基于改进YOLOv8的高速公路服务区车辆违停检测

doi:10.19678/j.issn.1000-3428.0068901

摘要/Abstract

摘要：

在高速公路服务区违停检测过程中光照、天气变化等复杂环境会使车辆检测精度急剧下降, 同时摄像机拍摄角度、车体高度等因素会增加车辆违停检测的误报率和漏报率。为此, 提出一种基于改进YOLOv8的高速公路服务区违停检测算法。在YOLOv8网络模型的特征金字塔池化层中, 构建膨胀空间金字塔池化(DSPP)模块和基于分支注意力机制的膨胀空间金字塔池化(DSPPA)模块, 减少特征提取网络中深层语义信息的丢失, 同时利用DSPPA中的分支注意力(BA)机制为不同感受野分支特征赋予不同的权重, 使模型更关注与目标尺寸相适应的特征。设计基于全局匹配的停车位分配策略, 有效降低了视角倾斜、车辆重叠遮挡等情况下违规占用停车位的误报率与漏报率。实验结果表明, 改进算法的违停检测误报率从15%下降至8%, 违停检测漏报率从7.5%下降至6.1%, 具有较好的车辆违停检测效果。

关键词: YOLOv8, 车辆检测, 空间金字塔池化, 全局匹配, 车辆违停检测

Abstract:

In highway service areas, complex environments such as lighting and weather changes can cause a sharp decline in vehicle detection accuracy. In addition, factors such as the inclination angle of the camera and the height of installation can increase false-negative and false-positive rates. To this end, a vehicle violation detection algorithm based on the improved YOLOv8 is proposed for highway service areas. First, the feature pyramid pooling layer of the YOLOv8 network, a Dilated Space Pyramid Pooling(DSPP) module, and a DSPP based on branch Attention(DSPPA) module are constructed to reduce the loss of semantic information in the backbone. The Branch Attention(BA) mechanism in DSPPA assigns different weights to the branches with varying degrees of contribution, making the model focus more on features that are suitable for the target size. Second, a parking space allocation strategy based on global matching is designed to effectively reduce the false-negative and false-positive rates of illegal parking detection in situations involving tilted views and overlapping vehicles. The experimental results show that the improved algorithm reduces the false-negative rate of parking violation detection from 15% to 8% and the false-positive rate from 7.5% to 6.1%, demonstrating considerable performance improvement in vehicle violation detection.

Key words: YOLOv8, vehicle detection, Spatial Pyramid Pooling(SPP), global matching, vehicle violation detection

陈伟, 王晓龙, 张晏玮, 安国成, 江波. 基于改进YOLOv8的高速公路服务区车辆违停检测[J]. 计算机工程, 2024, 50(4): 11-19.

Wei CHEN, Xiaolong WANG, Yanwei ZHANG, Guocheng AN, Bo JIANG. Vehicle Violation Detection Based on Improved YOLOv8 in Highway Service Areas[J]. Computer Engineering, 2024, 50(4): 11-19.

https://www.ecice06.com/CN/Y2024/V50/I4/11

图/表 16

图1 车辆违停检测算法流程

Fig.1 Procedure of vehicle violation detection algorithm

图2 YOLOv8网络结构

Fig.2 Network structure of YOLOv8

图3 SPP模块结构

Fig.3 Structure of SPP module

图4 最大池化与分组膨胀卷积操作

Fig.4 Maxpooling and group dilation convolution operation

图5 DSPP模块结构

Fig.5 Structure of DSPP module

图6 DSPPA模块结构

Fig.6 Structure of DSPPA module

图7 拍摄角度、车体高度等差异产生的误分配

Fig.7 Mismatching caused by differences such as shooting angle and vehicle height

图8 基于全局匹配的停车位分配策略流程

Fig.8 Process of parking space allocation strategy based on global matching

图9 停车位占用权重划分

Fig.9 Weight division of parking space occupancy

图10 各车型样本数量分布

Fig.10 Distribution of number of samples for different kind of vehicles

图11 改进前后的车辆违停检测算法的漏报率与误报率对比

Fig.11 Comparison of false-negative and false-positive rates between pre- and post-improvement vehicle violation detection algorithms

图12 高速公路服务区车辆违停检测可视化结果

Fig.12 Visualization results of vehicle violation detection in highway service areas

