A CNN-RF-SVM Hybrid Method for Traffic Congestion Monitoring

DOI

10.2991/978-94-6239-648-7_12How to use a DOI?

Keywords

CNN-RF-SVM Composite Method; Traffic Congestion Identification; Traffic Density Singapore

Abstract

With the development of the automotive industry and increasing demand for personal mobility, the growing number of vehicles on roads has led to traffic congestion and environmental pollution. Accurate traffic congestion monitoring has become a prominent research focus. The integration of surveillance camera recognition with intelligent transportation systems presents a promising solution for congestion mitigation. This study categorizes traffic congestion data collected from Singapore’s Land Transport Authority (LTA) open API into five classes: empty, low, medium, high, and congested. The dataset is then partitioned into three subsets (training, validation, and testing) through stratified sampling. A hybrid CNN-RF-SVM approach is proposed for congestion detection. Experimental results demonstrate that compared with traditional image recognition models, the proposed method achieves 36.6% and 26% improvements in F1-score over CNN-SVM and CNN-RF models respectively. The framework provides high-precision road congestion identification, which can effectively identify and judge congested roads, offering reliable data support for real-time monitoring and dynamic traffic management.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jiaxu Zhu
PY  - 2026
DA  - 2026/04/24
TI  - A CNN-RF-SVM Hybrid Method for Traffic Congestion Monitoring
BT  - Proceedings of the International Workshop on Advances in Deep Learning for Image Analysis and Computer Vision (IWADIC 2025)
PB  - Atlantis Press
SP  - 97
EP  - 106
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-648-7_12
DO  - 10.2991/978-94-6239-648-7_12
ID  - Zhu2026
ER  -