The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans cette lettre, nous proposons une nouvelle méthode de description des caractéristiques de mouvement global de bas niveau basée sur des histogrammes d'index de quantification vectorielle (VQ) de vecteurs de caractéristiques de mouvement (MFVVQIH) à des fins de récupération de plans vidéo. La contribution réside dans trois aspects : premièrement, nous utilisons VQ pour éliminer les points singuliers dans l'espace vectoriel des caractéristiques de mouvement ; Deuxièmement, nous utilisons l'histogramme d'index vectoriel des caractéristiques de mouvement global d'une vidéo tournée comme signature de mouvement globale ; troisièmement, la récupération de plans vidéo basée sur des histogrammes d'index au lieu de vecteurs de caractéristiques de mouvement d'origine garantit une faible complexité de calcul et assure ainsi une récupération de plans vidéo en temps réel. Les résultats expérimentaux montrent que le schéma proposé présente une grande précision et une faible complexité de calcul.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Fa-Xin YU, Zhe-Ming LU, Zhen LI, Hao LUO, "Global Motion Representation of Video Shot Based on Vector Quantization Index Histogram" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 1, pp. 90-92, January 2009, doi: 10.1587/transinf.E92.D.90.
Abstract: In this Letter, we propose a novel method of low-level global motion feature description based on Vector Quantization (VQ) index histograms of motion feature vectors (MFVVQIH) for the purpose of video shot retrieval. The contribution lies in three aspects: first, we use VQ to eliminate singular points in the motion feature vector space; second, we utilize the global motion feature vector index histogram of a video shot as the global motion signature; third, video shot retrieval based on index histograms instead of original motion feature vectors guarantees the low computation complexity, and thus assures a real-time video shot retrieval. Experimental results show that the proposed scheme has high accuracy and low computation complexity.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.90/_p
Copier
@ARTICLE{e92-d_1_90,
author={Fa-Xin YU, Zhe-Ming LU, Zhen LI, Hao LUO, },
journal={IEICE TRANSACTIONS on Information},
title={Global Motion Representation of Video Shot Based on Vector Quantization Index Histogram},
year={2009},
volume={E92-D},
number={1},
pages={90-92},
abstract={In this Letter, we propose a novel method of low-level global motion feature description based on Vector Quantization (VQ) index histograms of motion feature vectors (MFVVQIH) for the purpose of video shot retrieval. The contribution lies in three aspects: first, we use VQ to eliminate singular points in the motion feature vector space; second, we utilize the global motion feature vector index histogram of a video shot as the global motion signature; third, video shot retrieval based on index histograms instead of original motion feature vectors guarantees the low computation complexity, and thus assures a real-time video shot retrieval. Experimental results show that the proposed scheme has high accuracy and low computation complexity.},
keywords={},
doi={10.1587/transinf.E92.D.90},
ISSN={1745-1361},
month={January},}
Copier
TY - JOUR
TI - Global Motion Representation of Video Shot Based on Vector Quantization Index Histogram
T2 - IEICE TRANSACTIONS on Information
SP - 90
EP - 92
AU - Fa-Xin YU
AU - Zhe-Ming LU
AU - Zhen LI
AU - Hao LUO
PY - 2009
DO - 10.1587/transinf.E92.D.90
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2009
AB - In this Letter, we propose a novel method of low-level global motion feature description based on Vector Quantization (VQ) index histograms of motion feature vectors (MFVVQIH) for the purpose of video shot retrieval. The contribution lies in three aspects: first, we use VQ to eliminate singular points in the motion feature vector space; second, we utilize the global motion feature vector index histogram of a video shot as the global motion signature; third, video shot retrieval based on index histograms instead of original motion feature vectors guarantees the low computation complexity, and thus assures a real-time video shot retrieval. Experimental results show that the proposed scheme has high accuracy and low computation complexity.
ER -