一种新的目标检测与跟踪算法

A new algorithm of target detection and tracking

针对目前目标检测与跟踪算法实时性和精确性不高的问题,提出了一种新的算法.该法采用差分法分割检测目标,在混合高斯背景模型的基础上,通过检测目标的位置和颜色特征,并利用改进的Hough变换检测目标形状,找到与之匹配的目标轨迹,从而实现目标的准确跟踪.实验结果表明,该方法具有较高的检测精度和跟踪效率,能够满足智能监控系统的实时性要求.

In view of the problem of the current target detection and tracking algorithm of real-time and precision,a new mehod based on Gaussian mixture model was put forward that it uses difference method to detect the target,by detecting the target position and color features and using improved Hough transform to detect target shape,finds a match with the target trajectory so as to achieve the goal accurate tracking.The experimental results showed that the method has higher detection accuracy and tracking efficiency and can meet the needs of intelligent monitoring system in real-time.