Abstract
The dynamic video abstract is an important part of video content analysis. Firstly, the objective of motion is analyzed, and the objective of the movement is extracted. Then, the moving trajectory of each target is analyzed, and different targets are spliced into a common background scene, and they are combined in some way. The algorithm uses Gaussian mixture model and particle filter to do a large number of calculations to achieve the background modeling and the detection of moving object. With the increase of image resolution, the computing increased significantly. To improve the real-time performance of the algorithm, a video abstract algorithm based on CUDA is proposed in this paper. Through the data analysis and parallel mining of the algorithm, time-consuming modules of the calculation, such as Histogram equalization, Gaussian mixture model, particle filter, were implemented in GPU by using massively parallel processing threads to improve the efficiency. The experimental results show that the algorithm can improve the calculation speed significantly in NVIDIA Tesla K20 and CUDA7.5.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Wang, J., Jiang, X., Sun, T.: Summary of video abstract technology. J. Image Graph. 19(12), 1685–1695 (2014)
Tian, H., Ding, S., Yu, C., Zhou, L.: Research on video abstract technology based on target detection and tracking. Comput. Sci. 43(11), 297–312 (2016)
Hua, Y., Liu, W.: Improved Gauss mixture model for moving target detection. J. Comput. Appl. 34(2), 580–584 (2014)
Li, B., Yang, G.: Adaptive foreground extraction of Gauss mixture model. J. Image Graph. 18(12), 1620–1627 (2013)
Li, T., Fan, H., Sun, S.: Particle filter theory and method and its application in multi-target tracking. Acta Autom. Sin. 41(12), 1981–2002 (2015)
Wang, F., Lu, M., Zhao, Q.: Particle filter algorithm. Chin. J. Comput. 37(8), 1679–1694 (2014)
CUDA parallel computing platform [EB/OL]. http://www.nvidia.cn/object/cuda-cn.html
Cook, S.: CUDA parallel programming: guide for GPU programming. In: Su, T., Li, D. (eds.) Translated Version.1, pp. 191–200. Mechanical Industry Press, Beijing (2014)
Jian, L., Wang, C., Liu, Y., et al.: Parallel data mining techniques on Graphics Processing Unit with Compute Unified Device Architecture (CUDA). J. Supercomput. 64(3), 942–967 (2013)
Yang, N.Z., Zhu, Y., Pu, Y.: Parallel image processing based on CUDA. In: 2008 International Conference on Computer Science and Software Engineering, ICCSSE 2008. IEEE Computer Society, California, pp. 198–201 (2008)
Acknowledgments
This work was supported by the Natural Science Foundation of Shandong Province, Grant No. ZR2015YL020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Li, H. et al. (2018). Implementation of Video Abstract Algorithm Based on CUDA. In: Gu, X., Liu, G., Li, B. (eds) Machine Learning and Intelligent Communications. MLICOM 2017. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 227. Springer, Cham. https://doi.org/10.1007/978-3-319-73447-7_43
Download citation
DOI: https://doi.org/10.1007/978-3-319-73447-7_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-73446-0
Online ISBN: 978-3-319-73447-7
eBook Packages: Computer ScienceComputer Science (R0)