Research on the Mean Shift Target Tracking and Recognition Technology Based on Multi-Feature Fusion

Abstract:

This article topics based on multi-feature fusion the Mean shift target tracking technology belongs to the field of intelligent video analysis, moving target tracking is interested in moving target location each image in a video sequence to find and acquire the target movement. Moving target tracking problem can be stated as interested in moving target movement prediction in the video sequence, feature extraction, feature matching and template update problem. In this paper, we consider using compressed domain features as a complement of the color features to extract the compressed domain features first need to understand the compressed domain detection technology. Detection based on the compressed domain, that is, in the case of not decoding or a small amount of decoding, directly on the compression characteristics of the image analysis, in order to achieve the detection of the image moving object.

• Periodical: Advanced Materials Research (Volume 705)
• Pages: 561-564
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.705.561
• Online since: June 2013
• Authors: Yong Jun Peng, Fen Tan, Jun Sun
• Keywords: Mean-Shift, Multi-Feature Fusion, Target Recognition, Target Tracking

References

[1] D. COMANICIU, P. MEER. Mean shift analysis and application [J]. Proceedings of the Seventh IEEE International Conference Computer Vision 1999: 2: 1197-1203.

DOI: 10.1109/iccv.1999.790416

[2] Yilmaz A, Shafique K, Shah M. Target tracking in airborne forward looking infrared imagery. Int'l Journal of Image and Vision Computing, 2003,21(7):623−635.

DOI: 10.1016/s0262-8856(03)00059-3

[3] Comaniciu D,Ramesh V,Meer P.The variable bandwidth mean shift and data-driven scale selection[A].8thIntl Conf on Computer Vision[C].2001,1:438-445.

DOI: 10.1109/iccv.2001.937550

[4] Comaniciu D,Meer P.Mean shift:A robust application toward feature space analysis[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.

DOI: 10.1109/34.1000236

[5] Peng NingSong, Yang Jie, eta. Automatic Selection of Kernel-Bandwidth for Mean-Shift Object Tracking[J]. Journal of Software，2005，16（9）：1542~1550.

DOI: 10.1360/jos161542

[6] Shi Ying Adaptive feature-spatial representation for mean-shift tracker. Proceedings - International Conference on Image Processing, ICIP. 2008, 2008, pp:2012-2015.

DOI: 10.1109/icip.2008.4712179

[7] Li Peihua. An adaptive binning color model for mean shift tracking. IEEE Transactions on Circuits and Systems for Video Technology, September 2008, pp: 1293-1299.

DOI: 10.1109/tcsvt.2008.928528