Predicting dynamical evolution of human activities from a single image

Suhas Lohit, Ankan Bansal, Nitesh Shroff, Jaishanker Pillai, Pavan Turaga, Rama Chellappa

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

Abstract

A human pose often conveys not only the configuration of the body parts, but also implicit predictive information about the ensuing motion. This dynamic information can benefit vision applications which lack explicit motion cues. The human visual system can easily perceive the dynamic information in still images. However, computational algorithms to infer and utilize it in computer vision applications are limited. In this paper, we propose a probabilistic framework to infer the dynamic information associated with a human pose. The inference problem is posed as a nonparametric density estimation problem on a non-Euclidean manifold of linear dynamical models. Since direct modeling is intractable, we develop a data driven approach, estimating the density for the test sample under consideration. Statistical inference on the estimated density provides us with quantities of interest like the most probable future motion of the human and the amount of motion information conveyed by a pose. Our experiments demonstrate that the extracted motion information benefits numerous applications in computer vision. In particular, the predicted future motion is useful for activity recognition, human trajectory synthesis, and motion prediction.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
PublisherIEEE Computer Society
Pages496-505
Number of pages10
Volume2018-June
ISBN (Electronic)9781538661000
DOIs
StatePublished - Dec 13 2018
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States
Duration: Jun 18 2018Jun 22 2018

Other

Other31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
CountryUnited States
CitySalt Lake City
Period6/18/186/22/18

Fingerprint

Computer vision
Trajectories
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Lohit, S., Bansal, A., Shroff, N., Pillai, J., Turaga, P., & Chellappa, R. (2018). Predicting dynamical evolution of human activities from a single image. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 (Vol. 2018-June, pp. 496-505). [8575541] IEEE Computer Society. https://doi.org/10.1109/CVPRW.2018.00079

Predicting dynamical evolution of human activities from a single image. / Lohit, Suhas; Bansal, Ankan; Shroff, Nitesh; Pillai, Jaishanker; Turaga, Pavan; Chellappa, Rama.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. Vol. 2018-June IEEE Computer Society, 2018. p. 496-505 8575541.

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

Lohit, S, Bansal, A, Shroff, N, Pillai, J, Turaga, P & Chellappa, R 2018, Predicting dynamical evolution of human activities from a single image. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. vol. 2018-June, 8575541, IEEE Computer Society, pp. 496-505, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, United States, 6/18/18. https://doi.org/10.1109/CVPRW.2018.00079
Lohit S, Bansal A, Shroff N, Pillai J, Turaga P, Chellappa R. Predicting dynamical evolution of human activities from a single image. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. Vol. 2018-June. IEEE Computer Society. 2018. p. 496-505. 8575541 https://doi.org/10.1109/CVPRW.2018.00079
Lohit, Suhas ; Bansal, Ankan ; Shroff, Nitesh ; Pillai, Jaishanker ; Turaga, Pavan ; Chellappa, Rama. / Predicting dynamical evolution of human activities from a single image. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018. Vol. 2018-June IEEE Computer Society, 2018. pp. 496-505
@inproceedings{620f83b16d2d412997ce314f82205a46,
title = "Predicting dynamical evolution of human activities from a single image",
abstract = "A human pose often conveys not only the configuration of the body parts, but also implicit predictive information about the ensuing motion. This dynamic information can benefit vision applications which lack explicit motion cues. The human visual system can easily perceive the dynamic information in still images. However, computational algorithms to infer and utilize it in computer vision applications are limited. In this paper, we propose a probabilistic framework to infer the dynamic information associated with a human pose. The inference problem is posed as a nonparametric density estimation problem on a non-Euclidean manifold of linear dynamical models. Since direct modeling is intractable, we develop a data driven approach, estimating the density for the test sample under consideration. Statistical inference on the estimated density provides us with quantities of interest like the most probable future motion of the human and the amount of motion information conveyed by a pose. Our experiments demonstrate that the extracted motion information benefits numerous applications in computer vision. In particular, the predicted future motion is useful for activity recognition, human trajectory synthesis, and motion prediction.",
author = "Suhas Lohit and Ankan Bansal and Nitesh Shroff and Jaishanker Pillai and Pavan Turaga and Rama Chellappa",
year = "2018",
month = "12",
day = "13",
doi = "10.1109/CVPRW.2018.00079",
language = "English (US)",
volume = "2018-June",
pages = "496--505",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Predicting dynamical evolution of human activities from a single image

AU - Lohit, Suhas

AU - Bansal, Ankan

AU - Shroff, Nitesh

AU - Pillai, Jaishanker

AU - Turaga, Pavan

AU - Chellappa, Rama

PY - 2018/12/13

Y1 - 2018/12/13

N2 - A human pose often conveys not only the configuration of the body parts, but also implicit predictive information about the ensuing motion. This dynamic information can benefit vision applications which lack explicit motion cues. The human visual system can easily perceive the dynamic information in still images. However, computational algorithms to infer and utilize it in computer vision applications are limited. In this paper, we propose a probabilistic framework to infer the dynamic information associated with a human pose. The inference problem is posed as a nonparametric density estimation problem on a non-Euclidean manifold of linear dynamical models. Since direct modeling is intractable, we develop a data driven approach, estimating the density for the test sample under consideration. Statistical inference on the estimated density provides us with quantities of interest like the most probable future motion of the human and the amount of motion information conveyed by a pose. Our experiments demonstrate that the extracted motion information benefits numerous applications in computer vision. In particular, the predicted future motion is useful for activity recognition, human trajectory synthesis, and motion prediction.

AB - A human pose often conveys not only the configuration of the body parts, but also implicit predictive information about the ensuing motion. This dynamic information can benefit vision applications which lack explicit motion cues. The human visual system can easily perceive the dynamic information in still images. However, computational algorithms to infer and utilize it in computer vision applications are limited. In this paper, we propose a probabilistic framework to infer the dynamic information associated with a human pose. The inference problem is posed as a nonparametric density estimation problem on a non-Euclidean manifold of linear dynamical models. Since direct modeling is intractable, we develop a data driven approach, estimating the density for the test sample under consideration. Statistical inference on the estimated density provides us with quantities of interest like the most probable future motion of the human and the amount of motion information conveyed by a pose. Our experiments demonstrate that the extracted motion information benefits numerous applications in computer vision. In particular, the predicted future motion is useful for activity recognition, human trajectory synthesis, and motion prediction.

UR - http://www.scopus.com/inward/record.url?scp=85060860803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060860803&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2018.00079

DO - 10.1109/CVPRW.2018.00079

M3 - Conference contribution

VL - 2018-June

SP - 496

EP - 505

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

PB - IEEE Computer Society

ER -