Evaluation of different descriptors for identifying similar video shots

Nicola Adami, Riccardo Leonardi, Yao Wang

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

Abstract

In this paper, three techniques for video sequence retrieval which use statistical measures of color patterns in shots are proposed and compared. The first technique is based on a correlation of the MPEG7 Dominant Color Descriptor (DC) [6] as single characteristic feature of a shot. The second approach is to model color pattern distribution in a shot with a codebook, obtained by VQ (Vector Quantization) of the frame blocks composing the shot. The last one models the color pattern distribution using a GMM (Gaussian Mixture Model). Such descriptors are used to establish correspondence between non consecutive camera records through an appropriately designed similarity measure. As such, a new distance measure is used in the comparison between the shot descriptors, by extending the metric proposed in [9]. A comparison is made of the dissimilarity performance associated with each of the three proposed descriptors, demonstrating the superior results obtainable with the VQ based approach.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Multimedia and Expo
PublisherIEEE Computer Society
Pages741-744
Number of pages4
ISBN (Print)0769511988
DOIs
StatePublished - 2001
Event2001 IEEE International Conference on Multimedia and Expo, ICME 2001 - Tokyo, Japan
Duration: Aug 22 2001Aug 25 2001

Other

Other2001 IEEE International Conference on Multimedia and Expo, ICME 2001
CountryJapan
CityTokyo
Period8/22/018/25/01

Fingerprint

Color
Vector quantization
Cameras

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Adami, N., Leonardi, R., & Wang, Y. (2001). Evaluation of different descriptors for identifying similar video shots. In Proceedings - IEEE International Conference on Multimedia and Expo (pp. 741-744). [1237828] IEEE Computer Society. https://doi.org/10.1109/ICME.2001.1237828

Evaluation of different descriptors for identifying similar video shots. / Adami, Nicola; Leonardi, Riccardo; Wang, Yao.

Proceedings - IEEE International Conference on Multimedia and Expo. IEEE Computer Society, 2001. p. 741-744 1237828.

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

Adami, N, Leonardi, R & Wang, Y 2001, Evaluation of different descriptors for identifying similar video shots. in Proceedings - IEEE International Conference on Multimedia and Expo., 1237828, IEEE Computer Society, pp. 741-744, 2001 IEEE International Conference on Multimedia and Expo, ICME 2001, Tokyo, Japan, 8/22/01. https://doi.org/10.1109/ICME.2001.1237828
Adami N, Leonardi R, Wang Y. Evaluation of different descriptors for identifying similar video shots. In Proceedings - IEEE International Conference on Multimedia and Expo. IEEE Computer Society. 2001. p. 741-744. 1237828 https://doi.org/10.1109/ICME.2001.1237828
Adami, Nicola ; Leonardi, Riccardo ; Wang, Yao. / Evaluation of different descriptors for identifying similar video shots. Proceedings - IEEE International Conference on Multimedia and Expo. IEEE Computer Society, 2001. pp. 741-744
@inproceedings{feee180aac8d477d8d606f75b8dcf791,
title = "Evaluation of different descriptors for identifying similar video shots",
abstract = "In this paper, three techniques for video sequence retrieval which use statistical measures of color patterns in shots are proposed and compared. The first technique is based on a correlation of the MPEG7 Dominant Color Descriptor (DC) [6] as single characteristic feature of a shot. The second approach is to model color pattern distribution in a shot with a codebook, obtained by VQ (Vector Quantization) of the frame blocks composing the shot. The last one models the color pattern distribution using a GMM (Gaussian Mixture Model). Such descriptors are used to establish correspondence between non consecutive camera records through an appropriately designed similarity measure. As such, a new distance measure is used in the comparison between the shot descriptors, by extending the metric proposed in [9]. A comparison is made of the dissimilarity performance associated with each of the three proposed descriptors, demonstrating the superior results obtainable with the VQ based approach.",
author = "Nicola Adami and Riccardo Leonardi and Yao Wang",
year = "2001",
doi = "10.1109/ICME.2001.1237828",
language = "English (US)",
isbn = "0769511988",
pages = "741--744",
booktitle = "Proceedings - IEEE International Conference on Multimedia and Expo",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Evaluation of different descriptors for identifying similar video shots

AU - Adami, Nicola

AU - Leonardi, Riccardo

AU - Wang, Yao

PY - 2001

Y1 - 2001

N2 - In this paper, three techniques for video sequence retrieval which use statistical measures of color patterns in shots are proposed and compared. The first technique is based on a correlation of the MPEG7 Dominant Color Descriptor (DC) [6] as single characteristic feature of a shot. The second approach is to model color pattern distribution in a shot with a codebook, obtained by VQ (Vector Quantization) of the frame blocks composing the shot. The last one models the color pattern distribution using a GMM (Gaussian Mixture Model). Such descriptors are used to establish correspondence between non consecutive camera records through an appropriately designed similarity measure. As such, a new distance measure is used in the comparison between the shot descriptors, by extending the metric proposed in [9]. A comparison is made of the dissimilarity performance associated with each of the three proposed descriptors, demonstrating the superior results obtainable with the VQ based approach.

AB - In this paper, three techniques for video sequence retrieval which use statistical measures of color patterns in shots are proposed and compared. The first technique is based on a correlation of the MPEG7 Dominant Color Descriptor (DC) [6] as single characteristic feature of a shot. The second approach is to model color pattern distribution in a shot with a codebook, obtained by VQ (Vector Quantization) of the frame blocks composing the shot. The last one models the color pattern distribution using a GMM (Gaussian Mixture Model). Such descriptors are used to establish correspondence between non consecutive camera records through an appropriately designed similarity measure. As such, a new distance measure is used in the comparison between the shot descriptors, by extending the metric proposed in [9]. A comparison is made of the dissimilarity performance associated with each of the three proposed descriptors, demonstrating the superior results obtainable with the VQ based approach.

UR - http://www.scopus.com/inward/record.url?scp=84908266343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908266343&partnerID=8YFLogxK

U2 - 10.1109/ICME.2001.1237828

DO - 10.1109/ICME.2001.1237828

M3 - Conference contribution

SN - 0769511988

SP - 741

EP - 744

BT - Proceedings - IEEE International Conference on Multimedia and Expo

PB - IEEE Computer Society

ER -