DocumentCode
2803658
Title
Notice of Retraction
Particle Filter Tracking Algorithm Based on Multi-Information Fusion
Author
Cheng Shu-hong ; Hu Chun-hai
Author_Institution
Coll. of Electr. Eng., Yanshan Univ., Qinhuangdao, China
fYear
2009
fDate
19-20 Dec. 2009
Firstpage
1
Lastpage
4
Abstract
Notice of Retraction
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Traditional color histogram-based PF was unstable only using the color information. The particle filter tracking algorithm proposed in our paper is based on multi-information fusion, which combining structural similarity index (SSIM)and scale invariant feature transform (SFIT), SSIM was used to measure target similarity between two frames in correlation tracking and the color distribute the particle weighting comprehensively, through SIFT we extract the object´s local keypoints, what may based on to update the particle weighting by distance kernel function, dealing with in the condition of cluttered background, object and the background´s color similarity and illumination changes etc, tracking the interested object accurately. The experiments present that our algorithm can track the targets more robustly and adaptively than the traditional algorithm using the same particles.
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Traditional color histogram-based PF was unstable only using the color information. The particle filter tracking algorithm proposed in our paper is based on multi-information fusion, which combining structural similarity index (SSIM)and scale invariant feature transform (SFIT), SSIM was used to measure target similarity between two frames in correlation tracking and the color distribute the particle weighting comprehensively, through SIFT we extract the object´s local keypoints, what may based on to update the particle weighting by distance kernel function, dealing with in the condition of cluttered background, object and the background´s color similarity and illumination changes etc, tracking the interested object accurately. The experiments present that our algorithm can track the targets more robustly and adaptively than the traditional algorithm using the same particles.
Keywords
image colour analysis; image fusion; particle filtering (numerical methods); transforms; color histogram; color similarity; distance kernel function; illumination changes; multiinformation fusion; particle filter tracking algorithm; particle weighting; scale invariant feature transform; structural similarity index; Colored noise; Data mining; Educational institutions; Kernel; Lighting; Noise measurement; Particle filters; Particle measurements; Particle tracking; Target tracking;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Engineering and Computer Science, 2009. ICIECS 2009. International Conference on
Conference_Location
Wuhan
Print_ISBN
978-1-4244-4994-1
Type
conf
DOI
10.1109/ICIECS.2009.5362579
Filename
5362579
Link To Document