[1]史双飞,张 震.基于决策的人脸检测与自动跟踪方法[J].计算机技术与发展,2019,29(09):35-39.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 007]
　SHI Shuang-fei,ZHANG Zhen.A Method of Face Detection and Automatic Tracking Based on Decision Making[J].,2019,29(09):35-39.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 007]
点击复制

基于决策的人脸检测与自动跟踪方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年09期
页码:
35-39
栏目:
智能、算法、系统工程
出版日期:
2019-09-10

文章信息/Info

Title:
A Method of Face Detection and Automatic Tracking Based on Decision Making
文章编号:
1673-629X(2019)09-0035-05
作者:
史双飞; 张 震
上海大学 机电工程与自动化学院,上海 200072
Author(s):
SHI Shuang-fei; ZHANG Zhen
School of Mechanical and Electrical Engineering and Automation,Shanghai University,Shanghai 200072,China
关键词:
VJ 算法; AdaBoost 算法; MDP 模型; 光流法; Kalman 运动估计
Keywords:
VJ algorithm; AdaBoost algorithm; MDP model; optical flow; Kalman motion estimation
分类号:
TP391.4
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 09. 007
摘要:
对人脸检测与跟踪的研究现状进行了简要介绍,发现传统的 MDP(Markov decision processes)跟踪算法需要手动初始化,这不利于实际场景中的灵活运用。因此,提出一种基于 Viola-Jones 人脸检测算法和改进的 MDP 自动跟踪算法。从视频序列中提取人脸的类 Haar 特征,采用 AdaBoost 算法构建强分类器,并利用级联方式将强分类器进行联合,从而提高人脸检测率。 MDP 跟踪算法将在线的多目标跟踪问题规划成 MDP 中的决策,为每一个人脸目标建立一个 MDP 模型,并用 VJ 检测器的输出来初始化该模型,将人脸的出现到消失看作是 MDP 模型中的状态转移,在跟踪过程中采用光流法结合 Kalman 运动估计提高人脸跟踪的准确性和鲁棒性,减少目标 ID 的分配错误。 在此过程中 VJ 检测器作为监督指标,与跟踪器的输出进行关联。 实验结果表明,该算法可以稳定地检测并跟踪场景内的人脸目标,其速率也能满足应用要求。
Abstract:
The present status of face detection and tracking is briefly introduced. It is found that the traditional MDP (Markov decision processes) tracking algorithm needs to be initialized manually,which is not conducive to the flexible use of the actual scene. Therefore,we propose an algorithm based on Viola-Jones algorithm and improved MDP automatic tracking algorithm. First,the Haar-like features of human faces are extracted from video sequences,and a strong classifier is constructed by using AdaBoost algorithm. The strong classifiers are combined by cascade method to improve the rate of face detection. Second,MDP tracking algorithm divides the online multi-target tracking problem into decision. An MDP model is established for each face target and initialized with the output of the VJ detector. The appearance and disappearance of human faces is regarded as state transition in MDP model. In the process of tracking,optical flow method combined with Kalman motion estimation is used to improve the accuracy and robustness of face tracking and reduce the ID switches. In this process,the VJ detector is also used as a monitoring index to correlate with the output of the tracker. Finally,experiment shows that the proposed algorithm can detect and track human faces stably in the scene,and its speed can meet the application requirements.

相似文献/References:

[1]张礼雄,张忠林.视频中多目标车辆的检测与跟踪方法研究[J].计算机技术与发展,2018,28(07):125.[doi:10.3969/ j. issn.1673-629X.2018.07.027]
　ZHANG Li-xiong,ZHANG Zhong-lin.Research on Method of Detection and Tracking of Multi-objective Vehicle Based on Video[J].,2018,28(09):125.[doi:10.3969/ j. issn.1673-629X.2018.07.027]
[2]王 燕,曹建芳,李艳飞.融合混合优化组合的大规模场景图像分类算法[J].计算机技术与发展,2019,29(09):86.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 017]
　WANG Yan,CAO Jian-fang,LI Yan-fei.A Classification Algorithm for Large-scale Scene Images Fusing Hybrid Optimization and Combination[J].,2019,29(09):86.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 017]
[3]乔旭坤,李 顺,李 君,等.基于机器学习的硬盘故障预测研究[J].计算机技术与发展,2022,32(06):215.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 036]
　QIAO Xu-kun,LI Shun,LI Jun,et al.Research on Hard Disk Failure Prediction Based on Machine Learning[J].,2022,32(09):215.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 036]

更新日期/Last Update: 2019-09-10