Going into depth: Evaluating 2D and 3D cues for object classification on a new, 
large-scale object dataset

Browatzki, B; Fischer J, Graf B, Bülthoff, HH; Wallraven, C

doi:10.1109/ICCVW.2011.6130385

DetailsSummary

Going into depth: Evaluating 2D and 3D cues for object classification on a new, large-scale object dataset

Browatzki, B., Fischer J, Graf B, Bülthoff, H., & Wallraven, C. (2011). Going into depth: Evaluating 2D and 3D cues for object classification on a new, large-scale object dataset. In 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (pp. 1189-1195). Piscataway, NJ, USA: IEEE.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-B920-1 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-B921-0

Genre: Conference Paper

Files

show Files

Locators

show

Creators

show

hide

Creators:
Browatzki, B¹, Author
Fischer J, Graf B, Bülthoff, HH¹, Author
Wallraven, C¹, Author

Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797

Content

show

hide

Free keywords: -

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 environments-we 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.

Details

show

hide

Language(s):

Dates: Date issued: 2011-11

Publication Status: Issued

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: ISBN: 978-1-467-30062-9
URI: http://www.vision.ee.ethz.ch/CDC4CV/index.html
DOI: 10.1109/ICCVW.2011.6130385
BibTex Citekey: BrowatzkiFGBW2011

Degree: -

Event

show

hide

Title: 1st ICCV Workshop on Consumer Depth Cameras in Computer Vision (CD4CV2011)

Place of Event: Barcelona, Spain

Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show

hide

Title: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

Source Genre: Proceedings

Creator(s):

Affiliations:

Publ. Info: Piscataway, NJ, USA : IEEE

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1189 - 1195 Identifier: -