Abstract: Neurofilaments are long flexible cytoplasmic protein polymers that are transported rapidly but intermittently along the axonal processes of nerve cells. Current methods for studying this movement involve manual tracking of fluorescently tagged neurofilament polymers in videos acquired by time-lapse fluorescence microscopy. This paper describes an automated tracking method with particle filtering. To increase the efficiency of this approach, it takes advantage of the fact that neurofilament movement is confined within the boundaries of the axon to limit both the orientation and location of the neurofilament in the particle tracking algorithm such that fewer particles than generic particle filtering are generated significantly. It demonstrates the efficacy and efficiency of this method by performing tracking experiments on real time-lapse image sequences of neurofilament movement, and it shows that the method performs well compared to manual tracking by an experienced user. This spatially constrained particle filtering approach should also be applicable to the movement of other axonally transported cargoes.

Key words: fluorescence microscopy, neurofilament, object tracking, particle filtering, spatial constraint

摘要： 神经丝蛋白质（Neurofilament）是一种长而柔软的蛋白质有机物，它能在神经细胞中沿着神经轴突快速且随机地运动。人们希望通过对神经丝蛋白质的跟踪来分析它的运动性能，从而进一步了解神经细胞的性能。目前，研究人员只是通过在显微镜下拍摄到的神经丝蛋白质的运动视频，人工地跟踪它运动。这种人工跟踪不但对大量图像实现起来非常费时，而且会带来很多人为跟踪误差。提出了一种基于粒子滤波算法实现对神经丝蛋白质全自动跟踪的全新方法。为了提高粒子滤波的计算效率，在粒子滤波算法中利用了神经丝蛋白质在神经轴突内运动这一特征，限制了算法中粒子的位置和方向，从而显著地降低了粒子使用的数量，大大减少了算法的运算时间。在实际的实时跟踪实验中，提出的粒子滤波跟踪算法与通用的粒子滤波算法相比，显示出了运算速度快和跟踪准确的优点。同样，这种空间约束粒子滤波方法也适用于其他轴突物质的运动跟踪。

关键词: 荧光显微镜, 神经丝蛋白质, 目标跟踪, 粒子滤波, 空间约束