Key Frame Extraction in 3D Video by Rate-Distortion Optimization

Author

Xu, Jianfeng ; Yamasaki, Toshihiko ; Aizawa, Kiyoharu

Author_Institution

Dept. of Electron. Eng., Tokyo Univ.

fYear

2006

fDate

9-12 July 2006

Firstpage

1

Lastpage

4

Abstract

3D video, which consists of a sequence of 3D mesh models, can provide detailed 3D information both in spatial and temporal domain. In this paper, a key frame extraction method has been developed to summarize 3D video by rate-distortion optimization. For this purpose, we introduce an effective feature vector extraction algorithm from 3D video. Prior to key frame extraction, shot detection is performed using the feature vectors as a pre-processing. Then, a rate-distortion (R-D) curve is generated in each shot, where the locations of key frames are optimized. Lastly, R-D trade-off can be achieved by optimizing a cost function with a Lagrange multiplier. Our experimental results show the extracted key frames are compact and faithful to original 3D video

Keywords

feature extraction; optimisation; rate distortion theory; video signal processing; 3D video; Lagrange multiplier; feature vector extraction algorithm; key frame extraction method; rate-distortion optimization; shot detection; Cost function; Data mining; Feature extraction; Gunshot detection systems; Histograms; Lagrangian functions; Rate distortion theory; Rate-distortion; Video sequences; Video sharing;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2006 IEEE International Conference on

Conference_Location

Toronto, Ont.

Print_ISBN

1-4244-0366-7

Electronic_ISBN

1-4244-0367-7

Type

conf

DOI

10.1109/ICME.2006.262499

Filename

4036521