Inferring Intersection Traffic Patterns With Sparse Video Surveillance Information: An ST-GAN Method
- 23 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 71 (9) , 9840-9852
Abstract
Traffic patterns of urban road intersections are important in traffic monitoring and accident prediction, thus play crucial roles in urban traffic management. Although real-time traffic information is consistently provided by surveillance cameras equipped at road intersections, the sparsity of surveillance distribution poses great challenges in performing a complete real-time traffic pattern analysis. To tackle that, existing works either assume that the traffic patterns are static, or assume a multi-variant distribution model for intersection traffic volumes. The former assumption neglects the temporal features of traffic patterns, and the latter is limited in capturing fine-grained spatiotemporal dependencies. To tackle the problem, we propose a novel framework, SpatioTemporal-Generative Adversarial Network (ST-GAN), that exploits deep spatiotemporal features of urban networks and offers accurate traffic pattern inferences with incomplete surveillance information. The ST-GAN framework incorporates a modified GCN network wired with the encoder-decoder mechanism and an LSTM network, which are further boosted by an iterative adversarial training process. Comprehensive experiments on real datasets show that ST-GAN achieves better inference accuracies than state-of-the-art solutions.Keywords
Funding Information
- Project of Stable Support for Youth Team in Basic Research Field
- CAS (YSBR-005)
- National Natural Science Foundation of China (62072427)
- Anhui Science Foundation for Distinguished Young Scholars (1908085J24)
- Natural Science Foundation of Jiangsu Province (BK20191193)
This publication has 40 references indexed in Scilit:
- Generative Face Completion2017
- Citywide Traffic Volume Estimation Using Trajectory DataIEEE Transactions on Knowledge and Data Engineering, 2016
- Improving Traffic Flow Prediction With Weather Information in Connected Cars: A Deep Learning ApproachIEEE Transactions on Vehicular Technology, 2016
- Data-driven traffic flow analysis for vehicular communications2014
- Intelligent Video Systems and Analytics: A SurveyIEEE Transactions on Industrial Informatics, 2013
- T-Drive: Enhancing Driving Directions with Taxi Drivers' IntelligenceIEEE Transactions on Knowledge and Data Engineering, 2011
- Data-Driven Intelligent Transportation Systems: A SurveyIEEE Transactions on Intelligent Transportation Systems, 2011
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Prediction of Road Traffic using a Neural Network ApproachNeural Computing and Applications, 1999
- Exploratory Orientation Data Analysis: Kernel Density Estimation and ClusteringMaterials Science Forum, 1994