Rule-based scene boundary detection for semantic video segmentation

In this paper, we present a technique for semantic video segmentation. Our technique uses a combination of low-level features and high-level rules which organizes the video into scenes, shots and key-frames. Features in color domain is calculated and utilized for detecting the key-frames and estimating the similarity between shots. By applying a set of high-level rules, similar shots are merged and the scene boundaries are determined. Finally, a likelihood function is designed for improving the accuracy of scene boundary results. Experimental results from several Hollywood movies have demonstrated and show a better performance of both precision and recall has been achieved comparing with other existing works.

[1]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[2]  William J. Christmas,et al.  Video Shot Cut Detection using Adaptive Thresholding , 2000, BMVC.

[3]  Janko Calic,et al.  A rule-based video annotation system , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Chong-Wah Ngo,et al.  Video summarization and scene detection by graph modeling , 2005, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Majid Mirmehdi,et al.  Temporal video segmentation and classification of edit effects , 2003, Image Vis. Comput..

[6]  Mubarak Shah,et al.  Detection and representation of scenes in videos , 2005, IEEE Transactions on Multimedia.

[7]  N. Nikolaidis,et al.  Video shot detection and condensed representation. a review , 2006, IEEE Signal Processing Magazine.

[8]  Hui Fang,et al.  A fuzzy logic approach for detection of video shot boundaries , 2006, Pattern Recognit..

[9]  Jiuyong Li.  Robust rule-based prediction , 2006, IEEE Transactions on Knowledge and Data Engineering.

[10]  Amit Mukherjee,et al.  Detection of pseudosinusoidal epileptic seizure segments in the neonatal EEG by cascading a rule-based algorithm with a neural network , 2006, IEEE Transactions on Biomedical Engineering.

[11]  Kanad K. Biswas,et al.  A fuzzy theoretic approach for video segmentation using syntactic features , 2001, Pattern Recognit. Lett..

[12]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[13]  Chong-Wah Ngo,et al.  Motion-Based Video Representation for Scene Change Detection , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[14]  Hui Fang,et al.  Predictive-based cross line for fast motion estimation in MPEG-4 videos , 2004, IS&T/SPIE Electronic Imaging.

[15]  Masaharu Ogawa,et al.  A highlight scene detection and video summarization system using audio feature for a personal video recorder , 2005, IEEE Transactions on Consumer Electronics.

[16]  Rita Cucchiara,et al.  Linear Transition Detection as a Unified Shot Detection Approach , 2007, IEEE Transactions on Circuits and Systems for Video Technology.