Moving Target Detection Based on Principle of Connectivity and Texture Gradient

Article Preview

Abstract:

In target detection, “hole” phenomenon is present in the detection result, and the shadow is difficult to remove. To solve these problems, we propose a target detection algorithm based on principle of connectivity and texture gradient. Firstly, we use the connectivity principle to find the largest target prospects connection area to get a complete target contour, secondly we use target texture gradient information to further remove the shadow of the target. At last, the experimental results show that the algorithm can obtain a clear target profile and improve the accuracy of the moving target segmentation.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 605-607)

Pages:

2117-2120

Citation:

Online since:

December 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] I. Haritaoglu, D. Harwood, L. Davis: IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 22 (2000), p.809–830.

DOI: 10.1109/34.868683

Google Scholar

[2] Junchao Yin, Zhifang Liu: Computer Engineering and Design. Vol. 32(2011), pp.2817-2820. In Chinese.

Google Scholar

[3] A. SH. Lim, A. EI. Jamal. International Conference on Image Processing. Vol. 10 (2001), pp.925-931.

Google Scholar

[4] Jing Zhang, Yongmei Cheng: Computer Measurement and Control. Vol. 18 (2010), pp.1139-1141. In Chinese.

Google Scholar

[5] Xueyou Hu, Liang Tao, Minsheng Ni: Computer Applications. Vol. 31(2011), pp.1602-1608. In Chinese.

Google Scholar

[6] Stocker: IEEE International Symposium on Circuits and Systems. Vol. 5 (2002), pp.25-28.

Google Scholar

[7] Yang Xu, Chengdong Wu, Dongyue Chen: Application Research of Computers. Vol. 28 (2011), pp.1206-1209. In Chinese.

Google Scholar