原文传递
Multi-view crowd congestion monitoring system based on an ensemble of convolutional neural network classifiers
| 题名： | Multi-view crowd congestion monitoring system based on an ensemble of convolutional neural network classifiers |
| 正文语种： | 英文 |
| 作者： | Yan Li;Majid Sarvi;Kourosh Khoshelham;Milad Haghani |
| 作者单位： | University of Melbourne |
| 关键词： | 3D GIS; convolutional neural networks; crowd congestion; ensemble learning; level of service; multi-view video surveillance |
| 摘要： | Multi-view video surveillanee is a highly valuable tool to ensure the safety of the crowd in large public space. By utilizing complementary information captured by multiple cameras, the issue of limited views and occlusion in single views can be addressed to gain better insight into the whole monitored space. However, multi-view surveillanee has been widely applied to microscopic crowd analysis, for example pedestrian detection and tracking, while macroscopic level analysis, which deals with the whole crowd, has received little attention. We propose a multi-view framework for the gen eratio n of level of service maps, which are the most comm only used measure of con gestion at macroscopic level, based on an ens em-ble of state-of-the-art Convolutional Neural Networks (CNNs). Several combination rules are compared and evaluated on two datasets, both in sparse and dense seenarios. Our results show that this fusio n framework improves the accuracy of level of service map gen eration, from 83.2% to 89.8%, and eliminates blind spots in single views. Our framework is imple-mented on a 3 D GIS platform, which provides a suitable interface for multi-view crowd con-gestion management. The results of a loading test show that a maximum of 48 cameras can be processed at a map refresh rate of 2 seconds. |
| 出版日期： | 2020 |
| 出版年： | 2020 |
| 期刊名称： | Journal of Intelligent Transportation Systems Technology Planning and Operations |
| 卷： | Vol24 |
| 期： | No01-06 |
| 页码： | 437-448 |
相关文献
- Direct generation of level of service maps from images using convolutional and long short-term memory networks
- Convolutional neural network for recognizing highway traffic congestion
- Maximum Gradient Decision-Making for Railways Based on Convolutional Neural Network
- Prediction of Traffic Incident Duration Using Clustering-Based Ensemble Learning Method
- Spatial-Temporal Graph-Enabled Convolutional Neural Network-Based Approach for Traffic Networkwide Travel Time
- Multi-objective optimal predictive control of signals in urban traffic network
检索历史
应用推荐
