Configuration estimates improve pedestrian finding

Duan Tran, D. A. Forsyth

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

Abstract

Fair discriminative pedestrian finders are now available. In fact, these pedestrian finders make most errors on pedestrians in configurations that are uncommon in the training data, for example, mounting a bicycle. This is undesirable. However, the human configuration can itself be estimated discriminatively using structure learning. We demonstrate a pedestrian finder which first finds the most likely human pose in the window using a discriminative procedure trained with structure learning on a small dataset. We then present features (local histogram of oriented gradient and local PCA of gradient) based on that configuration to an SVM classifier. We show, using the INRIA Person dataset, that estimates of configuration significantly improve the accuracy of a discriminative pedestrian finder.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
StatePublished - Dec 1 2009
Event21st Annual Conference on Neural Information Processing Systems, NIPS 2007 - Vancouver, BC, Canada
Duration: Dec 3 2007Dec 6 2007

Publication series

NameAdvances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

Other

Other21st Annual Conference on Neural Information Processing Systems, NIPS 2007
CountryCanada
CityVancouver, BC
Period12/3/0712/6/07

Fingerprint

Bicycles
Mountings
Classifiers

ASJC Scopus subject areas

  • Information Systems

Cite this

Tran, D., & Forsyth, D. A. (2009). Configuration estimates improve pedestrian finding. In Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference (Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference).

Configuration estimates improve pedestrian finding. / Tran, Duan; Forsyth, D. A.

Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. 2009. (Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference).

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

Tran, D & Forsyth, DA 2009, Configuration estimates improve pedestrian finding. in Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference, 21st Annual Conference on Neural Information Processing Systems, NIPS 2007, Vancouver, BC, Canada, 12/3/07.
Tran D, Forsyth DA. Configuration estimates improve pedestrian finding. In Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. 2009. (Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference).
Tran, Duan ; Forsyth, D. A. / Configuration estimates improve pedestrian finding. Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. 2009. (Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference).
@inproceedings{c70bcc0e26754ec3905c2a6740914502,
title = "Configuration estimates improve pedestrian finding",
abstract = "Fair discriminative pedestrian finders are now available. In fact, these pedestrian finders make most errors on pedestrians in configurations that are uncommon in the training data, for example, mounting a bicycle. This is undesirable. However, the human configuration can itself be estimated discriminatively using structure learning. We demonstrate a pedestrian finder which first finds the most likely human pose in the window using a discriminative procedure trained with structure learning on a small dataset. We then present features (local histogram of oriented gradient and local PCA of gradient) based on that configuration to an SVM classifier. We show, using the INRIA Person dataset, that estimates of configuration significantly improve the accuracy of a discriminative pedestrian finder.",
author = "Duan Tran and Forsyth, {D. A.}",
year = "2009",
month = "12",
day = "1",
language = "English (US)",
isbn = "160560352X",
series = "Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference",
booktitle = "Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference",

}

TY - GEN

T1 - Configuration estimates improve pedestrian finding

AU - Tran, Duan

AU - Forsyth, D. A.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Fair discriminative pedestrian finders are now available. In fact, these pedestrian finders make most errors on pedestrians in configurations that are uncommon in the training data, for example, mounting a bicycle. This is undesirable. However, the human configuration can itself be estimated discriminatively using structure learning. We demonstrate a pedestrian finder which first finds the most likely human pose in the window using a discriminative procedure trained with structure learning on a small dataset. We then present features (local histogram of oriented gradient and local PCA of gradient) based on that configuration to an SVM classifier. We show, using the INRIA Person dataset, that estimates of configuration significantly improve the accuracy of a discriminative pedestrian finder.

AB - Fair discriminative pedestrian finders are now available. In fact, these pedestrian finders make most errors on pedestrians in configurations that are uncommon in the training data, for example, mounting a bicycle. This is undesirable. However, the human configuration can itself be estimated discriminatively using structure learning. We demonstrate a pedestrian finder which first finds the most likely human pose in the window using a discriminative procedure trained with structure learning on a small dataset. We then present features (local histogram of oriented gradient and local PCA of gradient) based on that configuration to an SVM classifier. We show, using the INRIA Person dataset, that estimates of configuration significantly improve the accuracy of a discriminative pedestrian finder.

UR - http://www.scopus.com/inward/record.url?scp=84858756366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858756366&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84858756366

SN - 160560352X

SN - 9781605603520

T3 - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

BT - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

ER -