Towards a Standard Protocol for the Evaluation of Video-to-Shots Segmentation Algorithms

This paper proposes a general framework to evaluate and compare several temporal video segmentation algorithms. The problems that must be solved to confront different methods summarize as gathering a common content set to test the methods, building a reference segmentation, establishing the rules to match the results with the reference, and providing a quality measure. Some solutions to these problems are given in this study and are applied for evaluating different methods developed in various contexts. The paper concludes by presenting results obtained on practical tests. This study was made by a work group of AIM (Multimedia Indexation Action) Working Group 10 of the ISIS Coordinated Research Program.

[1]  P. Joly,et al.  The automatic real-time analysis of film editing and transition effects and its applications , 1994, Comput. Graph..

[2]  A. Del Bimbo,et al.  Film semantic analysis , 1995, Proceedings of Conference on Computer Architectures for Machine Perception.

[3]  John S. Boreczky,et al.  Comparison of video shot boundary detection techniques , 1996, Electronic Imaging.

[4]  Thomas D. C. Little,et al.  A Survey of Technologies for Parsing and Indexing Digital Video1 , 1996, J. Vis. Commun. Image Represent..

[5]  John D. Lafferty,et al.  Text Segmentation Using Exponential Models , 1997, EMNLP.

[6]  Sethuraman Panchanathan,et al.  Review of Image and Video Indexing Techniques , 1997, J. Vis. Commun. Image Represent..

[7]  Riccardo Leonardi,et al.  Scene break detection: a comparison , 1998, Proceedings Eighth International Workshop on Research Issues in Data Engineering. Continuous-Media Databases and Applications.

[8]  Michael J. Witbrock,et al.  Story segmentation and detection of commercials in broadcast news video , 1998, Proceedings IEEE International Forum on Research and Technology Advances in Digital Libraries -ADL'98-.

[9]  Georges Quénot,et al.  Two Systems for Temporal Video Segmentation , 1999 .