Video Synopsis Generation Using GPGPU

Zong Yue Wang

doi:10.4028/www.scientific.net/AMM.433-435.297

Paper Titles

Study on Image Corner Extraction Based on the Improved Canny Edge Detector
p.273

A Pattern Recognition Method Based on Modified Perception Algorithm
p.277

Sub-Pixel Edge Detection of Color Image Based on Dimensionality Reduction Technique and Curve Fitting
p.281

A Novel Threshold Selection Method Based on Iterative Clustering Strategy
p.288

Video Synopsis Generation Using GPGPU
p.297

A New Adaptive Image Denoising Method Based on Wavelet Packet Transform and Neighbor Dependency
p.301

An Improved Compressive Sensing Image Fusion Algorithm Based on NSCT Transform
p.306

3D Subtitles Superimposed Technical Overview
p.310

Adjustment Method between Phonological Attributes and Phone Boundaries
p.316

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 433-435Video Synopsis Generation Using GPGPU

Video Synopsis Generation Using GPGPU

Abstract:

Video summaries provide a compact video representation preserving the essential activities of the original video, but the summaries may be confusing when mixing different activities together. Summaries Clustered methodology, showing similar activities simultaneously, enables to view much easier and more efficiently. However, it is very time consuming in generating summaries, especially in calculating motion distance and collision cost. To improve the efficiency of generating summaries, a parallel video synopsis generation algorithm is proposed based on GPGPU. The experiment result shows generation efficiency is improved greatly through GPU parallel computing. The acceleration radio can reach at 5.75 when data size is above 1600*960*30000.

You might also be interested in these eBooks

Advances in Mechatronics and Control Engineering II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 433-435)

Pages:

297-300

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.433-435.297

Citation:

Cite this paper

Online since:

October 2013

Authors:

Zong Yue Wang

Keywords:

GPGPU, Parallel, Summarization, Video Synopsis

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Pope A., Kumar R., Sawhney H., Wan C.: Video abstraction: Summarizing video content for retrieval and visualization. Proc. Thirty-Second Asilomar Conference on Signals, Systems & Computers, (1998), pp.915-919.

DOI: 10.1109/acssc.1998.751015

Google Scholar

[2] Zhu X., Wu X., Fan J., Elmagarmid A. K., Aref W. G.: Exploring video content structure for hierarchical summarization. Multimedia Systems, Vol. 10(2004), pp.98-115.

DOI: 10.1007/s00530-004-0142-7

Google Scholar

[3] Bennett E. P., McMillan L.: Computational time-lapse video. ACM Transactions on Graphics (TOG), Vol. 26 (2007), p.102.

DOI: 10.1145/1276377.1276505

Google Scholar

[4] White Papers: Video Synopsis Technology http: /briefcam. com/company/technology.

Google Scholar

[5] Pritch Y., Ratovitch S., Hendel A., Peleg S.: Clustered synopsis of surveillance video. Advanced Video and Signal Based Surveillance, AVSS'09, (2009), pp.195-200.

DOI: 10.1109/avss.2009.53

Google Scholar

[6] Information on http: /www. nvidia. com/object/cuda_home_new. html.

Google Scholar