Detecting, localizing and recovering kinematics of textured animals

Deva Ramanan, D. A. Forsyth, Kobus Barnard

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

Abstract

We develop and demonstrate an object recognition system capable of accurately detecting, localizing, and recovering the kinematic configuration of textured animals in real images. We build a deformation model of shape automatically from videos of animals and an appearance model of texture from a labeled collection of animal images, and combine the two models automatically. We develop a simple texture descriptor that outperforms the state of the art. We test our animal models on two datasets; images taken by professional photographers from the Corel collection, and assorted images from the web returned by Google. We demonstrate quite good performance on both datasets. Comparing our results with simple baselines, we show that for the Google set, we can recognize objects from a collection demonstrably hard for object recognition.

Original languageEnglish (US)
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages635-642
Number of pages8
ISBN (Print)0769523722, 9780769523729
DOIs
StatePublished - Jan 1 2005
Externally publishedYes
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: Jun 20 2005Jun 25 2005

Publication series

NameProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
VolumeII

Other

Other2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
CountryUnited States
CitySan Diego, CA
Period6/20/056/25/05

Fingerprint

Kinematics
Animals
Object recognition
Textures

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ramanan, D., Forsyth, D. A., & Barnard, K. (2005). Detecting, localizing and recovering kinematics of textured animals. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 (pp. 635-642). [1467501] (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005; Vol. II). IEEE Computer Society. https://doi.org/10.1109/CVPR.2005.126

Detecting, localizing and recovering kinematics of textured animals. / Ramanan, Deva; Forsyth, D. A.; Barnard, Kobus.

Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society, 2005. p. 635-642 1467501 (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005; Vol. II).

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

Ramanan, D, Forsyth, DA & Barnard, K 2005, Detecting, localizing and recovering kinematics of textured animals. in Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005., 1467501, Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. II, IEEE Computer Society, pp. 635-642, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, CA, United States, 6/20/05. https://doi.org/10.1109/CVPR.2005.126
Ramanan D, Forsyth DA, Barnard K. Detecting, localizing and recovering kinematics of textured animals. In Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society. 2005. p. 635-642. 1467501. (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005). https://doi.org/10.1109/CVPR.2005.126
Ramanan, Deva ; Forsyth, D. A. ; Barnard, Kobus. / Detecting, localizing and recovering kinematics of textured animals. Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. IEEE Computer Society, 2005. pp. 635-642 (Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005).
@inproceedings{59141b8929d847c089fce576c7531711,
title = "Detecting, localizing and recovering kinematics of textured animals",
abstract = "We develop and demonstrate an object recognition system capable of accurately detecting, localizing, and recovering the kinematic configuration of textured animals in real images. We build a deformation model of shape automatically from videos of animals and an appearance model of texture from a labeled collection of animal images, and combine the two models automatically. We develop a simple texture descriptor that outperforms the state of the art. We test our animal models on two datasets; images taken by professional photographers from the Corel collection, and assorted images from the web returned by Google. We demonstrate quite good performance on both datasets. Comparing our results with simple baselines, we show that for the Google set, we can recognize objects from a collection demonstrably hard for object recognition.",
author = "Deva Ramanan and Forsyth, {D. A.} and Kobus Barnard",
year = "2005",
month = "1",
day = "1",
doi = "10.1109/CVPR.2005.126",
language = "English (US)",
isbn = "0769523722",
series = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",
publisher = "IEEE Computer Society",
pages = "635--642",
booktitle = "Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005",

}

TY - GEN

T1 - Detecting, localizing and recovering kinematics of textured animals

AU - Ramanan, Deva

AU - Forsyth, D. A.

AU - Barnard, Kobus

PY - 2005/1/1

Y1 - 2005/1/1

N2 - We develop and demonstrate an object recognition system capable of accurately detecting, localizing, and recovering the kinematic configuration of textured animals in real images. We build a deformation model of shape automatically from videos of animals and an appearance model of texture from a labeled collection of animal images, and combine the two models automatically. We develop a simple texture descriptor that outperforms the state of the art. We test our animal models on two datasets; images taken by professional photographers from the Corel collection, and assorted images from the web returned by Google. We demonstrate quite good performance on both datasets. Comparing our results with simple baselines, we show that for the Google set, we can recognize objects from a collection demonstrably hard for object recognition.

AB - We develop and demonstrate an object recognition system capable of accurately detecting, localizing, and recovering the kinematic configuration of textured animals in real images. We build a deformation model of shape automatically from videos of animals and an appearance model of texture from a labeled collection of animal images, and combine the two models automatically. We develop a simple texture descriptor that outperforms the state of the art. We test our animal models on two datasets; images taken by professional photographers from the Corel collection, and assorted images from the web returned by Google. We demonstrate quite good performance on both datasets. Comparing our results with simple baselines, we show that for the Google set, we can recognize objects from a collection demonstrably hard for object recognition.

UR - http://www.scopus.com/inward/record.url?scp=24644450745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24644450745&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2005.126

DO - 10.1109/CVPR.2005.126

M3 - Conference contribution

AN - SCOPUS:24644450745

SN - 0769523722

SN - 9780769523729

T3 - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

SP - 635

EP - 642

BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005

PB - IEEE Computer Society

ER -