Shandong Key Laboratory of Medical Physics and Image Processing, School of Physics and Electronics, Shandong Normal University, Jinan 250014, China.
School of Physics and Electronics, Shandong Normal University, Jinan 250014, China.
Sensors (Basel). 2019 Mar 12;19(5):1245. doi: 10.3390/s19051245.
With the revolutionary development of cloud computing and internet of things, the integration and utilization of "big data" resources is a hot topic of the artificial intelligence research. Face recognition technology information has the advantages of being non-replicable, non-stealing, simple and intuitive. Video face tracking in the context of big data has become an important research hotspot in the field of information security. In this paper, a multi-feature fusion adaptive adjustment target tracking window and an adaptive update template particle filter tracking framework algorithm are proposed. Firstly, the skin color and edge features of the face are extracted in the video sequence. The weighted color histogram are extracted which describes the face features. Then we use the integral histogram method to simplify the histogram calculation of the particles. Finally, according to the change of the average distance, the tracking window is adjusted to accurately track the tracking object. At the same time, the algorithm can adaptively update the tracking template which improves the accuracy and accuracy of the tracking. The experimental results show that the proposed method improves the tracking effect and has strong robustness in complex backgrounds such as skin color, illumination changes and face occlusion.
随着云计算和物联网的革命性发展，“大数据”资源的整合与利用是人工智能研究的热门话题。人脸识别技术信息具有不可复制、不可窃取、简单直观的优点。大数据背景下的视频人脸跟踪已成为信息安全领域的一个重要研究热点。本文提出了一种多特征融合自适应调整目标跟踪窗口和自适应更新模板粒子滤波跟踪框架算法。首先，在视频序列中提取人脸的肤色和边缘特征。提取描述人脸特征的加权颜色直方图。然后，我们使用积分直方图方法简化粒子的直方图计算。最后，根据平均距离的变化，调整跟踪窗口以准确跟踪跟踪对象。同时，该算法可以自适应地更新跟踪模板，从而提高跟踪的准确性和精度。实验结果表明，所提出的方法提高了跟踪效果，在肤色、光照变化和人脸遮挡等复杂背景下具有较强的鲁棒性。
