Paper Info
Title
Video Copy Detection Using Inclined Video Tomography and Bag-of-Visual-Words
Abstract
Techniques for video fingerprinting are helpful in managing vast libraries of video clips. Recent advances have shown that video tomography and Bag-of-Visual-Words (BoVW) can be successfully used for the purpose of video fingerprinting. In this paper, we introduce a novel video signature (i.e., a novel video fingerprint) that takes advantage of both video tomography and BoVW. Specifically, the proposed video signature is created by first extracting inclined tomography images from the video content, and by subsequently applying the BoVW approach to the inclined tomography images obtained. The key to our approach is that we make the angle of inclination of the tomography images dependent on the amount of motion in the video content. That way, the proposed video signature is able to capture both spatial and temporal information. Experimental results obtained for the publicly available TREVID-2009 video set indicate that video copy detection by means of the proposed video signature is robust against spatial and temporal transformations.
Year
DOI
Venue
2012
10.1109/ICME.2012.58
ICME
Keywords
Field
DocType
video clip,video fingerprinting,video tomography,video content,video copy detection,novel video fingerprint,trevid-2009 video,inclined video tomography,novel video signature,inclined tomography image,proposed video signature,bag of visual words,fingerprint identification,object recognition,feature extraction,image segmentation,tomography,fingerprint recognition,visualization,histograms
Object detection,Computer vision,Video post-processing,Pattern recognition,Computer science,Motion compensation,Multiview Video Coding,Video tracking,Artificial intelligence,Video copy detection,Video compression picture types,Uncompressed video
Conference
Citations 
PageRank 
References 
6
0.41
18
Authors
4
Name
Order
Citations
PageRank
Hyunseok Min1557.87
Se Min Kim260.41
Wesley De Neve352554.41
Yong Man Ro41192125.87