A Feature Extraction Strategy Based on Multiple Color Information


Article Preview

In this paper, a feature extraction strategy based on multiple color information fusion was proposed. Firstly this method started with analyzing the transform formula of color space, which transform was mainly thinking about RGB color space to other color spaces. Secondly by analyzing the characteristic of every color space in describing the actual color information, the advantages and disadvantages of every color space were showed. Thirdly through above conclusion, the algorithm which extracted the target feature only using single color information was defective, and then the strategy based on multiple color information fusion was proposed. Lastly the detail fusion strategy was given, which fused the probability distributed information of multiple color into the last probability distributed information as the target feature. The feature extraction strategy in this paper is verified by the camshift algorithm. The results show that the multiple color information fusion can improve the tracking performance of moving target.



Advanced Materials Research (Volumes 433-440)

Edited by:

Cai Suo Zhang




Y. B. Han et al., "A Feature Extraction Strategy Based on Multiple Color Information", Advanced Materials Research, Vols. 433-440, pp. 6175-6181, 2012

Online since:

January 2012




[1] Jong Bae Kin and Hang Joon Kin, Efficient region-based motion Segmentation for a video monitoring system, Pattern Recognition Letters, vol. 24, p.113–128, (2003).

DOI: https://doi.org/10.1016/s0167-8655(02)00194-0

[2] Wan Min, Guo Baolong, and Liu Xiaoding, Research of A Video Object Detection Method in MPEG-4, Modern Electronics Technique, vol. 5, p.62–64, (2005).

[3] G Sasa, and S Loncaric, Spatio-temporal image segmentation using optical flow and clustering algorithm, " First Int, lWork-shop on Image and signal Processing and Analysis, Pula, Croatia, p.63–68, (2000).

[4] P W Power, and J A Schoonees, Understanding background mixture models for foreground segmentation, In proceedings of Imag and Vision Computing, Aukland New Zealand, p.267–271, (2003).

[5] Xu Yimei, Guo Baolong, and Chen Long, Moving Objects Detection Based on RGB Color Space and Background Subtraction, Computer Simulation, vol. 25(3), p.214–217, March (2008).

[6] Xu Kun, He Yuyao, and Wang Weiya, Object tracking algorithm with adaptive color space based on CamShift, Journal of Computer Applications, vol. 29(3), p.757–760, March (2009).

DOI: https://doi.org/10.3724/sp.j.1087.2009.00757

[7] HARINI V, PAUL S, and NIKOS P, Robust Target Detection and Trackingthrough Integration of Motion, Color, and Geometry, Computer Vision and Image Understanding, vol. 103(2), p.121–138, (2006).

DOI: https://doi.org/10.1016/j.cviu.2006.04.003

[8] Chu Hongxia, Ye Shujiang, and Guo Qingchang, Object Tracking Algorithm Based on Camshift Algorithm Combinating with Difference in Frame, Proceedings of the IEEE International Conference on Automation and Logistics, China, (2007).

DOI: https://doi.org/10.1109/ical.2007.4338529

[9] Liu Xia, Chu Hongxia, and Li Pingjun, Research of the Improved Camshift Tracking Algorithm, Proceedings of the 2007 IEEE International Conference on Mehatronics and Automation, China, (2007).

DOI: https://doi.org/10.1109/icma.2007.4303678

[10] Bogdan Kwolek, CamShift-based tracking in joint color-spatial spaces, Computer Analysis of Images and Patterns, p.693–700, (2005).

DOI: https://doi.org/10.1007/11556121_85

[11] Han Yanbin, and Li Jinping, An Approach for Face Recognition Based on Local Feature, Journal of University Jinan (Science And Technology), vol. 27(1), p.56–59, (2007).

[12] Han Yanbin, Liu Mingjun, and Li Jinping, Face detection and location based on skin-color modeling and geometric features, Computer Science, vol. 33(10A), p.311–314, (2006).

Fetching data from Crossref.
This may take some time to load.