A real-time detection for traffic surveillance video shaking
Yaoyao Niu, Danfeng Hong, Zhenkuan Pan, Xin Wu
Available Online March 2014.
- https://doi.org/10.2991/mce-14.2014.35How to use a DOI?
- video shaking; hierarchical; gray projection; correlation coefficient; real-time.
- Shaking happens to the traffic surveillance video inevitably, which can lead to the degradation of monitor system performance. A hierarchical gray project the correlation algorithm (HGPC) is proposed to solve the problem of the shaking in the traffic surveillance video. First, global hierarchical gray project correlation algorithm (GHGPC) is used to detect the video roughly. Then, in order to further improve the detection accuracy, we used the local hierarchical gray project correlation algorithm (LHGPC) to deal with the results from the rough matching. The experiment results on the video library HGTVL database show that the accuracy of the proposed algorithm is 91.4%, which is superior to the previous methods. In addition, the detection time is only 47ms, which meets the real-time requirement. Therefore, it is proved to be effective and feasible to dispose the video shaking.respectively. At last, we gain the fusion image by using the inverse IHS transform on the fusion component I gained by the inverse NSCT transform. Experiments show that our method have better fusion quality and can be more better to keep the visible spectral and detail information than some traditional methods such as, Laplace method, Wavelet method and Lifting Wavelet method.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Yaoyao Niu AU - Danfeng Hong AU - Zhenkuan Pan AU - Xin Wu PY - 2014/03 DA - 2014/03 TI - A real-time detection for traffic surveillance video shaking BT - 2014 International Conference on Mechatronics, Control and Electronic Engineering (MCE-14) PB - Atlantis Press SP - 160 EP - 164 SN - 1951-6851 UR - https://doi.org/10.2991/mce-14.2014.35 DO - https://doi.org/10.2991/mce-14.2014.35 ID - Niu2014/03 ER -