Title :
Video Retrieval Based on Tracked Features Quantization
Author :
Kubo, Hiroaki ; Pilet, Julien ; Saito, Hideo ; Satoh, Shin´ichi
Author_Institution :
Grad. Sch. of Sci. & Technol., Keio Univ., Tokyo, Japan
Abstract :
In this paper, we present an image retrieval method based on feature tracking. Feature tracks are summarized into a compact discreet value and used for video indexing purpose. As opposed to existing space-time features, we do not make any assumption on the motion visible on the indexed videos. As a result, given an example query, our system is able to retrieve related videos from a large database. We evaluated our system with the copy detection benchmark MUSCLE-VCD-2007. We also ran retrieval experiment on hours of TV broadcast.
Keywords :
feature extraction; indexing; quantisation (signal); video retrieval; compact discreet value; copy detection benchmark MUSCLE-VCD-2007; features quantization; image retrieval method; space time features; video indexing purpose; video retrieval; Benchmark testing; Feature extraction; Histograms; Indexes; Motion pictures; Prototypes; Content based retrieval; Descriptor; Quantization; Video retrieval;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.794
