Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points

Salvador Pacheco-Gutierrez; Alexandru Stancu; Mohamed Mustafa; Eduard Codres; Bogdan Codres

doi:10.1109/ICSTCC.2015.7321318

Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points

Salvador Pacheco-Gutierrez, Alexandru Stancu, Mohamed Mustafa, Eduard Codres, Bogdan Codres

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

396 Downloads (Pure)

Abstract

This article presents a novel systematic methodologyfor the detection of interest points in 3D point clouds and itscorresponding descriptors by using the information of an RGBcamera and a structured-light sensor. This is achieved by fusingSpeeded-Up Robust Features (SURF) in the image space, andhistograms that statistically represent the relationship of threedimensional geometric data around the interest points. The SURFalgorithm is implemented over an image whose pixel coordinateshave a direct corresponding 3D point, thus allowing the fusion ofboth approaches. By combining both methodologies, it is intentto define a set of interest points whose descriptors are able tomaintain the intrinsic characteristics of its constituent parts suchas repeatability, distinctiveness and robustness while remainingcompact and fast to compute. The detected points will be usefor both, localization and mapping of mobile robots in partiallyunknown environments.

Original language	English
Title of host publication	System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on
Place of Publication	Romania
Publisher	IEEE
Pages	348-353
Number of pages	6
DOIs	https://doi.org/10.1109/ICSTCC.2015.7321318
Publication status	Published - Oct 2015
Event	System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on - Cheile Gradistei, Romania Duration: 14 Oct 2015 → 16 Oct 2015

Conference

Conference	System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on
City	Cheile Gradistei, Romania
Period	14/10/15 → 16/10/15

Keywords

Computer vision; Robotics; Landmark Detection and Characterization; SLAM.

Access to Document

10.1109/ICSTCC.2015.7321318

FULL-TEXT

Cite this

@inproceedings{a54013dbdebb404bbf2f9aa6fb2b61bc,

title = "Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points",

abstract = "This article presents a novel systematic methodologyfor the detection of interest points in 3D point clouds and itscorresponding descriptors by using the information of an RGBcamera and a structured-light sensor. This is achieved by fusingSpeeded-Up Robust Features (SURF) in the image space, andhistograms that statistically represent the relationship of threedimensional geometric data around the interest points. The SURFalgorithm is implemented over an image whose pixel coordinateshave a direct corresponding 3D point, thus allowing the fusion ofboth approaches. By combining both methodologies, it is intentto define a set of interest points whose descriptors are able tomaintain the intrinsic characteristics of its constituent parts suchas repeatability, distinctiveness and robustness while remainingcompact and fast to compute. The detected points will be usefor both, localization and mapping of mobile robots in partiallyunknown environments.",

keywords = "Computer vision; Robotics; Landmark Detection and Characterization; SLAM.",

author = "Salvador Pacheco-Gutierrez and Alexandru Stancu and Mohamed Mustafa and Eduard Codres and Bogdan Codres",

year = "2015",

month = oct,

doi = "10.1109/ICSTCC.2015.7321318",

language = "English",

pages = "348--353",

booktitle = "System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on",

publisher = "IEEE",

address = "United States",

note = "System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on ; Conference date: 14-10-2015 Through 16-10-2015",

}

Pacheco-Gutierrez, S, Stancu, A, Mustafa, M, Codres, E & Codres, B 2015, Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points. in System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on. IEEE, Romania, pp. 348-353, System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on, Cheile Gradistei, Romania, 14/10/15. https://doi.org/10.1109/ICSTCC.2015.7321318

Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points. / Pacheco-Gutierrez, Salvador; Stancu, Alexandru; Mustafa, Mohamed et al.
System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on. Romania: IEEE, 2015. p. 348-353.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points

AU - Pacheco-Gutierrez, Salvador

AU - Stancu, Alexandru

AU - Mustafa, Mohamed

AU - Codres, Eduard

AU - Codres, Bogdan

PY - 2015/10

Y1 - 2015/10

N2 - This article presents a novel systematic methodologyfor the detection of interest points in 3D point clouds and itscorresponding descriptors by using the information of an RGBcamera and a structured-light sensor. This is achieved by fusingSpeeded-Up Robust Features (SURF) in the image space, andhistograms that statistically represent the relationship of threedimensional geometric data around the interest points. The SURFalgorithm is implemented over an image whose pixel coordinateshave a direct corresponding 3D point, thus allowing the fusion ofboth approaches. By combining both methodologies, it is intentto define a set of interest points whose descriptors are able tomaintain the intrinsic characteristics of its constituent parts suchas repeatability, distinctiveness and robustness while remainingcompact and fast to compute. The detected points will be usefor both, localization and mapping of mobile robots in partiallyunknown environments.

AB - This article presents a novel systematic methodologyfor the detection of interest points in 3D point clouds and itscorresponding descriptors by using the information of an RGBcamera and a structured-light sensor. This is achieved by fusingSpeeded-Up Robust Features (SURF) in the image space, andhistograms that statistically represent the relationship of threedimensional geometric data around the interest points. The SURFalgorithm is implemented over an image whose pixel coordinateshave a direct corresponding 3D point, thus allowing the fusion ofboth approaches. By combining both methodologies, it is intentto define a set of interest points whose descriptors are able tomaintain the intrinsic characteristics of its constituent parts suchas repeatability, distinctiveness and robustness while remainingcompact and fast to compute. The detected points will be usefor both, localization and mapping of mobile robots in partiallyunknown environments.

KW - Computer vision; Robotics; Landmark Detection and Characterization; SLAM.

U2 - 10.1109/ICSTCC.2015.7321318

DO - 10.1109/ICSTCC.2015.7321318

M3 - Conference contribution

SP - 348

EP - 353

BT - System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on

PB - IEEE

CY - Romania

T2 - System Theory, Control and Computing (ICSTCC), 2015 19th International Conference on

Y2 - 14 October 2015 through 16 October 2015

ER -

Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this