• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2020, Vol. 42 ›› Issue (09): 1587-1598.

• 图形与图像 • 上一篇    下一篇

融合TLD框架的DSST实时目标跟踪改进算法

黄浩淼1,4,张江2,张晶1,3,4,保峻嵘5   


  1. (1.昆明理工大学信息工程与自动化学院,云南 昆明 650500;

    2.中国船舶集团有限公司第七〇五研究所昆明分部,云南 昆明 650102;3.云南枭润科技服务有限公司,云南 昆明 650500;

    4.昆明理工大学云南省人工智能重点实验室,云南 昆明 650500;5.云南省信息技术发展中心,云南 昆明 650228)

  • 收稿日期:2019-12-12 修回日期:2020-03-06 接受日期:2020-09-25 出版日期:2020-09-25 发布日期:2020-09-25
  • 基金资助:
    云南省技术创新人才项目(2019HB113);云南省“万人计划”产业技术领军人才项目(云发改人事[2019]1096号)

An improved DSST real-time target tracking algorithm based on TLD framework

HUANG Hao-miao1,4,ZHANG Jiang2,ZHANG Jing1,3,4,BAO Jun-rong5   

  1. (1.Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500;

    2.Kunming Branch of the 705th Research Institute of China State ShipBuilding Co.,Ltd.,Kunming 650102;

    3.Yunnan Xiaorun Technology Service Co.,Ltd.,Kunming 650500;

    4.Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology,Kunming 650500;

    5.Yunnan Information Technology Development Center,Kunming 650228,China)

  • Received:2019-12-12 Revised:2020-03-06 Accepted:2020-09-25 Online:2020-09-25 Published:2020-09-25

摘要: 针对目标快速运动导致的图像模糊,使DSST算法难以区分目标与背景信息,滤波器在训练阶段循环移位采集密集样本容易产生边界效应,导致跟踪漂移的问题,提出了一种融合TLD框架的DSST实时目标跟踪改进算法(TLD-DSST)。改进DSST算法的位置滤波器,通过空间正则化的方法加入权重系数矩阵,降低非目标区域的响应,对快速运动目标进行粗定位;与此同时,引入朴素贝叶斯分类器改进TLD检测器,提高检测器对目标与背景信息的区分能力,然后将DSST目标响应的位置与TLD检测器得到的目标区域进行最优相似性匹配,得到精确定位的结果。通过TLD检测器正负样本在线更新机制,不断优化算法的鲁棒性。实验结果表明,TLD-DSST算法对于快速运动等复杂情景下的目标跟踪,具有很高的精确度和成功率。


关键词: TLD检测器, 边界效应, 空间正则化, 最优相似性匹配, 朴素贝叶斯分类器

Abstract: In view of the image blurring caused by fast target movement, it is difficult for the DSST algorithm to distinguish between the target and the background information. The filter is cyclically shifted during the training phase to collect dense samples, which easily results in boundary effect and leads to the tracking drift problem. Therefore, this paper proposes an improved DSST real-time target trac- king algorithm (TLD-DSST) that incorporates the TLD framework. The algorithm improves the position filter of the DSST algorithm, adds the weight coefficient matrix through the spatial regularization me- thod to reduce the response of the non-target area, and performs rough positioning of the target under fast motion. At the same time, a naive Bayesian classifier is introduced to improve the TLD detector, in order to improve the detector's ability to distinguish between the target and the background information. Moreover, the optimal similarity matching is performed on the position of the DSST target response and the target area obtained by the TLD detector, so as to get the precise positioning result. The TLD detector positive and negative sample online update mechanism is used to continuously optimize the robustness of the algorithm. Experimental results show that the TLD-DSST algorithm has high accuracy and success rate for target tracking in complex scenarios such as fast motion.


Key words:  , TLD detector, boundary effect, spatial regularization, optimal similarity matching, naive Bayes classifier