Diversity promoting online sampling for streaming video summarization

Rushil Anirudh, Ahnaf Masroor, Pavan Turaga

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

4 Citations (Scopus)

Abstract

Many applications benefit from sampling algorithms where a small number of well chosen samples are used to generalize different properties of a large dataset. In this paper, we use diverse sampling for streaming video summarization. Several emerging applications support streaming video, but existing summarization algorithms need access to the entire video which requires a lot of memory and computational power. We propose a memory efficient and computationally fast, online algorithm that uses competitive learning for diverse sampling. Our algorithm is a generalization of online K-means such that the cost function reduces clustering error, while also ensuring a diverse set of samples. The diversity is measured as the volume of a convex hull around the samples. Finally, the performance of the proposed algorithm is measured against human users for 50 videos in the VSUMM dataset. The algorithm performs better than batch mode summarization, while requiring significantly lower memory and computational requirements.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages3329-3333
Number of pages5
Volume2016-August
ISBN (Electronic)9781467399616
DOIs
StatePublished - Aug 3 2016
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: Sep 25 2016Sep 28 2016

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period9/25/169/28/16

Fingerprint

Video streaming
Sampling
Data storage equipment
Cost functions

Keywords

  • Online Algorithms
  • Sampling
  • Streaming Video
  • Video Summarization

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Anirudh, R., Masroor, A., & Turaga, P. (2016). Diversity promoting online sampling for streaming video summarization. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (Vol. 2016-August, pp. 3329-3333). [7532976] IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7532976

Diversity promoting online sampling for streaming video summarization. / Anirudh, Rushil; Masroor, Ahnaf; Turaga, Pavan.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. p. 3329-3333 7532976.

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

Anirudh, R, Masroor, A & Turaga, P 2016, Diversity promoting online sampling for streaming video summarization. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. vol. 2016-August, 7532976, IEEE Computer Society, pp. 3329-3333, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 9/25/16. https://doi.org/10.1109/ICIP.2016.7532976
Anirudh R, Masroor A, Turaga P. Diversity promoting online sampling for streaming video summarization. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August. IEEE Computer Society. 2016. p. 3329-3333. 7532976 https://doi.org/10.1109/ICIP.2016.7532976
Anirudh, Rushil ; Masroor, Ahnaf ; Turaga, Pavan. / Diversity promoting online sampling for streaming video summarization. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. Vol. 2016-August IEEE Computer Society, 2016. pp. 3329-3333
@inproceedings{29ba2bf653ab42ce870b223b95c41051,
title = "Diversity promoting online sampling for streaming video summarization",
abstract = "Many applications benefit from sampling algorithms where a small number of well chosen samples are used to generalize different properties of a large dataset. In this paper, we use diverse sampling for streaming video summarization. Several emerging applications support streaming video, but existing summarization algorithms need access to the entire video which requires a lot of memory and computational power. We propose a memory efficient and computationally fast, online algorithm that uses competitive learning for diverse sampling. Our algorithm is a generalization of online K-means such that the cost function reduces clustering error, while also ensuring a diverse set of samples. The diversity is measured as the volume of a convex hull around the samples. Finally, the performance of the proposed algorithm is measured against human users for 50 videos in the VSUMM dataset. The algorithm performs better than batch mode summarization, while requiring significantly lower memory and computational requirements.",
keywords = "Online Algorithms, Sampling, Streaming Video, Video Summarization",
author = "Rushil Anirudh and Ahnaf Masroor and Pavan Turaga",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7532976",
language = "English (US)",
volume = "2016-August",
pages = "3329--3333",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",
publisher = "IEEE Computer Society",
address = "United States",

}

TY - GEN

T1 - Diversity promoting online sampling for streaming video summarization

AU - Anirudh, Rushil

AU - Masroor, Ahnaf

AU - Turaga, Pavan

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Many applications benefit from sampling algorithms where a small number of well chosen samples are used to generalize different properties of a large dataset. In this paper, we use diverse sampling for streaming video summarization. Several emerging applications support streaming video, but existing summarization algorithms need access to the entire video which requires a lot of memory and computational power. We propose a memory efficient and computationally fast, online algorithm that uses competitive learning for diverse sampling. Our algorithm is a generalization of online K-means such that the cost function reduces clustering error, while also ensuring a diverse set of samples. The diversity is measured as the volume of a convex hull around the samples. Finally, the performance of the proposed algorithm is measured against human users for 50 videos in the VSUMM dataset. The algorithm performs better than batch mode summarization, while requiring significantly lower memory and computational requirements.

AB - Many applications benefit from sampling algorithms where a small number of well chosen samples are used to generalize different properties of a large dataset. In this paper, we use diverse sampling for streaming video summarization. Several emerging applications support streaming video, but existing summarization algorithms need access to the entire video which requires a lot of memory and computational power. We propose a memory efficient and computationally fast, online algorithm that uses competitive learning for diverse sampling. Our algorithm is a generalization of online K-means such that the cost function reduces clustering error, while also ensuring a diverse set of samples. The diversity is measured as the volume of a convex hull around the samples. Finally, the performance of the proposed algorithm is measured against human users for 50 videos in the VSUMM dataset. The algorithm performs better than batch mode summarization, while requiring significantly lower memory and computational requirements.

KW - Online Algorithms

KW - Sampling

KW - Streaming Video

KW - Video Summarization

UR - http://www.scopus.com/inward/record.url?scp=85006788920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006788920&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7532976

DO - 10.1109/ICIP.2016.7532976

M3 - Conference contribution

VL - 2016-August

SP - 3329

EP - 3333

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -