Congestion Detection Algorithm of Highway Toll Station Based on Multi-Information Fusion

doi:10.19678/j.issn.1000-3428.0069031

Abstract

Abstract:

At highway toll stations, factors such as occlusion, shadows, and the depth of field significantly impact the accuracy of congestion detection. Moreover, relying solely on a single parameter for congestion detection cannot accurately reflect the actual congestion situation at toll stations. To address these challenges, this paper proposes a multistep approach. First, a target detection algorithm is employed to identify vehicles within the designated area. Spatial features extracted from the images of these vehicles are used to calculate the lane occupancy rate. Second, comprehensive vehicle flow is estimated utilizing the Deep SORT target tracking algorithm and sliding balance mechanism to mitigate false and missed detections caused by occlusion and shadowing effects. Furthermore, an optical flow-based vehicle speed estimation method is utilized to reduce congestion detection errors resulting from changes in the depth of field. Finally, through the fusion of three distinct dimensions of information (target presence, lane occupancy rate, and vehicle speed), a congestion index is obtained. The values of this index can be clustered into five categories to determine the real-time congestion state at highway toll stations. Experimental are conducted on a congested dataset collected from high-speed toll stations. The results demonstrate that the proposed multi-information fusion-based congestion detection algorithm achieves an accuracy rate of 90.4%, enabling the precise identification of traffic congestion at toll stations.

Key words: multi-information fusion, object detection, object tracking, vehicle speed estimation, congestion detection

摘要：

在高速收费站拥堵检测场景中, 遮挡、阴影、景深等因素严重影响检测算法的精度, 基于单信息的拥堵检测算法无法准确反映收费站真实拥堵情况, 对此, 提出一种高速收费站多信息融合拥堵检测算法。首先采用目标检测算法检测目标区域车辆, 利用图像空间特征计算车道占用率; 其次利用Deep SORT目标跟踪算法与滑动平衡机制进行车流量综合估计, 减少因为遮挡和阴影导致的车辆误检、漏检问题; 最后利用基于光流信息熵的车速估计方法, 降低因景深变化导致的拥堵状态检测误差。通过融合3种不同维度信息得到拥堵指数, 拥堵指数聚类为5种拥堵类别以判断真实拥堵状态, 从而实现高速收费站的拥堵检测。实验结果表明, 在高速收费站拥堵数据集上, 采用多信息融合的拥堵检测算法准确率达到90.4%, 能够实现对收费站拥堵状态的准确检测。

关键词: 多信息融合, 目标检测, 目标跟踪, 车速估计, 拥堵检测

WANG Xiaolong, JIANG Bo, LUO Runshu, AN Guocheng. Congestion Detection Algorithm of Highway Toll Station Based on Multi-Information Fusion[J]. Computer Engineering, 2025, 51(5): 377-386.

王晓龙, 江波, 罗润书, 安国成. 基于多信息融合的高速收费站拥堵检测算法[J]. 计算机工程, 2025, 51(5): 377-386.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069031

https://www.ecice06.com/EN/Y2025/V51/I5/377

Figures/Tables 10

Fig.1 YOLOv5 network structure

Fig.2 Deep SORT tracking procedure

Fig.3 Congestion detection algorithm procedure

Fig.4 Shi-Tomasi corner detection

Fig.5 L-K optical flow pyramid

Fig.6 Five congestion status

Fig.7 Multi-Information box-plot

Fig.8 Multi-information box-plot(after data cleaning)

