Finding the optimal temporal partitioning of video sequences

The existing techniques for shot partitioning either process each shot boundary independently or proceed sequentially. The sequential process assumes the last shot boundary is correctly detected and utilizes the shot length distribution to adapt the threshold for detecting the next boundary. These t...

Full description

Bibliographic Details
Main Authors: Truong, Ba, Venkatesh, Svetha
Other Authors: SuviSoft Oy Ltd
Format: Conference Paper
Published: IEEE Computer Society Press 2005
Online Access:http://hdl.handle.net/20.500.11937/25202
_version_ 1848751642541817856
author Truong, Ba
Venkatesh, Svetha
author2 SuviSoft Oy Ltd
author_facet SuviSoft Oy Ltd
Truong, Ba
Venkatesh, Svetha
author_sort Truong, Ba
building Curtin Institutional Repository
collection Online Access
description The existing techniques for shot partitioning either process each shot boundary independently or proceed sequentially. The sequential process assumes the last shot boundary is correctly detected and utilizes the shot length distribution to adapt the threshold for detecting the next boundary. These techniques are only locally optimal and suffer from the strong assumption about the correct detection of the last boundary. Addressing these fundamental issues, in this paper, we aim to find the global optimal shot partitioning by utilizing Bayesian principles to model the probability of a particular video partition being the shot partition. A computationally efficient algorithm based on dynamic programming is then formulated. The experimental results on a large movie set show that our algorithm performs consistently better than the best adaptive-thresholding technique commonly used for the task.
first_indexed 2025-11-14T07:55:58Z
format Conference Paper
id curtin-20.500.11937-25202
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:55:58Z
publishDate 2005
publisher IEEE Computer Society Press
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-252022017-09-13T15:19:35Z Finding the optimal temporal partitioning of video sequences Truong, Ba Venkatesh, Svetha SuviSoft Oy Ltd The existing techniques for shot partitioning either process each shot boundary independently or proceed sequentially. The sequential process assumes the last shot boundary is correctly detected and utilizes the shot length distribution to adapt the threshold for detecting the next boundary. These techniques are only locally optimal and suffer from the strong assumption about the correct detection of the last boundary. Addressing these fundamental issues, in this paper, we aim to find the global optimal shot partitioning by utilizing Bayesian principles to model the probability of a particular video partition being the shot partition. A computationally efficient algorithm based on dynamic programming is then formulated. The experimental results on a large movie set show that our algorithm performs consistently better than the best adaptive-thresholding technique commonly used for the task. 2005 Conference Paper http://hdl.handle.net/20.500.11937/25202 10.1109/ICME.2005.1521638 IEEE Computer Society Press restricted
spellingShingle Truong, Ba
Venkatesh, Svetha
Finding the optimal temporal partitioning of video sequences
title Finding the optimal temporal partitioning of video sequences
title_full Finding the optimal temporal partitioning of video sequences
title_fullStr Finding the optimal temporal partitioning of video sequences
title_full_unstemmed Finding the optimal temporal partitioning of video sequences
title_short Finding the optimal temporal partitioning of video sequences
title_sort finding the optimal temporal partitioning of video sequences
url http://hdl.handle.net/20.500.11937/25202