A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images

Troy McDaniel; Kanav Kahol; Priyamvada Tripathi; David P. Smith; Laura Bratton; Ravi Atreya; Sethuraman Panchanathan

doi:10.1109/HAVE.2005.1545659

A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images

Troy McDaniel, Kanav Kahol, Priyamvada Tripathi, David P. Smith, Laura Bratton, Ravi Atreya, Sethuraman Panchanathan

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

3 Scopus citations

Abstract

Humans have an uncanny ability to estimate haptic features of an object such as haptic shape, size, texture and material by visual inspection. A significant computer vision problem is that of estimating haptic features from visual images. While explorations have been made in estimation of visual features such as visual texture, work on estimation of haptic features from video is still in its infancy. We present a methodology to establish ground truth for estimation of haptic features from visual images. We assembled a visio-haptic database of 48 objects ranging from nonsense objects to everyday objects. The variation was controlled in objects by systematically varying haptic features such as shape and texture, and the physical and perceptual ground truth of visual and haptic features was documented. This database provides visio-haptic features of objects and can be used to develop algorithms to estimate haptic features from visual images. Finally, a tactile cueing experiment is presented demonstrating how visio-haptic ground truth can be used to assess the accuracy of a system for visio-haptic conversion of image content.

Original language	English (US)
Title of host publication	HAVE 2005
Subtitle of host publication	IEEE International Workshop on Haptic Audio Visual Environments and their Applications
Pages	95-100
Number of pages	6
DOIs	https://doi.org/10.1109/HAVE.2005.1545659
State	Published - 2005
Event	HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications - Ottawa, ON, Canada Duration: Oct 1 2005 → Oct 2 2005

Publication series

Name	HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications
Volume	2005

Other

Other	HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications
Country/Territory	Canada
City	Ottawa, ON
Period	10/1/05 → 10/2/05

Keywords

Image databases
Machine vision
Tactile displays
Tactile systems
Testing
Visualization

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/HAVE.2005.1545659

Cite this

McDaniel, T., Kahol, K., Tripathi, P., Smith, D. P., Bratton, L., Atreya, R., & Panchanathan, S. (2005). A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images. In HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications (pp. 95-100). Article 1545659 (HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications; Vol. 2005). https://doi.org/10.1109/HAVE.2005.1545659

A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images. / McDaniel, Troy; Kahol, Kanav; Tripathi, Priyamvada et al.
HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications. 2005. p. 95-100 1545659 (HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications; Vol. 2005).

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

McDaniel, T, Kahol, K, Tripathi, P, Smith, DP, Bratton, L, Atreya, R & Panchanathan, S 2005, A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images. in HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications., 1545659, HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications, vol. 2005, pp. 95-100, HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications, Ottawa, ON, Canada, 10/1/05. https://doi.org/10.1109/HAVE.2005.1545659

McDaniel T, Kahol K, Tripathi P, Smith DP, Bratton L, Atreya R et al. A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images. In HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications. 2005. p. 95-100. 1545659. (HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications). doi: 10.1109/HAVE.2005.1545659

McDaniel, Troy ; Kahol, Kanav ; Tripathi, Priyamvada et al. / A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images. HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications. 2005. pp. 95-100 (HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications).

@inproceedings{4f41fd16681e44678e10fe5f9094c865,

title = "A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images",

abstract = "Humans have an uncanny ability to estimate haptic features of an object such as haptic shape, size, texture and material by visual inspection. A significant computer vision problem is that of estimating haptic features from visual images. While explorations have been made in estimation of visual features such as visual texture, work on estimation of haptic features from video is still in its infancy. We present a methodology to establish ground truth for estimation of haptic features from visual images. We assembled a visio-haptic database of 48 objects ranging from nonsense objects to everyday objects. The variation was controlled in objects by systematically varying haptic features such as shape and texture, and the physical and perceptual ground truth of visual and haptic features was documented. This database provides visio-haptic features of objects and can be used to develop algorithms to estimate haptic features from visual images. Finally, a tactile cueing experiment is presented demonstrating how visio-haptic ground truth can be used to assess the accuracy of a system for visio-haptic conversion of image content.",

keywords = "Image databases, Machine vision, Tactile displays, Tactile systems, Testing, Visualization",

author = "Troy McDaniel and Kanav Kahol and Priyamvada Tripathi and Smith, {David P.} and Laura Bratton and Ravi Atreya and Sethuraman Panchanathan",

note = "Copyright: Copyright 2011 Elsevier B.V., All rights reserved.; HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications ; Conference date: 01-10-2005 Through 02-10-2005",

year = "2005",

doi = "10.1109/HAVE.2005.1545659",

language = "English (US)",

isbn = "0780393775",

series = "HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications",

pages = "95--100",

booktitle = "HAVE 2005",

}

TY - GEN

T1 - A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images

AU - McDaniel, Troy

AU - Kahol, Kanav

AU - Tripathi, Priyamvada

AU - Smith, David P.

AU - Bratton, Laura

AU - Atreya, Ravi

AU - Panchanathan, Sethuraman

PY - 2005

Y1 - 2005

N2 - Humans have an uncanny ability to estimate haptic features of an object such as haptic shape, size, texture and material by visual inspection. A significant computer vision problem is that of estimating haptic features from visual images. While explorations have been made in estimation of visual features such as visual texture, work on estimation of haptic features from video is still in its infancy. We present a methodology to establish ground truth for estimation of haptic features from visual images. We assembled a visio-haptic database of 48 objects ranging from nonsense objects to everyday objects. The variation was controlled in objects by systematically varying haptic features such as shape and texture, and the physical and perceptual ground truth of visual and haptic features was documented. This database provides visio-haptic features of objects and can be used to develop algorithms to estimate haptic features from visual images. Finally, a tactile cueing experiment is presented demonstrating how visio-haptic ground truth can be used to assess the accuracy of a system for visio-haptic conversion of image content.

AB - Humans have an uncanny ability to estimate haptic features of an object such as haptic shape, size, texture and material by visual inspection. A significant computer vision problem is that of estimating haptic features from visual images. While explorations have been made in estimation of visual features such as visual texture, work on estimation of haptic features from video is still in its infancy. We present a methodology to establish ground truth for estimation of haptic features from visual images. We assembled a visio-haptic database of 48 objects ranging from nonsense objects to everyday objects. The variation was controlled in objects by systematically varying haptic features such as shape and texture, and the physical and perceptual ground truth of visual and haptic features was documented. This database provides visio-haptic features of objects and can be used to develop algorithms to estimate haptic features from visual images. Finally, a tactile cueing experiment is presented demonstrating how visio-haptic ground truth can be used to assess the accuracy of a system for visio-haptic conversion of image content.

KW - Image databases

KW - Machine vision

KW - Tactile displays

KW - Tactile systems

KW - Testing

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=33845512536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845512536&partnerID=8YFLogxK

U2 - 10.1109/HAVE.2005.1545659

DO - 10.1109/HAVE.2005.1545659

M3 - Conference contribution

AN - SCOPUS:33845512536

SN - 0780393775

SN - 9780780393776

T3 - HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications

SP - 95

EP - 100

BT - HAVE 2005

T2 - HAVE 2005: IEEE International Workshop on Haptic Audio Visual Environments and their Applications

Y2 - 1 October 2005 through 2 October 2005

ER -

A methodology to establish ground truth for computer vision algorithms to estimate haptic features from visual images

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this