摘要
多目标跟踪相比较于单目标跟踪而言,视频中的目标数量增加,且在目标运动时,多个目标之间可能会产生遮挡,更增加了目标跟踪的难度,针对以上问题提出了Meanshift算法与卡尔曼滤波相结合的方法进行多目标的跟踪,首先采用Meanshift算法将目标与背景进行分割,然后分别建立Kalman数学模型,结果表明,该方法能够实现较为稳定的多目标的跟踪。
Comparing with the single target tracking,multi-object tracking is more complex. The number of targets in the video increases and targets may overlapped between each other which is more difficult to be tracked. In order to solve the problems,a method based on Meanshift and Kalman filter is proposed to track the multi objects. First,the target and the background are segmented in Meanshift algorithm. Then Kalman mathematical models are established respectively. The experiments results show that the method can achieve a more stable tracking.
作者
张艳艳
曾玉洁
张玉涛
ZHANG Yan-yan;ZENG Yu-jie;ZHANG Yu-tao(Jiangsu Key Laboratory of M eteorological Observation and Information Processing,Nanjing University of Information Science & Technology,Nanjing 210044,C hina)
出处
《信息技术》
2016年第12期10-13,共4页
Information Technology
基金
江苏省高校基金(12KJB510012)
2014大学生实践创新计划(201410300169)
江苏高校优势学科Ⅱ期建设工程资助项目
江苏省气象探测与信息处理重点实验室项目(KDXS1405)
