Efficient Measuring of Various Motions in MPEG Videos

J.H. Oh, P. Sankuratri, and W. Tavanapong (USA)


Image Processing and applications, Video Processing, Cam era and object motion detection, MPEG Video.


There is a need to analyze motions in video sequences to characterize them since motion is a representative feature that distinguishes videos from other multimedia. However, the existing approaches can only provide very preliminary classification of motions. To support in-depth measurement of various motions, we need to distinguish the different mo tions generated by the different sources. In this paper, we explicitly distinguish camera and object motions in a shot. In addition to distinguishing motions themselves, we pro pose new techniques to measure not only amount but also di rection of each motion distinguished, and express them into comparable forms. Our preliminary experimental studies in dicate that the proposed techniques are promising.

Important Links:

Go Back