多方法融合的粒子滤波算法的神经丝自动跟踪

doi:10.3969/j.issn.1001-2400.2016.04.032

Abstract

Abstract:

The neurofilament protein serves as the marker of the state for ALS (Amyotrophic Lateral Sclerosis) in the medical filed. In order to accurately capture the motion characteristics of the neurofilament protein in the axon, a new-type algorithm based on the particle filtering of multiple methods-fusion is introduced in this paper. This fusion algorithm integrates the advantages of the color histogram, kernel function method, and graph model strength into the particle filtering algorithm. In addition, in order to solve the problem of sample impoverishment, which will lead to the majority of particles overlapping on one single point in the computation of the particle filter, the re-sampling method is utilitied. However, the re-sampling method easily causes the loss of the particle anisotropy, which will reduce the tracking precision or even fail to the track. We present a new re-sampling constrained method to improve the particle anisotropy in the particle filtering. Experimental results indicate that the algorithm based on the improved method of re-sampling and the particle filter of multiple methods-fusion can effectively reduce the number of overlapping particles and precisely track the deformed neurofilament protein. Such a tracking method will be helpful in the research on the neurofilament protein in the medical filed.

Key words: target tracking, importance sampling, multiple methods-fusion, neurofilament protein, particle filtering, re-sampling constraints

JU Gang;YUAN Liang;LIU Xiaoyue. Neurofilament protein automatic tracking of the particle filter algorithm based on multiple methods fusion[J].Journal of Xidian University, 2016, 43(4): 184-190.

References

［1］ WANG H T, WU M F, ZHAN C J. Neurofilament Proteins in Axonal Regeneration and Neurodegenerative Diseases［J］. NEU-RAL Regeneration Research, 2012, 7(8): 620-626.
［2］ ZHU J D, YUAN L. Neurofilament Tracking by Detection in Fluorescence Microscopy Images［C］//Proceedings of 2013 IEEE International Conference on Image Processing. Piscataway: IEEE, 2013: 3123-3127.
［3］ YUAN L, Zheng Y F. Object Tracking With Particle Filtering in Fluorescence Microscopy Images: Application to the Motion of Neurfilaments in Axons［J］. IEEE Transactions on Medical Imaging, 2012, 31(1): 117-130.
［4］袁亮, 朱俊达. 基于检测的荧光显微镜图像中的神经丝蛋白跟踪［J］. 计算机工程与科学, 2013, 37(1): 119-124.
Yuan Liang, Zhu Junda. Neurofilaments Tracking by Detection In Fluorescence Microscopy Images［J］. Computer Engineering ＆ Science, 2013, 37(1): 119-124.
［5］ BAI K J, LIU W M. Improved Object Tracking with Particle Filter and Mean Shift［C］//Proceedings of the IEEE International Conference on Automation and Logistics. Piscataway: IEEE, 2007: 431-435.
［6］ KONG K Y, MARCUS A I, GIANNAKAKOU P, et al. Using Particle Filter to Track and Model Microtubule Dynamics［C］//Proceedings of the IEEE International Conference on Image Processing: 5. Piscataway: IEEE, 2007: 517-520.
［7］ ARULAMPALAM M S, MASKELL S, GORDON N, et al. A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussion Bayesian Tracking［J］. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188.
［8］ JU B, ZHANG Z H, ZHU J B. A Novel Proposal Distribution for Particle Filler［C］//Proceedings of the 2010 3rd International Congress on Image and Signal Processing: 7. Piscataway: IEEE, 2010: 3120-3124.
［9］ SMAL I, GRIGORIEV I. Microtuble Dynamics Analysis Using Kymographs and Variable-Rate Particle Filters［J］. IEEE Transactions on Medical Imaging, 2010, 19(7): 1861-1876.
［10］宋长贺, 李云松, 宁纪锋, 等. 分布场的多特征融合目标跟踪方法［J］. 西安电子科技大学学报, 2015, 42(4): 1-7.
SONG Changhe, LI Yunsong, NING Jifeng, et al. Study of Multi-feature Fusion Methods for Distribution Fields in Object Tracking［J］. Journal of Xidian University, 2015, 42(4): 1-7.
［11］崔丽珍, 李蕾. 基于核函数法及粒子滤波的煤矿井下定位算法研究［J］. 计算机工程与科学, 2013, 26(12): 1729-1733.
CUI Lizhen, LI Lei. Research on Underground Coal Mines Positioning Algorithms Based on Kernel Function and Particle Filter［J］. Chinese Journal of Sensrsand Actuators, 2013, 26(12):1729-1733.
［12］袁广林, 薛模根. 基于核函数粒子滤波和多特征自适应融合的目标跟踪［J］. 计算机辅助设计与图形学学报, 2009, 21(12): 1774-1784.
YUAN Guanglin, XUE Mogen. Kernel-Based Particle Filter for Target Tracking with Adaptive Multiple Features Fusion ［J］. Journal of Compter Aided Design ＆Computer Graphics, 2009, 21(12): 1774-1784.

