Camera Take Reconstruction

By Maia Zaharieva, Matthias Zeppelzauer, Christian Breiteneder, and Dalibor Mitrovic

Abstract

In this paper we focus on a novel issue in the field of video retrieval stemming from film analysis, namely the investigation of film montage patterns. For this purpose it is first necessary to reconstruct the original film sequences, i.e. the camera takes. For the decision whether or not two shots occurring anywhere in a film stem from the same take we use edge histograms and local feature tracking. Evaluation results on experimental film material (where montage patterns are of great importance) show a very good performance of the algorithm proposed.

Reference

M. Zaharieva, M. Zeppelzauer, C. Breiteneder, D. Mitrovic: "Camera Take Reconstruction"; Talk: Multimedia Modeling Conference, Chongqing, China; 01-06-2010 - 01-08-2010; in: "Advances in Multimedia Modeling", Springer, Lecture Notes in Computer Science, 5916 (2010), ISBN: 978-3-642-11300-0; 379 - 388.

BibTeX

@inproceedings{TUW-181928,     author = {Zaharieva, Maia and Zeppelzauer, Matthias and Breiteneder, Christian and Mitrovic, Dalibor},     title = {Camera Take Reconstruction},     booktitle = {Advances in Multimedia Modeling},     year = {2010},     pages = {379--388},     publisher = {Springer},     address = {Lecture Notes in Computer Science, 5916},     url = {http://publik.tuwien.ac.at/files/PubDat_181928.pdf},     isbn = {978-3-642-11300-0},     doi = {10.1007/978-3-642-11301-7},     note = {Vortrag: Multimedia Modeling Conference, Chongqing, China; 2010-01-06 -- 2010-01-08} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.