| 基于多层自适应聚类模型的密集人群分群检测算法 |
| |
| 引用本文： | 邵洁,赵倩.基于多层自适应聚类模型的密集人群分群检测算法[J].上海电力学院学报,2017,33(1):91-96. |
| |
| 作者姓名： | 邵洁 赵倩 |
| |
| 作者单位： | 上海电力学院 电子与信息工程学院,上海电力学院 电子与信息工程学院 |
| |
| 基金项目： | 国家自然科学基金（61302151，61401268）；上海市自然科学基金（13ZR1455100，15ZR1418400）. |
| |
| 摘 要： | 针对存在更复杂运动模式的无序运动人群密集场景,提出了一种基于多层自适应聚类模型的分群检测算法.以基于高斯混合模型的背景去除算法和自适应初始化聚类算法为核心,通过建立多层自适应聚类模型实现密集人群的分群检测.实验数据库选用了大量真实室内外密集人群运动场景视频,并通过大量对比实验验证了算法的有效性、可靠性和优越性.
|
| 关 键 词： | 密集人群 分群检测 自适应聚类 多层聚类模型 |
| 收稿时间： | 2016/3/16 0:00:00 |
Hierarchical Adaptive Clustering Based Group Detection in the Crowd |
| |
| SHAO Jie and ZHAO Qian.Hierarchical Adaptive Clustering Based Group Detection in the Crowd[J].Journal of Shanghai University of Electric Power,2017,33(1):91-96. |
| |
| Authors: | SHAO Jie and ZHAO Qian |
| |
| Affiliation: | School of Electronics and Information Engineering, Shanghai University of Electric Power, Shanghai 200090, China and School of Electronics and Information Engineering, Shanghai University of Electric Power, Shanghai 200090, China |
| |
| Abstract: | A hierarchical adaptive clustering based group detection algorithm is proposed for the crowded scenes involving multiple complex motion modalities.Gaussian Mixture Models based background subtraction algorithm and the adaptive initialization clustering algorithm are the key to the algorithm.Group detection is implemented by merging spatiotemporal features of salient points into different layers of the model.Our dataset is built by varieties of in-door and out-door real scene videos.The proposed algorithm outperforms many other algorithms in terms of its effectiveness,reliability and superiority by experimental comparisons. |
| |
| Keywords: | crowd group detection adaptive clustering hierarchical clustering model |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《上海电力学院学报》浏览原始摘要信息 |
|
点击此处可从《上海电力学院学报》下载全文 |
