当前位置: X-MOL 学术IEEE Trans. Cybern. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Crowd Characterization in Surveillance Videos Using Deep-Graph Convolutional Neural Network
IEEE Transactions on Cybernetics ( IF 9.4 ) Pub Date : 2021-12-01 , DOI: 10.1109/tcyb.2021.3126434
Shreetam Behera 1 , Debi Prosad Dogra 1 , Malay Kumar Bandyopadhyay 2 , Partha Pratim Roy 3
Affiliation  

Crowd behavior is a natural phenomenon that can provide valuable insight into the crowd characterization process. Modeling the visual appearance of a large crowd gathering can reveal meaningful information about its dynamics. Parametric modeling can be used to develop efficient and robust crowd monitoring systems. A crowd can be structured or unstructured based on the organization. In this article, crowd characterization has been mapped to a graph classification problem to classify movements based on order parameter ( ϕ\phi ), active force components, and steadiness (Reynolds number). The graphs are constructed from the motion groups obtained using an active Langevin framework. These graphs are processed using a deep graph convolutional neural network for crowd characterization. For experimentation, we have prepared a dataset comprising of videos from popular publicly available datasets and our own recorded videos. The proposed framework has been compared with the latest deep learning-based frameworks in terms of accuracy and area under the curve (AUC). We have obtained a 4%–5% improvement in accuracy and AUC values over the existing frameworks. The insights obtained from the proposed framework can be used for better crowd monitoring and management.

中文翻译:


使用深图卷积神经网络对监控视频中的人群进行表征



人群行为是一种自然现象,可以为人群特征描述过程提供有价值的见解。对大型人群聚集的视觉外观进行建模可以揭示有关其动态的有意义的信息。参数化建模可用于开发高效且强大的人群监控系统。根据组织的不同,群体可以是结构化的或非结构化的。在本文中,人群特征已映射到图分类问题,以根据顺序参数 ( phi\phi )、主动力分量和稳定性(雷诺数)对运动进行分类。这些图表是根据使用活动 Langevin 框架获得的运动组构建的。这些图使用深度图卷积神经网络进行处理,以进行人群特征描述。为了进行实验,我们准备了一个数据集,其中包含来自流行的公开数据集的视频和我们自己录制的视频。所提出的框架在准确性和曲线下面积(AUC)方面与最新的基于深度学习的框架进行了比较。与现有框架相比,我们的准确率和 AUC 值提高了 4%–5%。从所提出的框架中获得的见解可用于更好的人群监控和管理。
更新日期:2021-12-01
down
wechat
bug