With the rapid development of intelligent transportation systems, accurate recognition of traffic states plays a pivotal role in improving traffic efficiency and ensuring travel safety. Based on video image data, a traffic state recognition model based on the Vision-KAN network was constructed to identify four core traffic states, namely traffic accidents, traffic congestion, traffic fires, and smooth traffic. To verify the effectiveness of this model, the basic models of residual networks (ResNet), convolutional neural networks (CNN) and vision transformer (ViT) were selected for comparison. The experimental results show that the Vision-KAN model outperforms the comparison models in all aspects and demonstrates a high-precision recognition ability for traffic states in video images. It can provide strong support for intelligent traffic management and control as well as emergency response, and enhance road traffic efficiency and security guarantee capabilities.
ZHANG Hong-jun, ZHOU Wei, QI Yu-liang, JIN Shu-qing, TIAN Hai-feng.
Road Traffic State Recognition Based on Vision-KAN[J].
Science Technology and Engineering, 2026, 26(1): 369-374 DOI:10.12404/j.issn.1671-1815.2501888
ZhangL, JiaY, SunD, et al. A fuzzy weighted C-means classification method for traffic flow state division[J]. Modern Physics Letters B, 2021, 35(20): 2150341.
XuChuan, ZhuXinping, QuJingjing, et al. Prediction of traffic congestion status level at large airport fields[J]. Science Technology and Engineering, 2022, 22(35): 15825-15831.
HuangJiahui, HuangHe, YangLan, et al. An optimized method for urban traffic state discrimination[J]. Journal of Fudan University (Natural Science), 2025, 64(1): 1-13.
ChenYue, YangLiu, LiShuai, et al. Traffic congestion prediction algorithm based on CS-BiLSTM framework[J]. Science Technology and Engineering, 2022, 22(29): 12917-12926.
LiPengcheng, DongBaotian, LiSixian. Intersection traffic state recognition and correlation degree study based on temporal graph attention[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(5): 67-74.
CuiShuyan, YuRende, ZhuYanhua. Research on traffic state recognition method based on SVM[J]. Journal of Shandong University of Technology(Natural Science Edition), 2024, 38(5): 7-11, 60.
PengBo, TangJu, ZhangYuanyuan, et al. Automatic traffic state recognition from road videos based on 3D convolution neural network[J]. Journal of Southwest Jiaotong University, 2021, 56(1): 153-159.
[18]
CaiX, JingQ, PengB, et al. Automatic traffic state recognition based on video features extracted by an autoencoder[J]. Mathematical Problems in Engineering, 2022, 2022: 2850111.
LiXiying, LuMeiyan, HeZhaocheng, et al. Traffic state recognition based on vehicle dynamic behavior characteristics[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 44-55, 85.
[21]
LiuZ, WangY, VaidyaS, et al. KAN: Kolmogorov-Arnold networks[C]// 13th International Conference on Learning Representations. Singapore: ICLR, 2024: 66342-6638.
[22]
CheonM. Demonstrating the efficacy of Kolmogorov-Arnold networks in vision tasks[J]. ArXiv: 2406. 14916, 2024.