基于动态图像序列的运动目标检测与跟踪

Moving Object Detecting and Tracking Based on Statistical Background Model and Filter Estimation

运动目标的检测与跟踪在智能监控和车辆导航领域中得到了广泛的应用。该文提出了基于统计背景模型和α-β-γ滤波模型的运动目标检测和跟踪算法。在此方法中,首先建立背景的高斯模型,然后检测出场景中的运动目标,最后在目标检测的结果上,采用α-β-γ滤波器对检测出的运动区域进行运动参数估计,进而跟踪出运动目标的轨迹。实验表明,该方法能够有效地分割出序列图像中的前景目标,并提高了目标跟踪的稳定性。从而证明了该方法的有效性。

Motion object detecting and tracking is widely used in the areas of smart traffic monitoring, vehicle navigation. A new method based on statistical background model and α-β-γ filter model is proposed in this paper. In this method, Firstly, a Gauss model is used as the background model, the moving objects are extracted from the image sequence of the scenes, Finally, the motion parameters of detected region are estimated by the α-β-γ filter, and the motion trajectories of objects are also tracked. It can be seen from the experiment that the moving objects can be detected and tracked exactly, it is proved that the method adopted is very feasible.