帮助 关于我们

返回检索结果

光学影像序列中基于多视角聚类的群组行为分析
Multiview-based group behavior analysis in optical image sequence

查看参考文献36篇

李学龙 1 *   陈穆林 2   王琦 2,3  
文摘 群组行为分析是光学影像序列分析中的一项重要课题,在近年来引起了人工智能领域研究人员的广泛关注.与行人个体相比,群组能提供更高层的语义表示,为分析人群运动模式提供基础.本文将人群影像序列中的影像块作为研究对象,提出了一种基于多视角聚类的群组行为分析方法,对运动模式不同的群组进行区分,主要研究内容有:(1)提出了基于特征点的影像块构图方法,从交互关系、空间位置、运动方向分布,以及运动规律等方面衡量影像块之间的关系;(2)提出了一种多视角聚类方法,通过融合多种特征对每个影像块分配类标签,并引入图多样性正则项以避免特征冗余;(3)提出了一种类合并方法,根据类内特征点的运动方向和类中心位置坐标,对关联度较高的类别进行合并,自动确定最终群组数目. CUHK人群数据集上的实验结果证明了该方法能够准确划分出影像数据中的群组.另外,与现有方法相比,本文提出的多视角聚类方法也在不同数据集上取得了较好的实验结果.
其他语种文摘 Group behavior analysis is a hot topic in intelligent video surveillance, and has attracted a surge of interest in the field of artificial intelligence. Groups are the basic components of a crowd system, and provide a high-level representation of the crowd phenomenon. By investigating the motion dynamics within each image patch, this paper proposes a multiview-based group behavior analysis method that is able to divide the paths into different groups. The main contributions are threefold: (1) the correlation between image paths is captured from four views (interaction, distance, motion direction, and motion transition), (2) a multiview clustering method with diversity regularization is proposed to perceive the complementary information within the multiview data and alleviate the influence of redundant features, and (3) a cluster merging strategy is designed to combine the highly correlated clusters and determine the final groups automatically. Experimental results on several benchmark datasets validate the good performance of the proposed method.
来源 中国科学. 信息科学 ,2018,48(9):1227-1241 【核心库】
DOI 10.1360/N112017-00284
关键词 人群分析 ; 群组行为分析 ; 聚类算法 ; 图聚类 ; 多视角聚类
地址

1. 中国科学院西安光学精密机械研究所, 西安, 710119  

2. 西北工业大学计算机学院与光学影像分析与学习中心, 西安, 710072  

3. 西北工业大学无人系统研究院, 西安, 710072

语种 中文
文献类型 研究性论文
ISSN 1674-7267
学科 自动化技术、计算机技术
文献收藏号 CSCD:6336650

参考文献 共 36 共2页

1.  Wang Q. Multi-cue based tracking. Neurocomputing,2014,131:227-236 被引 4 次    
2.  Zhang Y Y. Single-image crowd counting via multi-column convolutional neural network. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2016:589-597 被引 7 次    
3.  Wang W Y. Finding coherent motions and semantic regions in crowd scenes: a diffusion and clustering approach. Proceedings of European Conference on Computer Vision,2014:756-771 被引 1 次    
4.  Yuan Y. Online anomaly detection in crowd scenes via structure analysis. IEEE Trans Cybern,2015,45:548-561 被引 5 次    
5.  Zhou B L. Coherent filtering: detecting coherent motions from crowd clutters. Proceedings of European Conference on Computer Vision,2012:857-871 被引 2 次    
6.  Shao J. Scene-independent group profiling in crowd. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2014:2227-2234 被引 2 次    
7.  Wu Y P. Coherent motion detection with collective density clustering. Proceedings of ACM Conference on Multimedia Conference,2015:361-370 被引 1 次    
8.  Zhou B L. Measuring crowd collectiveness. IEEE Trans Pattern Anal Mach Intel,2014,36:1586-1599 被引 5 次    
9.  Zhou B L. Random field topic model for semantic region analysis in crowded scenes from tracklets. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs,2011:3441-3448 被引 1 次    
10.  Wang Q. Quantifying and detecting collective motion by manifold learning. Proceedings of AAAI Conference on Artificial Intelligence,2017:4292-4298 被引 2 次    
11.  Chen M L. Anchor-based group detection in crowd scenes. Proceedings of International Conference on Acoustics, Speech and Signal Processing,2017:1378-1382 被引 2 次    
12.  Ali S. A Lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2007 被引 2 次    
13.  Li X L. A multiview-based parameter free framework for group detection. Proceedings of AAAI Conference on Artificial Intelligence,2017:4147-4153 被引 2 次    
14.  Chen M L. Patch-based topic model for group detection. Sci China Inf Sci,2017,60:113101 被引 1 次    
15.  Sharma R. A trajectory clustering approach to crowd flow segmentation in videos. Proceedings of IEEE International Conference on Image Processing,2016:1200-1204 被引 1 次    
16.  Kumar A. Co-regularized multi-view spectral clustering. Proceedings of Advances in Neural Information Processing Systems,2011:1413-1421 被引 2 次    
17.  Cai X. Heterogeneous image feature integration via multi-modal spectral clustering. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2011:1977-1984 被引 2 次    
18.  Li Y Q. Large-scale multi-view spectral clustering via bipartite graph. Proceedings of AAAI Conference on Artificial Intelligence,2015:2750-2756 被引 1 次    
19.  Xia R K. Robust multi-view spectral clustering via low-rank and sparse decomposition. Proceedings of AAAI Conference on Artificial Intelligence,2014:2149-2155 被引 2 次    
20.  Liu X W. Optimal neighborhood kernel clustering with multiple kernels. Proceedings of AAAI Conference on Artificial Intelligence,2017:2262-2272 被引 1 次    
引证文献 3 篇

1 李学龙 像素级语义理解:从分类到回归 中国科学. 信息科学,2021,51(4):521-564
被引 1 次

2 李学龙 视频萃取 中国科学. 信息科学,2021,51(5):695-734
被引 3 次

显示所有3篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号