Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
An integrated scheme for object-based video abstraction
MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
IEEE Transactions on Pattern Analysis and Machine Intelligence
Video Skimming and Characterization through the Combination of Image and Language Understanding
CAIVD '98 Proceedings of the 1998 International Workshop on Content-Based Access of Image and Video Databases (CAIVD '98)
Real-Time Multiple Objects Tracking with Occlusion Handling in Dynamic Scenes
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Multimedia Tools and Applications
Making a Long Video Short: Dynamic Video Synopsis
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Video summarization with visual and semantic features
PCM'10 Proceedings of the 11th Pacific Rim conference on Advances in multimedia information processing: Part I
Key observation selection-based effective video synopsis for camera network
Machine Vision and Applications
| Hi-index | 0.00 |
A synopsis video presents a condensed video activities occurring during different periods, based on moving objects extracted in the spatial-temporal domain. How to place different object tubes with least collision in limited video length is crucial to synopsis performance but has not been thoroughly studied in previous work. In this paper, we address an important problem in video synopsis, that of object start-time programming. We formulate the problem in terms of set theory. An objective is derived to maximize visual information in video synopsis. After relaxing the problem to obtain a continuous one, the problem can be efficiently solved via mean-shift. The resulting algorithm can converge to the local optimum within a few iterations.