Detection and Classification of Shot Transitions
Author(s) -
Samantha Porter,
Majid Mirmehdi,
Bjorn Thomas
Publication year - 2001
Publication title -
citeseer x (the pennsylvania state university)
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5244/c.15.9
Subject(s) - shot (pellet) , computer science , artificial intelligence , inter frame , computer vision , search engine indexing , motion estimation , block (permutation group theory) , block matching algorithm , object detection , process (computing) , change detection , frame (networking) , pattern recognition (psychology) , object (grammar) , video tracking , reference frame , mathematics , telecommunications , chemistry , geometry , organic chemistry , operating system
The process of shot break detection is a fundamental component in automatic video indexing, editing and archiving. This paper introduces a novel approach to the detection and classification of shot transitions in video sequences including cuts, fades and dissolves. It uses the average interframe correlation coefficient and block-based motion estimation to track image blocks through the video sequence and to distinguish changes caused by shot transitions from those caused by camera and object motion. We achieve better results compared with two established techniques.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom