The Research of Intelligent Vehicles Mean Shift Based on Difference Algorithm

Article Preview

Abstract:

The workflow of mean shift has been put forward which is aimed at the intelligent vehicles. To select the logical parameter, the simulation of the formwork and the selection of search region is made; and select the most suitable algorithm of the three related algorithms through the simulation analysis; in addition, to achieve the binary image by difference and denoising, to obtain the energy distribution of the image by calculating the gravity centre of the projection, then proceed to the next step, to gain the target location. So the feasibility of the algorithm can be validated by the test, and the good results are obtained.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

323-330

Citation:

Online since:

February 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Z. Cheng, P. Zhang. The Third Generation of TV Tracking Algorithm Based on Multi-Trace Processing(TMTP). Acta Electronica Sinica, 2003, 31(3): 361-364.

Google Scholar

[2] L. Zheng, C. Han, D. Zuo. A Multi-Mode Image Tracking System Based on Distributed Fusion. Systems Engineering and Electronics, 2002, 24(12): 1-4.

Google Scholar

[3] Ahmed J. Tafri M N, AhmadJ. Target tracking in an image sequence using wavelet features and a neural network. IEEE Transon Technology. 2005: l-6.

Google Scholar

[4] H. Li, B.S. Manjunath, S.K. Mitra, Multi-sensor Image Fusion Using the Wavelet Transform. Graphical Model and Image Processing[J], 57(1995) : 235-245.

DOI: 10.1006/gmip.1995.1022

Google Scholar

[5] S. Wu, G. Liao, B. Z. Advanced Technology on Radar Signal Processing. Radar[J], 2001 CIE International Conference on, Proceedings, 15-18 Oct. 2001: 16-19.

DOI: 10.1109/icr.2001.984615

Google Scholar

[6] Lee C H, et al. Automatic human face detection in a complex background using motion and color information. Pattern Recognition, 1996, 29(11) : 1877-1889.

DOI: 10.1016/0031-3203(96)00036-2

Google Scholar

[7] Vasileios Mezaris, Ioannis Kompatsiaris, Nikolaos V. Boulgouris and Michael G. Strintzis, Real-Time Compressed-Domain Spatiotemporal Segmentation and Ontologies for Video Indexing and Retrieval, IEEE Tansactions on Circuits and Systens For Viedo Technology, Vol. 14, No. 5, May (2004).

DOI: 10.1109/tcsvt.2004.826768

Google Scholar

[8] Brais Martinez,Xavie Binefa. Piecewise affine kernel tracking for non-planar targets[J, Pattern Reeognition, 2008, 12(3): (365~369).

DOI: 10.1016/j.patcog.2008.06.001

Google Scholar

[9] Vasileios Mezaris, Ioannis Kompatsiaris and Michael G. Strintzis, Video Object Segmentation Using Bayes-Based Temporal Tracking and Trajectory-Based Region Merging, IEEE Tansactions on Circuits and Systens For Viedo Technology, Jun 2004, Vol. 14, No. 6.

DOI: 10.1109/tcsvt.2004.828341

Google Scholar

[10] Chang Kim, Jenq-Neng Hwang. Fast and Automatic Video Object Segmentation and Tracking for Content-Based Applications, IEEE Trans on Circuits and Systems for Video Technology, vol. 12, no. 2, pp.122-129, Feb (2002).

DOI: 10.1109/76.988659

Google Scholar

[11] R. Knepper. SIRIUS, a long range infrared search and track system. Proe. SPIE. vol. 3061: 578 – 584, (1997).

DOI: 10.1117/12.280376

Google Scholar

[12] Joseph E. Misanin. USN shipboard infrared search and track (IRST) Program. Proe. SPIE. vol. 3061: 436-442, (1997).

DOI: 10.1117/12.280362

Google Scholar