Position-Invariant Robust Features for Long-Term Recognition of Dynamic Outdoor Scenes

Aram KAWEWONG; Sirinart TANGRUAMSUB; Osamu HASEGAWA

doi:10.1587/transinf.E93.D.2587

Position-Invariant Robust Features for Long-Term Recognition of Dynamic Outdoor Scenes

Aram KAWEWONG, Sirinart TANGRUAMSUB, Osamu HASEGAWA

Full Text Views

0

Cite this

Summary :

A novel Position-Invariant Robust Feature, designated as PIRF, is presented to address the problem of highly dynamic scene recognition. The PIRF is obtained by identifying existing local features (i.e. SIFT) that have a wide baseline visibility within a place (one place contains more than one sequential images). These wide-baseline visible features are then represented as a single PIRF, which is computed as an average of all descriptors associated with the PIRF. Particularly, PIRFs are robust against highly dynamical changes in scene: a single PIRF can be matched correctly against many features from many dynamical images. This paper also describes an approach to using these features for scene recognition. Recognition proceeds by matching an individual PIRF to a set of features from test images, with subsequent majority voting to identify a place with the highest matched PIRF. The PIRF system is trained and tested on 2000+ outdoor omnidirectional images and on COLD datasets. Despite its simplicity, PIRF offers a markedly better rate of recognition for dynamic outdoor scenes (ca. 90%) than the use of other features. Additionally, a robot navigation system based on PIRF (PIRF-Nav) can outperform other incremental topological mapping methods in terms of time (70% less) and memory. The number of PIRFs can be reduced further to reduce the time while retaining high accuracy, which makes it suitable for long-term recognition and localization.

Publication: IEICE TRANSACTIONS on Information Vol.E93-D No.9 pp.2587-2601

Publication Date: 2010/09/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E93.D.2587

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Cite this

Copy

Aram KAWEWONG, Sirinart TANGRUAMSUB, Osamu HASEGAWA, "Position-Invariant Robust Features for Long-Term Recognition of Dynamic Outdoor Scenes" in IEICE TRANSACTIONS on Information, vol. E93-D, no. 9, pp. 2587-2601, September 2010, doi: 10.1587/transinf.E93.D.2587.
Abstract: A novel Position-Invariant Robust Feature, designated as PIRF, is presented to address the problem of highly dynamic scene recognition. The PIRF is obtained by identifying existing local features (i.e. SIFT) that have a wide baseline visibility within a place (one place contains more than one sequential images). These wide-baseline visible features are then represented as a single PIRF, which is computed as an average of all descriptors associated with the PIRF. Particularly, PIRFs are robust against highly dynamical changes in scene: a single PIRF can be matched correctly against many features from many dynamical images. This paper also describes an approach to using these features for scene recognition. Recognition proceeds by matching an individual PIRF to a set of features from test images, with subsequent majority voting to identify a place with the highest matched PIRF. The PIRF system is trained and tested on 2000+ outdoor omnidirectional images and on COLD datasets. Despite its simplicity, PIRF offers a markedly better rate of recognition for dynamic outdoor scenes (ca. 90%) than the use of other features. Additionally, a robot navigation system based on PIRF (PIRF-Nav) can outperform other incremental topological mapping methods in terms of time (70% less) and memory. The number of PIRFs can be reduced further to reduce the time while retaining high accuracy, which makes it suitable for long-term recognition and localization.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2587/_p

Copy

@ARTICLE{e93-d_9_2587,
author={Aram KAWEWONG, Sirinart TANGRUAMSUB, Osamu HASEGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Position-Invariant Robust Features for Long-Term Recognition of Dynamic Outdoor Scenes},
year={2010},
volume={E93-D},
number={9},
pages={2587-2601},
abstract={A novel Position-Invariant Robust Feature, designated as PIRF, is presented to address the problem of highly dynamic scene recognition. The PIRF is obtained by identifying existing local features (i.e. SIFT) that have a wide baseline visibility within a place (one place contains more than one sequential images). These wide-baseline visible features are then represented as a single PIRF, which is computed as an average of all descriptors associated with the PIRF. Particularly, PIRFs are robust against highly dynamical changes in scene: a single PIRF can be matched correctly against many features from many dynamical images. This paper also describes an approach to using these features for scene recognition. Recognition proceeds by matching an individual PIRF to a set of features from test images, with subsequent majority voting to identify a place with the highest matched PIRF. The PIRF system is trained and tested on 2000+ outdoor omnidirectional images and on COLD datasets. Despite its simplicity, PIRF offers a markedly better rate of recognition for dynamic outdoor scenes (ca. 90%) than the use of other features. Additionally, a robot navigation system based on PIRF (PIRF-Nav) can outperform other incremental topological mapping methods in terms of time (70% less) and memory. The number of PIRFs can be reduced further to reduce the time while retaining high accuracy, which makes it suitable for long-term recognition and localization.},
keywords={},
doi={10.1587/transinf.E93.D.2587},
ISSN={1745-1361},
month={September},}

Copy

TY - JOUR
TI - Position-Invariant Robust Features for Long-Term Recognition of Dynamic Outdoor Scenes
T2 - IEICE TRANSACTIONS on Information
SP - 2587
EP - 2601
AU - Aram KAWEWONG
AU - Sirinart TANGRUAMSUB
AU - Osamu HASEGAWA
PY - 2010
DO - 10.1587/transinf.E93.D.2587
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2010
AB - A novel Position-Invariant Robust Feature, designated as PIRF, is presented to address the problem of highly dynamic scene recognition. The PIRF is obtained by identifying existing local features (i.e. SIFT) that have a wide baseline visibility within a place (one place contains more than one sequential images). These wide-baseline visible features are then represented as a single PIRF, which is computed as an average of all descriptors associated with the PIRF. Particularly, PIRFs are robust against highly dynamical changes in scene: a single PIRF can be matched correctly against many features from many dynamical images. This paper also describes an approach to using these features for scene recognition. Recognition proceeds by matching an individual PIRF to a set of features from test images, with subsequent majority voting to identify a place with the highest matched PIRF. The PIRF system is trained and tested on 2000+ outdoor omnidirectional images and on COLD datasets. Despite its simplicity, PIRF offers a markedly better rate of recognition for dynamic outdoor scenes (ca. 90%) than the use of other features. Additionally, a robot navigation system based on PIRF (PIRF-Nav) can outperform other incremental topological mapping methods in terms of time (70% less) and memory. The number of PIRFs can be reduced further to reduce the time while retaining high accuracy, which makes it suitable for long-term recognition and localization.
ER -