STAR: A Content Based Video Retrieval system for moving camera video shots

Author

Chattopadhyay, Chiranjoy ; Das, S.

Author_Institution

Dept. of Comput. Sci. & Eng., Indian Inst. of Technol., Madras, Chennai, India

fYear

2013

Firstpage

1

Lastpage

4

Abstract

This paper presents the design of STAR (Spatio-Temporal Analysis and Retrieval), an unsupervised Content Based Video Retrieval (CBVR) System. STAR´s key insight and primary contribution is that it models video content using a joint spatio-temporal feature representation and retrieves videos from the database which have similar moving object and trajectories of motion. Foreground moving blobs from a moving camera video shot are extracted, along with a trajectory for camera motion compensation, to form the space-time volume (STV). The STV is processed to obtain the EMST-CSS representation, which can discriminate across different categories of videos. Performance of STAR has been evaluated qualitatively and quantitatively using precision-recall metric on benchmark video datasets having unconstrained video shots, to exhibit efficiency of STAR.

Keywords

content-based retrieval; video cameras; video retrieval; CBVR system; EMST-CSS representation; STAR; content based video retrieval system; joint spatio-temporal feature representation; motion trajectories; moving camera video shots; space-time volume; spatio-temporal analysis and retrieval; Benchmark testing; Cameras; Feature extraction; Shape; Surface treatment; Trajectory; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), 2013 Fourth National Conference on

Conference_Location

Jodhpur

Print_ISBN

978-1-4799-1586-6

Type

conf

DOI

10.1109/NCVPRIPG.2013.6776267

Filename

6776267