Video retrieval based on scene change detection in compressed streams

This paper presents a new key frame extraction algorithm as well as a novel video-indexing scheme for a fast content-based browsing and retrieval in a video database. We first extract key frames by matching the AHIM (accumulated histogram intersection measure) of the DC image sequence constructed from the MPEG video sequence. Then we use the region segmentation-based projective histogram and its moments as database indices for video retrieval.

[1]  Yucel Altunbasak,et al.  Key frame selection from MPEG video data , 1997, Electronic Imaging.

[2]  Nilesh V. Patel,et al.  Video shot detection and characterization for video databases , 1997, Pattern Recognit..

[3]  Akio Yoneyama,et al.  Universal scene change detection on MPEG-coded data domain , 1997, Electronic Imaging.

[4]  Anil K. Jain,et al.  Image retrieval using color and shape , 1996, Pattern Recognit..

[5]  Boon-Lock Yeo,et al.  Rapid scene analysis on compressed video , 1995, IEEE Trans. Circuits Syst. Video Technol..

[6]  Georgy L. Gimel'farb,et al.  On retrieving textured images from an image database , 1996, Pattern Recognit..