Video editing based on object movement and camera motion

Authors:
Yang Wang;Masahito Hirakawa
Affiliations:
Beijing Forestry University, Beijing, China;Shimane University, Matsue, Japan
Venue:
Proceedings of the working conference on Advanced visual interfaces
Year:
2006

Citing 9
Cited 1

W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
A semi-automatic approach to home video editing

UIST '00 Proceedings of the 13th annual ACM symposium on User interface software and technology
M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Moving Object Tracking in Video

AIPR '00 Proceedings of the 29th Applied Imagery Pattern Recognition Workshop
W4: Who? When? Where? What? A Real Time System for Detecting and Tracking People

FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Adaptive Tracking of Multiple Non Rigid Objects in Cluttered Scenes

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Proscenium: a framework for spatio-temporal video editing

MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Gesture Tracking and Recognition for Lecture Video Editing

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Continuous tracking within and across camera streams

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Automated aesthetic enhancement of videos

Proceedings of the international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

The advancement of computer technology makes video devices/equipments powerful and inexpensive, and thereby the number of applications that can effectively utilize digital videos is increasing.In this paper, the authors propose a new type of video editing, which is based on the movement of objects. A video shot is automatically edited so that the selected objects are placed and kept at the center of the frames to make the resultant video more attractive. Ideally this is interpreted as applying pan, tilt, and/or zoom operations into a source video as post-conditions in video editing. Implementation issues for realization of this facility are also presented in this paper.