Influence of Video Quality on Multi-view Activity Recognition

Jun Ho Choi, Manri Cheon, Jong-Seok Lee

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

1 Citation (Scopus)

Abstract

This paper presents a study that evaluates the performance of multi-view human activity recognition with videos having degraded quality. For the activity recognition models, a support vector machine-based approach using spatiotemporal features and a deep learning-based approach using convolutional and recurrent layers are built. We investigate the recognition performance of the two models with respect to the bitrate of the compressed videos and the peak signal-to-noise ratio of the videos corrupted by additive Gaussian random noise. We analyze the robustness of the models for the degraded videos.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages511-515
Number of pages5
ISBN (Electronic)9781538629369
DOIs
Publication statusPublished - 2017 Dec 28
Event19th IEEE International Symposium on Multimedia, ISM 2017 - Taichung, Taiwan, Province of China
Duration: 2017 Dec 112017 Dec 13

Publication series

NameProceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017
Volume2017-January

Other

Other19th IEEE International Symposium on Multimedia, ISM 2017
CountryTaiwan, Province of China
CityTaichung
Period17/12/1117/12/13

Fingerprint

Signal-To-Noise Ratio
Human Activities
Support vector machines
Signal to noise ratio
Learning
Recognition (Psychology)
Support Vector Machine
Deep learning

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Sensory Systems

Cite this

Choi, J. H., Cheon, M., & Lee, J-S. (2017). Influence of Video Quality on Multi-view Activity Recognition. In Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017 (pp. 511-515). (Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISM.2017.101
Choi, Jun Ho ; Cheon, Manri ; Lee, Jong-Seok. / Influence of Video Quality on Multi-view Activity Recognition. Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 511-515 (Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017).
@inproceedings{9ce10718d15940599d85d51a4d8556d6,
title = "Influence of Video Quality on Multi-view Activity Recognition",
abstract = "This paper presents a study that evaluates the performance of multi-view human activity recognition with videos having degraded quality. For the activity recognition models, a support vector machine-based approach using spatiotemporal features and a deep learning-based approach using convolutional and recurrent layers are built. We investigate the recognition performance of the two models with respect to the bitrate of the compressed videos and the peak signal-to-noise ratio of the videos corrupted by additive Gaussian random noise. We analyze the robustness of the models for the degraded videos.",
author = "Choi, {Jun Ho} and Manri Cheon and Jong-Seok Lee",
year = "2017",
month = "12",
day = "28",
doi = "10.1109/ISM.2017.101",
language = "English",
series = "Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "511--515",
booktitle = "Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017",
address = "United States",

}

Choi, JH, Cheon, M & Lee, J-S 2017, Influence of Video Quality on Multi-view Activity Recognition. in Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017. Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 511-515, 19th IEEE International Symposium on Multimedia, ISM 2017, Taichung, Taiwan, Province of China, 17/12/11. https://doi.org/10.1109/ISM.2017.101

Influence of Video Quality on Multi-view Activity Recognition. / Choi, Jun Ho; Cheon, Manri; Lee, Jong-Seok.

Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 511-515 (Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017; Vol. 2017-January).

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

TY - GEN

T1 - Influence of Video Quality on Multi-view Activity Recognition

AU - Choi, Jun Ho

AU - Cheon, Manri

AU - Lee, Jong-Seok

PY - 2017/12/28

Y1 - 2017/12/28

N2 - This paper presents a study that evaluates the performance of multi-view human activity recognition with videos having degraded quality. For the activity recognition models, a support vector machine-based approach using spatiotemporal features and a deep learning-based approach using convolutional and recurrent layers are built. We investigate the recognition performance of the two models with respect to the bitrate of the compressed videos and the peak signal-to-noise ratio of the videos corrupted by additive Gaussian random noise. We analyze the robustness of the models for the degraded videos.

AB - This paper presents a study that evaluates the performance of multi-view human activity recognition with videos having degraded quality. For the activity recognition models, a support vector machine-based approach using spatiotemporal features and a deep learning-based approach using convolutional and recurrent layers are built. We investigate the recognition performance of the two models with respect to the bitrate of the compressed videos and the peak signal-to-noise ratio of the videos corrupted by additive Gaussian random noise. We analyze the robustness of the models for the degraded videos.

UR - http://www.scopus.com/inward/record.url?scp=85045922102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045922102&partnerID=8YFLogxK

U2 - 10.1109/ISM.2017.101

DO - 10.1109/ISM.2017.101

M3 - Conference contribution

T3 - Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017

SP - 511

EP - 515

BT - Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Choi JH, Cheon M, Lee J-S. Influence of Video Quality on Multi-view Activity Recognition. In Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 511-515. (Proceedings - 2017 IEEE International Symposium on Multimedia, ISM 2017). https://doi.org/10.1109/ISM.2017.101