Going into depth

Evaluating 2D and 3D cues for object classification on a new large-scale object dataset

Björn Browatzki, Jan Fischer, Birgit Graf, Heinrich Bulthoff, Christian Wallraven

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

55 Citations (Scopus)

Abstract

Categorization of objects solely based on shape and appearance is still a largely unresolved issue. With the advent of new sensor technologies*such as consumer-level range sensors*new possibilities for shape processing have become available for a range of new application domains. In the first part of this paper*we introduce a novel*large dataset containing 18 categories of objects found in typical household and office environmentswe envision this dataset to be useful in many applications ranging from robotics to computer vision. The second part of the paper presents computational experiments on object categorization with classifiers exploiting both two-dimensional and three-dimensional information. We evaluate categorization performance for both modalities in separate and combined representations and demonstrate the advantages of using range data for object and shape processing skills.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
Pages1189-1196
Number of pages8
DOIs
Publication statusPublished - 2011 Dec 1
Event2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011 - Barcelona, Spain
Duration: 2011 Nov 62011 Nov 13

Other

Other2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011
CountrySpain
CityBarcelona
Period11/11/611/11/13

Fingerprint

Sensors
Processing
Computer vision
Robotics
Classifiers
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Browatzki, B., Fischer, J., Graf, B., Bulthoff, H., & Wallraven, C. (2011). Going into depth: Evaluating 2D and 3D cues for object classification on a new large-scale object dataset. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1189-1196). [6130385] https://doi.org/10.1109/ICCVW.2011.6130385

Going into depth : Evaluating 2D and 3D cues for object classification on a new large-scale object dataset. / Browatzki, Björn; Fischer, Jan; Graf, Birgit; Bulthoff, Heinrich; Wallraven, Christian.

Proceedings of the IEEE International Conference on Computer Vision. 2011. p. 1189-1196 6130385.

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

Browatzki, B, Fischer, J, Graf, B, Bulthoff, H & Wallraven, C 2011, Going into depth: Evaluating 2D and 3D cues for object classification on a new large-scale object dataset. in Proceedings of the IEEE International Conference on Computer Vision., 6130385, pp. 1189-1196, 2011 IEEE International Conference on Computer Vision Workshops, ICCV Workshops 2011, Barcelona, Spain, 11/11/6. https://doi.org/10.1109/ICCVW.2011.6130385
Browatzki B, Fischer J, Graf B, Bulthoff H, Wallraven C. Going into depth: Evaluating 2D and 3D cues for object classification on a new large-scale object dataset. In Proceedings of the IEEE International Conference on Computer Vision. 2011. p. 1189-1196. 6130385 https://doi.org/10.1109/ICCVW.2011.6130385
Browatzki, Björn ; Fischer, Jan ; Graf, Birgit ; Bulthoff, Heinrich ; Wallraven, Christian. / Going into depth : Evaluating 2D and 3D cues for object classification on a new large-scale object dataset. Proceedings of the IEEE International Conference on Computer Vision. 2011. pp. 1189-1196
@inproceedings{7dfb0139b1f04b0bb8f041dd078d0330,
title = "Going into depth: Evaluating 2D and 3D cues for object classification on a new large-scale object dataset",
abstract = "Categorization of objects solely based on shape and appearance is still a largely unresolved issue. With the advent of new sensor technologies*such as consumer-level range sensors*new possibilities for shape processing have become available for a range of new application domains. In the first part of this paper*we introduce a novel*large dataset containing 18 categories of objects found in typical household and office environmentswe envision this dataset to be useful in many applications ranging from robotics to computer vision. The second part of the paper presents computational experiments on object categorization with classifiers exploiting both two-dimensional and three-dimensional information. We evaluate categorization performance for both modalities in separate and combined representations and demonstrate the advantages of using range data for object and shape processing skills.",
author = "Bj{\"o}rn Browatzki and Jan Fischer and Birgit Graf and Heinrich Bulthoff and Christian Wallraven",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/ICCVW.2011.6130385",
language = "English",
isbn = "9781467300629",
pages = "1189--1196",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",

}

TY - GEN

T1 - Going into depth

T2 - Evaluating 2D and 3D cues for object classification on a new large-scale object dataset

AU - Browatzki, Björn

AU - Fischer, Jan

AU - Graf, Birgit

AU - Bulthoff, Heinrich

AU - Wallraven, Christian

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Categorization of objects solely based on shape and appearance is still a largely unresolved issue. With the advent of new sensor technologies*such as consumer-level range sensors*new possibilities for shape processing have become available for a range of new application domains. In the first part of this paper*we introduce a novel*large dataset containing 18 categories of objects found in typical household and office environmentswe envision this dataset to be useful in many applications ranging from robotics to computer vision. The second part of the paper presents computational experiments on object categorization with classifiers exploiting both two-dimensional and three-dimensional information. We evaluate categorization performance for both modalities in separate and combined representations and demonstrate the advantages of using range data for object and shape processing skills.

AB - Categorization of objects solely based on shape and appearance is still a largely unresolved issue. With the advent of new sensor technologies*such as consumer-level range sensors*new possibilities for shape processing have become available for a range of new application domains. In the first part of this paper*we introduce a novel*large dataset containing 18 categories of objects found in typical household and office environmentswe envision this dataset to be useful in many applications ranging from robotics to computer vision. The second part of the paper presents computational experiments on object categorization with classifiers exploiting both two-dimensional and three-dimensional information. We evaluate categorization performance for both modalities in separate and combined representations and demonstrate the advantages of using range data for object and shape processing skills.

UR - http://www.scopus.com/inward/record.url?scp=84856641335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856641335&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2011.6130385

DO - 10.1109/ICCVW.2011.6130385

M3 - Conference contribution

SN - 9781467300629

SP - 1189

EP - 1196

BT - Proceedings of the IEEE International Conference on Computer Vision

ER -