Scene context dependent key frame selection in streaming

A.G. Nguyen1, Jenq-Neng Hwang2
1Boeing Company, Seattle, WA, USA
2Information Processing lab, Department of EE, University of Washington, Seattle, WA, USA

Tóm tắt

In this paper, we describe the development of our scene context dependent key frame selection method to reduce the amount of recorded video data. We propose the use of motion analysis (MA) to adapt to scene content in our key frame selection process. Based on the information generated by the motion analysis stage, frames in the video sequence which contain significant motion information are selected to retain for recording. We also show that our proposed method performs better than the traditional time-lapse recording method.

Từ khóa

#Layout #Video recording #Motion analysis #Surveillance #Image motion analysis #Multimedia systems #Cameras #Optical computing #Weather forecasting #Multimedia databases

Tài liệu tham khảo

1991, Coding of Moving Pictures and Associated Audio for Digital Storage Media at up to about 1 5 Mbs 0, Video coding for low bit rate communication 10.1145/500141.500188 nguyen, 2001, SPEM Rate Control, IEEE PCM Conference on Multimedia 2001 10.1016/0004-3702(81)90024-2 xu, 0, Motion and Optical flow in Robot Vision 10.1109/TPAMI.1980.4767032 10.1016/S0734-189X(83)80030-9 10.1364/JOSAA.2.000284 glazer, 1983, Scene Matching By Hierarchical Correlation, Proc IEEE CVPR, 432 sato, 1997, Multimedia Systems for Industrial Surveillance, Proc SPIE Intl Soc Opt Eng, 3020, 182 10.1109/76.754777 10.1364/JOSAA.2.000322