Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling

T. Nicosevici, R. Garcia, Shahriar Negahdaripour, M. Kudzinava, J. Ferrer

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

5 Citations (Scopus)

Abstract

Many applications in mobile and underwater robotics employ 3D vision techniques for navigation and mapping. These techniques usually involve the extraction and 3D reconstruction of scene interest points. Nevertheless, in large environments the huge volume of acquired information could pose serious problems to real-time data processing. Moreover, In order to minimize the drift, these techniques use data association to close trajectory loops, decreasing the uncertainties in estimating the position of the robot and increasing the precision of the resulting 3D models. When faced to large amounts of features, the efficiency of data association decreases drastically, affecting the global performance. This paper proposes a framework that highly reduces the number of extracted features with minimum impact on the precision of the 3D scene model. This is achieved by minimizing the representation redundancy by analyzing the geometry of the environment and extracting only those features that are both photometrically and geometrically significant.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages4969-4974
Number of pages6
DOIs
StatePublished - Nov 27 2007
Externally publishedYes
Event2007 IEEE International Conference on Robotics and Automation, ICRA'07 - Rome, Italy
Duration: Apr 10 2007Apr 14 2007

Other

Other2007 IEEE International Conference on Robotics and Automation, ICRA'07
CountryItaly
CityRome
Period4/10/074/14/07

Fingerprint

Redundancy
Navigation
Robotics
Trajectories
Robots
Geometry
Uncertainty

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering

Cite this

Nicosevici, T., Garcia, R., Negahdaripour, S., Kudzinava, M., & Ferrer, J. (2007). Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 4969-4974). [4209863] https://doi.org/10.1109/ROBOT.2007.364245

Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling. / Nicosevici, T.; Garcia, R.; Negahdaripour, Shahriar; Kudzinava, M.; Ferrer, J.

Proceedings - IEEE International Conference on Robotics and Automation. 2007. p. 4969-4974 4209863.

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

Nicosevici, T, Garcia, R, Negahdaripour, S, Kudzinava, M & Ferrer, J 2007, Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling. in Proceedings - IEEE International Conference on Robotics and Automation., 4209863, pp. 4969-4974, 2007 IEEE International Conference on Robotics and Automation, ICRA'07, Rome, Italy, 4/10/07. https://doi.org/10.1109/ROBOT.2007.364245
Nicosevici T, Garcia R, Negahdaripour S, Kudzinava M, Ferrer J. Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling. In Proceedings - IEEE International Conference on Robotics and Automation. 2007. p. 4969-4974. 4209863 https://doi.org/10.1109/ROBOT.2007.364245
Nicosevici, T. ; Garcia, R. ; Negahdaripour, Shahriar ; Kudzinava, M. ; Ferrer, J. / Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling. Proceedings - IEEE International Conference on Robotics and Automation. 2007. pp. 4969-4974
@inproceedings{97334d80613b4efea9bdcc8ac8dd890b,
title = "Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling",
abstract = "Many applications in mobile and underwater robotics employ 3D vision techniques for navigation and mapping. These techniques usually involve the extraction and 3D reconstruction of scene interest points. Nevertheless, in large environments the huge volume of acquired information could pose serious problems to real-time data processing. Moreover, In order to minimize the drift, these techniques use data association to close trajectory loops, decreasing the uncertainties in estimating the position of the robot and increasing the precision of the resulting 3D models. When faced to large amounts of features, the efficiency of data association decreases drastically, affecting the global performance. This paper proposes a framework that highly reduces the number of extracted features with minimum impact on the precision of the 3D scene model. This is achieved by minimizing the representation redundancy by analyzing the geometry of the environment and extracting only those features that are both photometrically and geometrically significant.",
author = "T. Nicosevici and R. Garcia and Shahriar Negahdaripour and M. Kudzinava and J. Ferrer",
year = "2007",
month = "11",
day = "27",
doi = "10.1109/ROBOT.2007.364245",
language = "English",
isbn = "1424406021",
pages = "4969--4974",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Identification of suitable interest points using geometric and photometric cues in motion video for efficient 3-D environmental modeling

AU - Nicosevici, T.

AU - Garcia, R.

AU - Negahdaripour, Shahriar

AU - Kudzinava, M.

AU - Ferrer, J.

PY - 2007/11/27

Y1 - 2007/11/27

N2 - Many applications in mobile and underwater robotics employ 3D vision techniques for navigation and mapping. These techniques usually involve the extraction and 3D reconstruction of scene interest points. Nevertheless, in large environments the huge volume of acquired information could pose serious problems to real-time data processing. Moreover, In order to minimize the drift, these techniques use data association to close trajectory loops, decreasing the uncertainties in estimating the position of the robot and increasing the precision of the resulting 3D models. When faced to large amounts of features, the efficiency of data association decreases drastically, affecting the global performance. This paper proposes a framework that highly reduces the number of extracted features with minimum impact on the precision of the 3D scene model. This is achieved by minimizing the representation redundancy by analyzing the geometry of the environment and extracting only those features that are both photometrically and geometrically significant.

AB - Many applications in mobile and underwater robotics employ 3D vision techniques for navigation and mapping. These techniques usually involve the extraction and 3D reconstruction of scene interest points. Nevertheless, in large environments the huge volume of acquired information could pose serious problems to real-time data processing. Moreover, In order to minimize the drift, these techniques use data association to close trajectory loops, decreasing the uncertainties in estimating the position of the robot and increasing the precision of the resulting 3D models. When faced to large amounts of features, the efficiency of data association decreases drastically, affecting the global performance. This paper proposes a framework that highly reduces the number of extracted features with minimum impact on the precision of the 3D scene model. This is achieved by minimizing the representation redundancy by analyzing the geometry of the environment and extracting only those features that are both photometrically and geometrically significant.

UR - http://www.scopus.com/inward/record.url?scp=36348982790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36348982790&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2007.364245

DO - 10.1109/ROBOT.2007.364245

M3 - Conference contribution

SN - 1424406021

SN - 9781424406029

SP - 4969

EP - 4974

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -