Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM

Yong Ju Lee, Jae-Bok Song

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For successful SLAM, perception of the environment is important. This paper proposes a scheme to autonomously detect features which are used as natural landmarks for indoor SLAM. Features are roughly selected by using entropy maps which measure the level of randomness of information. The selected features are evaluated by the saliency map based on similarity maps which measure the level of similarity between the selected features and the given image. In the saliency map, it is possible to distinguish the salient features from the background. In this research, the HSV color space is adopted for color representation instead of the RGB space. The robot estimates its pose using the detected features and builds a grid map of the unknown environment using a range sensor. The feature positions are stored in the grid map. Experimental results show that the feature detection proposed in this paper can autonomously detect features in unknown environments reasonably well.

Original languageEnglish
Title of host publicationICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings
Pages171-176
Number of pages6
Publication statusPublished - 2009 Dec 1
EventICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009 - Fukuoka, Japan
Duration: 2009 Aug 182009 Aug 21

Other

OtherICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009
CountryJapan
CityFukuoka
Period09/8/1809/8/21

Fingerprint

Color
Entropy
Robots
Sensors

ASJC Scopus subject areas

  • Information Systems
  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering

Cite this

Lee, Y. J., & Song, J-B. (2009). Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM. In ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings (pp. 171-176). [5333391]

Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM. / Lee, Yong Ju; Song, Jae-Bok.

ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings. 2009. p. 171-176 5333391.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, YJ & Song, J-B 2009, Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM. in ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings., 5333391, pp. 171-176, ICROS-SICE International Joint Conference 2009, ICCAS-SICE 2009, Fukuoka, Japan, 09/8/18.
Lee YJ, Song J-B. Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM. In ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings. 2009. p. 171-176. 5333391
Lee, Yong Ju ; Song, Jae-Bok. / Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM. ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings. 2009. pp. 171-176
@inproceedings{4e2a5797ae484211a270e978df824ff5,
title = "Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM",
abstract = "For successful SLAM, perception of the environment is important. This paper proposes a scheme to autonomously detect features which are used as natural landmarks for indoor SLAM. Features are roughly selected by using entropy maps which measure the level of randomness of information. The selected features are evaluated by the saliency map based on similarity maps which measure the level of similarity between the selected features and the given image. In the saliency map, it is possible to distinguish the salient features from the background. In this research, the HSV color space is adopted for color representation instead of the RGB space. The robot estimates its pose using the detected features and builds a grid map of the unknown environment using a range sensor. The feature positions are stored in the grid map. Experimental results show that the feature detection proposed in this paper can autonomously detect features in unknown environments reasonably well.",
author = "Lee, {Yong Ju} and Jae-Bok Song",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9784907764333",
pages = "171--176",
booktitle = "ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings",

}

TY - GEN

T1 - Autonomous detection and recognition of salient features using generation of saliency map for indoor visual SLAM

AU - Lee, Yong Ju

AU - Song, Jae-Bok

PY - 2009/12/1

Y1 - 2009/12/1

N2 - For successful SLAM, perception of the environment is important. This paper proposes a scheme to autonomously detect features which are used as natural landmarks for indoor SLAM. Features are roughly selected by using entropy maps which measure the level of randomness of information. The selected features are evaluated by the saliency map based on similarity maps which measure the level of similarity between the selected features and the given image. In the saliency map, it is possible to distinguish the salient features from the background. In this research, the HSV color space is adopted for color representation instead of the RGB space. The robot estimates its pose using the detected features and builds a grid map of the unknown environment using a range sensor. The feature positions are stored in the grid map. Experimental results show that the feature detection proposed in this paper can autonomously detect features in unknown environments reasonably well.

AB - For successful SLAM, perception of the environment is important. This paper proposes a scheme to autonomously detect features which are used as natural landmarks for indoor SLAM. Features are roughly selected by using entropy maps which measure the level of randomness of information. The selected features are evaluated by the saliency map based on similarity maps which measure the level of similarity between the selected features and the given image. In the saliency map, it is possible to distinguish the salient features from the background. In this research, the HSV color space is adopted for color representation instead of the RGB space. The robot estimates its pose using the detected features and builds a grid map of the unknown environment using a range sensor. The feature positions are stored in the grid map. Experimental results show that the feature detection proposed in this paper can autonomously detect features in unknown environments reasonably well.

UR - http://www.scopus.com/inward/record.url?scp=77951112568&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951112568&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77951112568

SN - 9784907764333

SP - 171

EP - 176

BT - ICCAS-SICE 2009 - ICROS-SICE International Joint Conference 2009, Proceedings

ER -