Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Physical Sciences and Mathematics
Motion-Based Video Representation For Scene Change Detection, Chong-Wah Ngo, Ting-Chuen Pong, Hong-Jiang Zhang, Roland T. Chin
Motion-Based Video Representation For Scene Change Detection, Chong-Wah Ngo, Ting-Chuen Pong, Hong-Jiang Zhang, Roland T. Chin
Research Collection School Of Computing and Information Systems
We present a new ly developed scheme for automatical ly partitioning videos into scenes. A scene is general ly referred to as a group of shots taken place in the same site. In this paper, we first propose a motion annotation algorithm based on the analysis of spatiotemporal image volumes. The algorithm characterizes the motions within shots by extracting and analyzing the motion trajectories encoded in the temporal slices of image volumes. A motion-based keyframe computing and selection strategy is thus proposed to compactly represent the content of shots. With these techniques, we further present a scene change detection algorithm …
Motion Characterization By Temporal Slices Analysis, Chong-Wah Ngo, Ting-Chuen Pong, Hong-Jiang Zhang, Roland T. Chin
Motion Characterization By Temporal Slices Analysis, Chong-Wah Ngo, Ting-Chuen Pong, Hong-Jiang Zhang, Roland T. Chin
Research Collection School Of Computing and Information Systems
This paper describes an approach to characterize camera and object motions based on the analysis of spatio temporal image volumes. In the spatio-temporal slices of image volumes, motion is depicted as oriented patterns. We propose a tensor histogram computation algorithm to represent these oriented patterns. The motion trajectories in a histogram are tracked to describe both the camera and object motions. In addition, we exploit the similarity of the temporal slices in a volume to reliably partition a volume into motion tractable units.
Predictive Adaptive Resonance Theory And Knowledge Discovery In Databases, Ah-Hwee Tan, Hui-Shin Vivien Soon
Predictive Adaptive Resonance Theory And Knowledge Discovery In Databases, Ah-Hwee Tan, Hui-Shin Vivien Soon
Research Collection School Of Computing and Information Systems
This paper investigates the scalability of predictive Adaptive Resonance Theory (ART) networks for knowledge discovery in very large databases. Although predictive ART performs fast and incremental learning, the number of recognition categories or rules that it creates during learning may become substantially large and cause the learning speed to slow down. To tackle this problem, we introduce an on-line algorithm for evaluating and pruning categories during learning. Benchmark experiments on a large scale data set show that on-line pruning has been effective in reducing the number of the recognition categories and the time for convergence. Interestingly, the pruned networks also …