References 25

1	张欢, 史峰. 基于流量预测的高速公路收费员动态配置模型. 交通运输系统工程与信息, 2009, 9(5): 71- 76.
	ZHANG H, SHI F. Dynamic equilibrium model of expressway toll collector based on traffic flow prediction. Journal of Transportation Systems Engineering and Information Technology, 2009, 9(5): 71- 76.
2	丁栋, 朱云龙, 库涛, 等. 基于影响模型的短时交通流预测方法. 计算机工程, 2012, 38(10): 164- 167. doi: 10.3969/j.issn.1000-3428.2012.10.050
	DING D, ZHU Y L, KU T, et al. Short-term traffic flow forecasting method based on influence model. Computer Engineering, 2012, 38(10): 164- 167. doi: 10.3969/j.issn.1000-3428.2012.10.050
3	孙玉砚, 孙利民, 朱红松, 等. 基于车牌识别系统车辆轨迹的行为异常检测. 计算机研究与发展, 2015, 52(8): 1921- 1929.
	SUN Y Y, SUN L M, ZHU H S, et al. Activity anomaly detection based on vehicle trajectory of automatic number plate recognition system. Journal of Computer Research and Development, 2015, 52(8): 1921- 1929.
4	杨龙海, 徐洪, 张春. 基于GPS数据的高速公路车辆异常行为检测. 重庆交通大学学报(自然科学版), 2018, 37(5): 97- 103.
	YANG L H, XU H, ZHANG C. Vehicle abnormal behavior detection on freeway based on global positioning system data. Journal of Chongqing Jiaotong University (Natural Science), 2018, 37(5): 97- 103.
5	蒋刚毅, 郁梅, 叶锡恩, 等. 一种基于视觉的车辆跟踪及交通流量参数估计新方法. 电路与系统学报, 2001, 6(4): 69-73, 83.
	JIANG G Y, YU M, YE X E, et al. New method of vision based vehicle tracking and traffic parameter estimation. Journal of Circuits and Systems, 2001, 6(4): 69-73, 83.
6	赖见辉, 王扬, 罗甜甜, 等. 基于YOLO_v3的侧视视频交通流量统计方法与验证. 公路交通科技, 2021, 38(1): 135- 142.
	LAI J H, WANG Y, LUO T T, et al. A YOLO_v3-based road-side video traffic volume counting method and verification. Journal of Highway and Transportation Research and Development, 2021, 38(1): 135- 142.
7	李俊彦, 宋焕生, 张朝阳, 等. 基于视频的多目标车辆跟踪及轨迹优化. 计算机工程与应用, 2020, 56(5): 194- 199.
	LI J Y, SONG H S, ZHANG Z Y, et al. Multi-object vehicle tracking and trajectory optimization based on video. Computer Engineering and Applications, 2020, 56(5): 194- 199.
8	SONG H S, LIANG H X, LI H Y, et al. Vision-based vehicle detection and counting system using deep learning in highway scenes. European Transport Research Review, 2019, 11, 51. doi: 10.1186/s12544-019-0390-4
9	李松江, 耿兰兰, 王鹏. 基于改进Yolov4的车辆目标检测. 计算机工程, 2023, 49(4): 272- 280. doi: 10.19678/j.issn.1000-3428.0062943
	LI S J, GENG L L, WANG P. Vehicle target detection based on improved Yolov4. Computer Engineering, 2023, 49(4): 272- 280. doi: 10.19678/j.issn.1000-3428.0062943
10	LUVIZON D C, NASSU B T, MINETTO R. A video-based system for vehicle speed measurement in urban roadways. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(6): 1393- 1404.
11	邹国建, 赖子良, 李晔. 基于时空注意力网络的动态高速路网交通速度预测. 计算机工程, 2023, 49(2): 303- 313. doi: 10.19678/j.issn.1000-3428.0063777
	ZOU G J, LAI Z L, LI Y. Traffic speed prediction based on spatio-temporal attention network for dynamic expressway network. Computer Engineering, 2023, 49(2): 303- 313. doi: 10.19678/j.issn.1000-3428.0063777
12	CHAKRABORTY P, ADU-GYAMFI Y O, PODDAR S, et al. Traffic congestion detection from camera images using deep convolution neural networks. Transportation Research Record: Journal of the Transportation Research Board, 2018, 2672(45): 222- 231. doi: 10.1177/0361198118777631
13	LIN Y, WANG R F, ZHU R, et al. The short-term exit traffic prediction of a toll station based on LSTM. Cham: Springer, 2020.
14	WANG P, ZHAO J D, GAO Y, et al. Lane work-schedule of toll station based on queuing theory and PSO-LSTM model. IEEE Access, 2020, 8, 84434- 84443. doi: 10.1109/ACCESS.2020.2992070
15	PETROVI AĆG A, NIKOLI AĆG M, BUGARI AĆG U, et al. Controlling highway toll stations using deep learning, queuing theory, and differential evolution. Engineering Applications of Artificial Intelligence, 2023, 119, 105683. doi: 10.1016/j.engappai.2022.105683
16	KE X, SHI L F, GUO W Z, et al. Multi-dimensional traffic congestion detection based on fusion of visual features and convolutional neural network. IEEE Transactions on Intelligent Transportation Systems, 2018, 20(6): 2157- 2170.
17	HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 1973, 3(6): 610- 621.
18	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. D., USA: IEEE Press, 2016: 779-788.
19	BEWLEY A, GE Z Y, OTT L, et al. Simple online and realtime tracking[EB/OL]. [2023-11-10]. https://arxiv.org/abs/1602.00763v2.
20	REID D. An algorithm for tracking multiple targets. IEEE Transactions on Automatic Control, 1979, 24(6): 843- 854. doi: 10.1109/TAC.1979.1102177
21	WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric[C]//Proceedings of IEEE International Conference on Image Processing. Washington D. D., USA: IEEE Press, 2017: 3645-3649.
22	LUCAS B D, KANADE T, LUCAS B D, et al. An iterative image registration technique with an application to stereo vision[C]//Proceedings of the 7th International Joint Conference on Artificial Intelligence. New York, USA: ACM Press, 1981: 674-679.
23	SHI J B, TOMASI. Good features to track[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. D., USA: IEEE Press, 1994: 593-600.
24	QUEEN J M. Some methods for classification and analysis of multivariate observations[C]//Proceedings of the 2nd Berkeley Symposium on Mathematical Statistics and Probability. Washington D. D., USA: IEEE Press, 1967: 281-297.
25	ARTHUR D, VASSILVITSKⅡ S, ARTHUR D, et al. K-means++[C]//Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms. New York, USA: ACM Press, 2007: 1027-1035.

