摘要
为了有效地解决目标颜色与背景颜色区分度较低而引起的目标定位不准确的问题以及目标被大面积遮挡而引起目标丢失的问题,提出了一种改进的meanshift运动目标跟踪算法。该算法利用harris角点检测法快速地提取目标的角点特征,并将这些角点嵌入到meanshift算法的迭代条件中进行目标搜索,然后结合卡尔曼滤波原理预测目标在下一帧中的位置,最终实现目标跟踪。实验证明该算法能够有效地提高跟踪的准确性和实时性。
In order to solve the inaccurate locating caused by low differentiation between object color and background color and the missing object resulted from largely blocked area of the object,an improved algorithm is proposed.This algorithm,with Harris corner,could effectively extract target＇s corner characteristic,these corners are embedded into the iteration condition of meanshift,algorithm for object search,and then in integration of kalman filter,the position of the target in the next frame is predicted and the target tracking finally realized.Experiment indicates that the proposed algorithm could effectively improve the accuracy and real-time performance of the target tracking.
出处
《通信技术》
2011年第11期76-79,共4页
Communications Technology
