交通场景下的大型车辆右转停车检测方法研究

doi:10.3778/j.issn.1002-8331.2308-0252

摘要/Abstract

摘要： 随着大型车辆右转必停的新交规逐步实施，针对现有的监管方式存在效率较低的问题，提出了一种大型车辆右转停车检测方法。对YOLOv7-tiny检测模型进行改进，在ELAN模块中引入注意力机制，以提升大型车辆的检测性能。设计了一种新的大型车辆右转车道定位方法，通过自适应探测车道，提高了其在不同监控视角下的定位准确性。对大型车辆的运动轨迹进行序列数据转换，并采用结合加权平均的中值滤波算法，有效降低了原始数据的噪声。在滑动窗口损失函数中引入权重因子，进一步提升了检测方法的鲁棒性。实验结果表明，改进后的大型车辆检测模型在自制数据集和公开数据集上均取得了性能提升，大型车辆右转车道定位方法具有更强的泛化能力，并且检测到的停车时间覆盖率达到了97.4%。

关键词: 大型车辆检测, 车道定位, 滤波算法, 损失函数, 停车时间检测

Abstract: With the gradual implementation of the new regulation requiring large vehicles to come to a complete stop before making a right turn, a detection method for right-turning parking of large vehicles is proposed to address the inefficiency of the existing regulatory approaches. Firstly, improvements are made to the YOLOv7-tiny detection model by introducing an attention mechanism in the ELAN module to enhance the detection performance of large vehicles. Next, a new method for locating the right turn lanes of large vehicles is designed, which improves the accuracy of positioning under different monitoring perspectives by using adaptive lane detection. Finally, the motion trajectory of large vehicles is transformed into sequential data, and a weighted average median filtering algorithm is employed to effectively reduce the noise in the original data. Simultaneously, a weight factor is introduced in the sliding window loss function to further enhance the robustness of the detection method. Experimental results demonstrate that the improved detection model for large vehicles achieves performance improvements on both self-made datasets and publicly available datasets. The method for locating the right turn lanes of large vehicles exhibits stronger generalization ability, and the coverage rate of detected parking time reaches 97.4%.

Key words: detection of large vehicles, lane positioning, filtering algorithm, loss function, parking time detection

王依凡, 董振江, 陈向东. 交通场景下的大型车辆右转停车检测方法研究[J]. 计算机工程与应用, 2025, 61(1): 352-360.

WANG Yifan, DONG Zhenjiang, CHEN Xiangdong. Research on Right Turn Parking Detection Method for Large Vehicles in Traffic Scenarios[J]. Computer Engineering and Applications, 2025, 61(1): 352-360.

参考文献

[1] WANG Z G, ZHAN J, DUAN C G, et al. A review of vehicle detection techniques for intelligent vehicles[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(8): 3811-3831.
[2] HOU X Y, WANG Y, CHAU L P. Vehicle tracking using deep SORT with low confidence track filtering[C]//Proceedings of the 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance. Piscataway: IEEE, 2019: 1-6.
[3] 李华. 基于人工智能的非现场执法场景下闯红灯违法行为检测[D]. 杭州: 杭州电子科技大学, 2022.
LI H. Detection of illegal behavior of running red light in off-site law enforcement scene based on artificial intelli-gence[D]. Hangzhou: Hangzhou Dianzi University, 2022.
[4] 宁交轩, 王茸. 道路交通事故死亡人数三连降[N]. 南京日报, 2023-06-28(A08).
NING J X, WANG R. Three consecutive declines in road traffic accident fatality numbers[N]. Nanjing Daily, 2023-06-28(A08).
[5] CAO X B, WU C X, YAN P K, et al. Linear SVM classification using boosting HOG features for vehicle detection in low-altitude airborne videos[C]//Proceedings of the 2011 18th IEEE International Conference on Image Processing. Piscataway: IEEE, 2011: 2421-2424.
[6] 张亮修. 基于Haar-like特征的实时道路车辆识别方法研究[D]. 青岛: 青岛大学, 2009.
ZHANG L X. Research on real-time road vehicle recognition method based on Haar-like feature[D]. Qingdao: Qingdao University, 2009.
[7] 李双. 基于Harris-SIFT和归一化割算法的车辆检测与识别[D]. 哈尔滨: 哈尔滨工程大学, 2012.
LI S. Vehicle detection and recognition based on Harris-SIFT and normalized cut algorithm[D]. Harbin: Harbin Engineering University, 2012.
[8] YU G H, YU P F, LI H Y, et al. An improved faster R-CNN method for car front detection[C]//Proceedings of the 2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference. Piscataway: IEEE, 2022: 7-12.
[9] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[10] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.
[11] LIU X M, FENG J, CHEN P. Vehicle detection in traffic monitoring scenes based on improved YOLOV5s[C]//Proceedings of the 2022 International Conference on Computer Engineering and Artificial Intelligence. Piscataway: IEEE, 2022: 467-471.
[12] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
[13] WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 7464-7475.
[14] 文奴, 郭仁忠, 贺彪. 基于DCN-Mobile-YOLO模型的多车道车辆计数[J]. 深圳大学学报(理工版), 2021, 38(6): 628-635.
WEN N, GUO R Z, HE B. Multi-lane vehicle counting based on DCN-Mobile-YOLO model[J]. Journal of Shenzhen University (Science and Engineering), 2021, 38(6): 628-635.
[15] PORIKLI F. Detection of temporarily static regions by processing video at different frame rates[C]//Proceedings of the 2007 IEEE Conference on Advanced Video and Signal Based Surveillance. Piscataway: IEEE, 2007: 236-241.
[16] 石时需, 郑启伦, 黄翰, 等. 基于粒子滤波算法的高速公路车辆停车检测[J]. 计算机工程与应用, 2008, 44(34): 239-242.
SHI S X, ZHENG Q L, HUANG H, et al. Vehicle breaking detection on express way based on particle filter algorithm[J]. Computer Engineering and Applications, 2008, 44(34): 239-242.
[17] 丁冰, 杨祖莨, 丁洁, 等. 基于改进YOLOv3的高速公路隧道内停车检测方法[J]. 计算机工程与应用, 2021, 57(23): 234-239.
DING B, YANG Z L, DING J, et al. Detection method of highway tunnel vehicle stopping based on improved YOLOv3[J]. Computer Engineering and Applications, 2021, 57(23): 234-239.
[18] WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric[C]//Proceedings of the 2017 IEEE International Conference on Image Processing. Piscataway: IEEE, 2017: 3645-3649.
[19] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13708-13717.
[20] LIN T Y, DOLLáR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 936-944.
[21] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8759-8768.
[22] WANG C Y, MARK LIAO H Y, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2020: 1571-1580.
[23] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.
[24] WANG C Y, YEH I H, LIAO H. You only learn one representation: unified network for multiple tasks[J]. Journal of Information Science and Engineering, 2021, 39: 691-709.
[25] WEN L Y, DU D W, CAI Z W, et al. UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking[J]. Computer Vision and Image Understanding, 2020, 193: 102907.
[26] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv: 1804. 02767, 2018.
[27] LI C Y, LI L L, JIANG H L, et al. YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv:2209.02976, 2022.
[28] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer, 2018: 3-19.
[29] WANG Q, WU B, ZHU P, et al. ECA-net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11531-11539.