sensors. In the identification step, a structural analysis of the natural landmarks that are present in the environment is performed. The extraction of edge points of these landmarks is done using the 3D point cloud obtained from the RGB-D sensor. These edge points are smoothed through the S l 0 algorithm, which minimizes the standard deviation of the normals at each point. Then, the second step of the proposed algorithm begins, which is the proper recognition of the natural landmarks. This recognition step is done as a real-time algorithm that extracts the points referring to the filtered edges and determines to which structure they belong to in the current scenario: stairs or doors. Finally, the geometrical characteristics that are intrinsic to the doors and stairs are identified. The approach proposed here has been validated with real robot experiments. The performed tests verify the efficacy of our proposed approach.https://www.mdpi.com/1424-8220/17/8/1824natural landmarksRGB-D sensors3D edge-point cloudrobot localization |
spellingShingle | Leonardo A. V. Souto André Castro Luiz Marcos Garcia Gonçalves Tiago P. Nascimento Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization Sensors natural landmarks RGB-D sensors 3D edge-point cloud robot localization |
title | Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization |
title_full | Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization |
title_fullStr | Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization |
title_full_unstemmed | Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization |
title_short | Stairs and Doors Recognition as Natural Landmarks Based on Clouds of 3D Edge-Points from RGB-D Sensors for Mobile Robot Localization |
title_sort | stairs and doors recognition as natural landmarks based on clouds of 3d edge points from rgb d sensors for mobile robot localization |
topic | natural landmarks RGB-D sensors 3D edge-point cloud robot localization |
url | https://www.mdpi.com/1424-8220/17/8/1824 |
work_keys_str_mv | AT leonardoavsouto stairsanddoorsrecognitionasnaturallandmarksbasedoncloudsof3dedgepointsfromrgbdsensorsformobilerobotlocalization AT andrecastro stairsanddoorsrecognitionasnaturallandmarksbasedoncloudsof3dedgepointsfromrgbdsensorsformobilerobotlocalization AT luizmarcosgarciagoncalves stairsanddoorsrecognitionasnaturallandmarksbasedoncloudsof3dedgepointsfromrgbdsensorsformobilerobotlocalization AT tiagopnascimento stairsanddoorsrecognitionasnaturallandmarksbasedoncloudsof3dedgepointsfromrgbdsensorsformobilerobotlocalization |