[1]	GU Zhaojun,CHEN Hui,WANG Jialiang,GAO Bing. Target tracking control algorithm for small size quad-rotor helicopter [J]. Journal of Xidian University, 2021, 48(5): 117-127.
[2]	LU Yan,LIAO Guisheng,HUANG Qingxiang. Cross-camera moving target tracking algorithm based on sparse representation [J]. Journal of Xidian University, 2021, 48(2): 197-204.
[3]	ZHANG Yichen,SHUI Penglang. Improved probabilistic multi-hypothesis tracker via the Poisson point process [J]. Journal of Xidian University, 2021, 48(2): 27-34.
[4]	LI Cuiyun,LI Yang,JI Hongbing,SHI Renzheng. GLMB extended target tracking based on one-step data association [J]. Journal of Xidian University, 2020, 47(5): 137-143.
[5]	ZHANG Yunpu,SHAN Ganlin,DUAN Xiusheng,WANG Meng. Scheduling of active/passive sensors for radiation control [J]. Journal of Xidian University, 2019, 46(6): 67-74.
[6]	SONG Jianfeng,MIAO Qiguang,SHEN Meng,QUAN Yining,CHEN Yusheng. Algorithm for tracking an infrared single target based on correlation filtering with multi-feature fusion [J]. Journal of Xidian University, 2019, 46(5): 142-147.
[7]	WANG Mingjie,JI Hongbing,LIU Long. Student’s t Distribution mixture CPHD filter with noise outliers [J]. Journal of Xidian University, 2019, 46(5): 134-141.
[8]	LI Cuiyun,CHEN Dongwei,SHI Renzheng. Adaptive target birth δ-generalized labeled multi-Bernoulli filtering algorithm [J]. Journal of Xidian University, 2019, 46(2): 12-16.
[9]	LIU Yuqing;XIAO Song;LI Lei. Online discriminant based superpixel tracking method [J]. Journal of Xidian University, 2018, 45(3): 13-17+168.
[10]	DENG Bing;SUN Zhengbo;HE Qing. Novel extended Kalman filter with linear-correction [J]. Journal of Xidian University, 2018, 45(3): 130-135.
[11]	LI Cuiyun;WANG Jingyi;JI Hongbing;WANG Rong. CPHD multi-target tracking algorithm with unknown model parameters [J]. Journal of Xidian University, 2017, 44(2): 37-41+184.
[12]	FANG Deliang;RAN Xiaomin;LI Ou. Energy efficient distributed sensor management algorithm [J]. Journal of Xidian University, 2017, 44(2): 171-177.
[13]	LIU Hongliang;ZHOU Shenghua;LIU Hongwei;LU Ruilian;YAN Junkun. Track quality evaluation method using amplitude information [J]. Journal of Xidian University, 2017, 44(1): 65-70.
[14]	WANG Haihuan;WANG Jun. Multi-target tracking with the cubature Kalman multi-bernoulli filter [J]. Journal of Xidian University, 2016, 43(6): 176-182.
[15]	LI Yanyan;SU Tao. Resource allocation approach for maneuvering target tracking in distributed MIMO radar systems [J]. Journal of Xidian University, 2016, 43(4): 10-16.

Neurofilament protein automatic tracking of the particle filter algorithm based on multiple methods fusion

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 10