基于区域活动轮廓运动目标跟踪方法研究

Moving Objects Tracking Using Region-based Active Contours

根据贝叶斯估计理论,首先建立了图像序列中运动目标的跟踪模型,然后用高斯分布来描述图像的区域信息,并通过对模型的分析,与区域活动轮廓模型建立对应关系,将问题的求解转化为能量最小化问题。同时为了克服目标在运动中发生的拓扑形变,采用水平集方法进行数值实现。实验结果表明,这种方法不仅可以对多个运动目标进行跟踪,并能非常好地逼近运动目标的轮廓,而且能够自然地处理运动目标的拓扑形变。

Firstly, tracking model of moving objects in images is established based on Bayesian theory. Secondly, image regional information is described by Gaussian distribution. At the same time, the tracking model is matched to region-based active contours through analyzing, and then this problem is converted into the minimizing of energy. Lastly, level set is used to solve the PDE equation, which can process topology naturally. The result shows that the proposed method not only could track multi-objects and approach to the objects contours, but also does well when the moving objects deforms topologically.