| 基于均值漂移算法和时空上下文算法的目标跟踪 |
| |
| 引用本文： | 周华争,马小虎. 基于均值漂移算法和时空上下文算法的目标跟踪[J]. 计算机科学, 2017, 44(8): 22-26 |
| |
| 作者姓名： | 周华争 马小虎 |
| |
| 作者单位： | 苏州大学计算机科学与技术学院 苏州215006,南京大学计算机软件新技术国家重点实验室 南京210023 |
| |
| 基金项目： | 本文受江苏省自然科学基金(BK20141195),南京大学计算机软件新技术国家重点实验室资助 |
| |
| 摘 要： | 在严重遮挡时,时空上下文STC(Spatio-Temporal Context)算法对目标位置的判断是正确的,而均值漂移MS(Mean Shift)算法对目标位置的判断会发生很大幅度的抖动,甚至跟踪错误目标。在遮挡结束后,时空上下文算法很难重新跟踪到正确目标,而均值漂移算法可以重新检测到跟踪目标。结合二者的优缺点,提出基于均值漂移算法和时空上下文算法的目标跟踪算法MSandSTC。该算法主要解决目标被严重遮挡的问题。在许多具有挑战性的数据集上的实验表明所提算法具有较好的实时性和鲁棒性。
|
| 关 键 词： | 目标跟踪 均值漂移 时空上下文 严重遮挡 |
| 收稿时间： | 2016-06-19 |
| 修稿时间： | 2016-07-28 |
Object Tracking Based on Mean Shift Algorithm and Spatio-Temporal Context Algorithm |
| |
| ZHOU Hua-zheng and MA Xiao-hu. Object Tracking Based on Mean Shift Algorithm and Spatio-Temporal Context Algorithm[J]. Computer Science, 2017, 44(8): 22-26 |
| |
| Authors: | ZHOU Hua-zheng and MA Xiao-hu |
| |
| Affiliation: | School of Computer Science and Technology,Soochow University,Suzhou 215006,China and State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210023,China |
| |
| Abstract: | When the target undergoes heavy occlusion,the spatio-temporal context (STC) algorithm can track the object accurately,but the mean shift algorithm is shaking in this situation.After occlusion,the mean shift algorithm can track the object again,however,the STC method cannot finish it.In order to make full use of these advantages,we developed a new algorithm MSandSTC to combine these two algorithms.Our algorithm can solve the problem of heavy occlusion.The efficiency,accuracy and robustness of the proposed algorithm are verified through experiments on a number of challenging data sets. |
| |
| Keywords: | Object tracking Mean shift Spatio-Temporal context Heavy occlusion |
|
|
点击此处可从《计算机科学》下载全文 |
|
