Smart City Gnosys

Smart city article details

Title	An Innovational Gnn-Based Urban Traffic-Flow Measuring Approach Using Dynamic Vision Sensor
ID_Doc	8359
Authors	Qian C.; Tang C.; Li C.; Zhao W.; Tang R.
Year	2025
Published	Measurement: Journal of the International Measurement Confederation, 252
DOI	http://dx.doi.org/10.1016/j.measurement.2025.117262
Abstract	Smart urban mobility is an important approach for meeting the rapid increasing demanding of the urban populations. Urban mobility problems could be more effectively resolved by artificial intelligent techniques. Traditional visual sensors and visual algorithms suffer from low dynamic response and high computational cost. This paper proposes an Event-camera Traffic-flow Measuring Graph Neural Network (ETM-GNN) method for traffic flow detection, which features low sampling latency and sparse data sampling characteristics. An optimized proximity search strategy is firstly developed for event-data preprocessing to construct an event graph, which is then fed into the proposed graph-based neural network for traffic detection. An innovational graph convolution block is developed by applying layer normalization instead of batch normalization for sequential event-data. The overall detection accuracy of the proposed approach reached as high as 85.62%, with equivalent event frame rate of 40 frames per second on average. The proposed method can be further applied to other areas where high dynamical object detection is required. © 2025
Author Keywords	Dynamic Vision Sensor; Smart city; Traffic flow measurement

Similar Articles

Id	Similarity	Authors	Title	Published
11029	0.912	Zhang H.; Liu J.; Tang Y.; Xiong G.	Attention Based Graph Covolution Networks For Intelligent Traffic Flow Analysis	IEEE International Conference on Automation Science and Engineering, 2020-August (2020)
4796	0.909	Ratnam V.S.; Suganya E.; Al-Farouni M.H.; Jeyanthi S.; Rajani Kanth T.V.	A Smart Traffic Flow Optimization Using Graph Convolutional Network With Graph Long Short-Term Memory	2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024 (2024)
24078	0.891	Mohsin K.S.; Mettu J.; Madhuri C.; Usharani G.; Silpa N.; Yellamma P.	Enhancing Urban Traffic Management Through Hybrid Convolutional And Graph Neural Network Integration	Journal of Machine and Computing, 4, 2 (2024)
34723	0.888	Zhou J.; Shuai S.; Wang L.; Yu K.; Kong X.; Xu Z.; Shao Z.	Lane-Level Traffic Flow Prediction With Heterogeneous Data And Dynamic Graphs	Applied Sciences (Switzerland), 12, 11 (2022)
52517	0.887	Huang X.; Pan Z.; Zhao G.	Spatial-Temporal Interactive Graph Convolutional Networks For Traffic Forecasting	2024 4th International Conference on Electronic Information Engineering and Computer Technology, EIECT 2024 (2024)
9007	0.887	Xu X.; Mao H.; Zhao Y.; Lü X.	An Urban Traffic Flow Fusion Network Based On A Causal Spatiotemporal Graph Convolution Network	Applied Sciences (Switzerland), 12, 14 (2022)
44472	0.887	Nie X.; Peng J.; Wu Y.; Gupta B.B.; El-Latif A.A.A.	Real-Time Traffic Speed Estimation For Smart Cities With Spatial Temporal Data: A Gated Graph Attention Network Approach	Big Data Research, 28 (2022)
58576	0.886	Zheng L.; Pu Y.; Sun W.	Traffic Flow Prediction Algorithm Based On Attention Spatiotemporal Graph Convolution Mechanism	IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) (2024)
20800	0.886	Diao Z.; Wang X.; Zhang D.; Xie G.; Chen J.; Pei C.; Meng X.; Xie K.; Zhang G.	Dmstg: Dynamic Multiview Spatio-Temporal Networks For Traffic Forecasting	IEEE Transactions on Mobile Computing, 23, 6 (2024)
3380	0.885	Hussain B.; Afzal M.K.; Anjum S.; Rao I.; Kim B.-S.	A Novel Graph Convolutional Gated Recurrent Unit Framework For Network-Based Traffic Prediction	IEEE Access, 11 (2023)