计算机工程与应用2019，Vol.55Issue(12)：124-131,8.DOI:10.3778/j.issn.1002-8331.1811-0391
高斯混合模型结合加权似然的目标跟踪算法
Target Tracking Algorithm Involving Gaussian Mixture Model and Weighted Likelihood
摘要
Abstract
The target tracking algorithm based on WLT and IGMM is proposed in view of the GMM algorithm’s poor adaptability while the background changes fastly and target are multiple. An adaptive Gauss mixture model involving frac-tional derivative learning rate is introduced to detect moving targets in real time. The target localization is achieved by maximizing its weighted likelihood in the video. Moreover, the algorithm handles scale and rotation changes of the muli-target. Experimental results in VOT2014 dataset suggested proposed algorithm involving WLT and IGMM comparing cur-rent popular tracking algorithm in tracking accuracy is improved greatly. In respond to the changes in multi-scale, multi-angle multi-target tracking shows greater advantage.关键词
改进高斯混合模型/分数阶导数学习率/目标跟踪算法/加权似然跟踪/期望值最大化Key words
Improved Gaussian Mixture Model(IGMM)/ fractional derivative learning rate/ target tracking algorithm/Weighted Likelihood Tracking(WLT)/ expectation-maximization分类
信息技术与安全科学引用本文复制引用
陈超..高斯混合模型结合加权似然的目标跟踪算法[J].计算机工程与应用,2019,55(12):124-131,8.基金项目
四川省应用基础研究计划(No.2015JY0120) （No.2015JY0120）
四川省高校科研创新团队项目(No.15JD0027) （No.15JD0027）
内江师范学院科研项目(No.15JC09). （No.15JC09）
