基于EKF-PF的序列图像中活跃细胞追踪算法的研究  

Study on Method of Tracking the Active Cells in Image Sequences Based on EKF-PF

作　　者：汤春明 刘颖[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《生物医学工程学杂志》2013年第1期6-11,共6页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(60875020)

摘　　要：在细胞序列图像中,由于活跃细胞非线性、非高斯的运动特点,对于它的准确预测和追踪是一个尚未解决的难题。本文利用扩展卡尔曼粒子滤波器(EKF-PF)来追踪该类细胞。算法先确定图像中的活跃细胞,再建立运动模型,并对运动模型进行了改进,加入了运动角度估计,对被追踪细胞所在区域中心位置的运动参数(位移、速度、加速度、运动角度)进行滤波预测,最后得到活跃细胞的运动轨迹。该算法对三个图像序列中的14个活跃细胞进行了轨迹的预测,预测结果与实测结果相比,误差在2.5个像素以内,基本能够实现对活跃细胞较准确地预测和追踪。In cell image sequences, due to the nonlinear and nonGaussian motion characteristics of active cells, the ac- curate prediction and tracking is still an unsolved problem. We applied extended Kalman particle filter （EKF-PF） here in our study, attempting to solve the problem. Firstly we confirmed the existence and positions of the active cells. Then we established a motion model and improved it via adding motion angle estimation. Next we predicted motion parameters, such as displacement, velocity, accelerated velocity and motion angle, in region centers of the cells being tracked. Finally we obtained the motion traces of active cells. There were fourteen active cells in three im- age sequences which have been tracked. The errors were less than 2.5 pixels when the prediction values were com- pared with actual values. It showed that the presented algorithm may basically reach the solution of accurate predi- lion and tracking of the active cells.

关 键 词：活跃细胞 非线性 非高斯 预测和追踪 扩展卡尔曼粒子滤波器 运动角度 

分 类 号：R318.51[医药卫生—生物医学工程]