[1]	XU Huajie, ZHENG Liwen, ZHANG Pin, QIN Yuanzhuo. Lightweight Concrete Crack Detection Method Based on Multi-Dimensional Attention Module [J]. Computer Engineering, 2025, 51(5): 351-360.
[2]	HUANG Kun, QI Zhaojian, WANG Juanmin, HU Qian, HU Weichao, PI Jianyong. Aggregation Pedestrian Detection Model Based on Improved YOLOv8 [J]. Computer Engineering, 2025, 51(5): 133-142.
[3]	WANG Zeyu, XU Huiying, ZHU Xinzhong, HUANG Xiao, LIANG Jiajie, LI Chen. Lightweight Fry Detection Algorithm Based on Improved YOLOv8: FD-YOLO [J]. Computer Engineering, 2025, 51(4): 327-338.
[4]	ZHOU Hanqi, FANG Dongxu, ZHANG Ningbo, SUN Wensheng. Multi-UAV Multi-Object Tracking Based on Deep Learning [J]. Computer Engineering, 2025, 51(4): 57-65.
[5]	LI Shuwei, HUANG Zhengxiang, HU Yun, LIU Xing, LU Xiao, GUO Chang, WU Chengzhong, WANG Yaonan. Low-Light Salient Object Detection Based on Source-Free Domain Adaptation [J]. Computer Engineering, 2025, 51(4): 75-84.
[6]	SUN Ziwen, QIAN Lizhi, YUAN Guanglin, YANG Chuandong, LING Chong. Transformer Object Tracking Method Based on Real-Time Dynamic Template Update [J]. Computer Engineering, 2025, 51(4): 158-168.
[7]	CUI Jinrong, YE Weihao, ZHENG Hong, LIU Tonglai, QI Long, XU Yong. Rice Seedling Counting in Complex Environments Based on Domain-Adaptive NWD-YOLOv5 [J]. Computer Engineering, 2025, 51(3): 320-333.
[8]	ZHANG Zhaoxin, HUANG Shize, ZHANG Bingjie, SHEN Tuo. Camouflaged Adversarial Example Generation Method for the Form of Motion Blur in Traffic Scenes [J]. Computer Engineering, 2025, 51(3): 45-53.
[9]	HUANG Shuyi, TAN Guang. Efficient Video Object Detection Based on Partitioning [J]. Computer Engineering, 2025, 51(2): 65-77.
[10]	SUN Haomiao, LI Zongmin, XIAO Qian, SUN Wenjie, ZHANG Wenxin. AI-Curling: An On-Site Curling Analysis and Decision-Making Method [J]. Computer Engineering, 2025, 51(2): 102-110.
[11]	LI Haifeng, LIU Sensen, WANG Huaichao, LI Nansha, ZHANG Yifan. Airport Pavement Underground Disease Detection Algorithm Integrating Association Reasoning [J]. Computer Engineering, 2025, 51(2): 397-406.
[12]	YANG Lisha, LI Maojun, HU Jianwen, WANG Dingxiang. Strip Steel Surface Defect Detection Algorithm Based on Improved YOLOv7-tiny [J]. Computer Engineering, 2025, 51(1): 208-215.
[13]	HU Shenglong, CHEN Bin, ZHANG Kaihua, SONG Huihui. Co-Saliency Object Detection Enhanced by Scene Structure Knowledge [J]. Computer Engineering, 2025, 51(1): 31-41.
[14]	ZENG Yuqi, LIU Bo, ZHONG Baichang, ZHONG Jin. Student Classroom Behavior Detection Algorithm Based on Improved YOLOv8 in Smart Education [J]. Computer Engineering, 2024, 50(9): 344-355.
[15]	LIN Chang, GUO Wei, REN Zhecong, JIN Haibo. Unification Algorithm for Object Tracking and Segmentation Based on Transformer [J]. Computer Engineering, 2024, 50(9): 130-141.

Please choose a citation manager

Content to export