Learning Methods for Dynamic Topic Modeling in Automated Behavior Analysis
Learning Methods for Dynamic Topic Modeling in Automated Behavior Analysis
复制标题
DOI：
10.1109/tnnls.2017.2735364
复制
发表时间：
2016-11
影响因子：
10.4
通讯作者：
Olga Isupova;Danil Kuzin;L. Mihaylova
中科院分区：
文献类型：
--
作者：
Olga Isupova;Danil Kuzin;L. Mihaylova
半监督和无监督系统为操作员提供了宝贵的支持，并且可以极大地减轻操作员的负担。鉴于处理大量视频数据并提供自主决策的必要性，本文提出了用于视频活动分析的新学习算法。活动和行为由动态主题模型描述。提出了两种基于期望最大化方法和变分贝叶斯推理的新颖学习算法。给出了模型参数后验估计的理论推导。将设计的学习算法与文献中先前介绍的吉布斯采样推理方案进行比较。在真实视频数据上对学习算法进行了详细比较。我们还提出了一种异常定位程序，优雅地嵌入到主题建模框架中。结果表明，所开发的学习算法可以达到95%的成功率。拟议的框架可应用于许多领域，包括交通系统、安全和监控。
Semisupervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators’ load. In the light of the necessity to process large volumes of video data and provide autonomous decisions, this paper proposes new learning algorithms for activity analysis in video. The activities and behaviors are described by a dynamic topic model. Two novel learning algorithms based on the expectation maximization approach and variational Bayes inference are proposed. Theoretical derivations of the posterior estimates of model parameters are given. The designed learning algorithms are compared with the Gibbs sampling inference scheme introduced earlier in the literature. A detailed comparison of the learning algorithms is presented on real video data. We also propose an anomaly localization procedure, elegantly embedded in the topic modeling framework. It is shown that the developed learning algorithms can achieve 95% success rate. The proposed framework can be applied to a number of areas, including transportation systems, security, and surveillance.