参考文献 25

1	张增超, 李强, 孙红雨, 等. 基于地磁传感器和UWB技术的停车位车辆检测方法与实现. 传感技术学报, 2019, 32 (12): 1917- 1922. URL
	ZHANG Z C, LI Q, SUN H Y, et al. Parking vehicle detection method and implementation based on geomagnetic sensor and UWB technology. Chinese Journal of Sensors and Actuators, 2019, 32 (12): 1917- 1922. URL
2	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. URL
	LI S J, GENG L L, WANG P. Vehicle target detection based on improved Yolov4. Computer Engineering, 2023, 49 (4): 272- 280. URL
3	BOCHKOVSKIY A, WANG C Y, LIAO H. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2023-10-19]. https://arxiv.org/abs/2004.10934.
4	杨露露, 马萍, 王聪, 等. 结合特征重用与特征重建的YOLO绝缘子检测方法[J/OL]. 计算机工程: 1-10[4-10-19]. https://doi.org/10.19678/j.issn.1000-3428.0068244.
	YANG L L, MA P, WANG C, et al. YOLO insulator detection method combining feature reuse and feature rebuild[J/OL]. Computer Engineering: 1-10[2023-10-19]. https://doi.org/10.19678/j.issn.1000-3428.0068244. (in Chinese)
5	HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[EB/OL]. [2023-10-19]. https://arxiv.org/abs/1608.06993.
6	杨祖莨, 丁洁, 刘晋峰. 一种新的结合卷积神经网络的隧道内停车检测方法. 重庆大学学报, 2021, 44 (6): 49- 59. URL
	YANG Z L, DING J, LIU J F. A new tunnel vehicle stopping detection methodology combined with convolutional neural network. Journal of Chongqing University, 2021, 44 (6): 49- 59. URL
7	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60 (6): 84- 90. doi: 10.1145/3065386
8	李国进, 胡洁, 艾矫燕. 基于改进SSD算法的车辆检测. 计算机工程, 2022, 48 (1): 266- 274. URL
	LI G J, HU J, AI J Y. Vehicle detection based on improved SSD algorithm. Computer Engineering, 2022, 48 (1): 266- 274. URL
9	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.
10	GIRSHICK R. Fast R-CNN[C]//Proceedings of IEEE International Conference on Computer Vision(ICCV). Washington D. C., USA: IEEE Press, 2015: 1440-1448.
11	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
12	DAI J F, LI Y, HE K M, et al. R-FCN: object detection via region-based fully convolutional networks[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2016: 379-387.
13	HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (2): 386- 397. doi: 10.1109/TPAMI.2018.2844175
14	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[EB/OL]. [2023-10-19]. https://arxiv.org/abs/1506.02640.
15	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-10-19]. https://arxiv.org/abs/1804.02767.
16	WANG C Y, BOCHKOVSKIY A, LIAO H. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[EB/OL]. [2023-10-19]. https://arxiv.org/abs/2207.02696.
17	GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. [2023-10-19]. https://arxiv.org/abs/2107.08430.
18	WANG C Y, YEH I H, LIAO H Y M. You only learn one representation: unified network for multiple tasks[EB/OL]. [2023-10-19]. https://arxiv.org/abs/2105.04206.
19	HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37 (9): 1904- 1916. doi: 10.1109/TPAMI.2015.2389824
20	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2017: 6000-6010.
21	WANG C Y, LIAO H Y M, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN[EB/OL]. [2023-10-19]. https://arxiv.org/abs/1911.11929.
22	LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[EB/OL]. [2023-10-19]. https://arxiv.org/abs/1612.03144.
23	LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 3698141.
24	YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL]. [2023-10-19]. https://arxiv.org/abs/1511.07122.
25	HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (8): 2011- 2023. doi: 10.1109/TPAMI.2019.2913372

[1]	贵向泉, 刘世清, 李立, 秦庆松, 李唐艳. 基于改进YOLOv8的景区行人检测算法[J]. 计算机工程, 2024, 50(7): 342-351.
[2]	陈伟, 王晓龙, 张晏玮, 安国成, 江波. 基于改进YOLOv8的高速公路服务区车辆违停检测[J]. 计算机工程, 2024, 50(4): 11-19.
[3]	赵继达, 甄国涌, 储成群. 基于YOLOv8的无人机图像目标检测算法[J]. 计算机工程, 2024, 50(4): 113-120.
[4]	李松江, 耿兰兰, 王鹏. 基于改进Yolov4的车辆目标检测[J]. 计算机工程, 2023, 49(4): 272-280.
[5]	马素刚, 陈期梅, 侯志强, 杨小宝, 张子贤. 基于密集连接与特征增强的语义分割算法[J]. 计算机工程, 2023, 49(3): 263-270.
[6]	郭克友, 王苏东, 李雪, 张沫. 基于Dim env-YOLO算法的昏暗场景车辆多目标检测[J]. 计算机工程, 2023, 49(3): 312-320.
[7]	王楷, 韩笑, 朱华吉, 缪祎晟, 吴华瑞. 基于YOLACT-RFX模型的穴盘甘蓝苗株分割算法[J]. 计算机工程, 2023, 49(12): 214-223.
[8]	王晓龙, 江波. 基于改进YOLOX-m的安全帽佩戴检测[J]. 计算机工程, 2023, 49(12): 252-261.
[9]	李国进, 胡洁, 艾矫燕. 基于改进SSD算法的车辆检测[J]. 计算机工程, 2022, 48(1): 266-274.
[10]	赵晨园, 李文新, 张庆熙. 一种改进的实时半全局立体匹配算法及硬件实现[J]. 计算机工程, 2021, 47(9): 162-170.
[11]	江枭宇, 李忠兵, 张军豪, 彭娇, 文婷. 基于NCS2神经计算棒的车辆检测方法[J]. 计算机工程, 2021, 47(3): 298-303.
[12]	李培媛, 黄迟. 基于CSPPNet与集成学习的人类蛋白质图像分类方法[J]. 计算机工程, 2020, 46(8): 235-242.
[13]	王金鹤, 苏翠丽, 孟凡云, 车志龙, 谭浩, 张楠. 基于非对称空间金字塔池化的立体匹配网络[J]. 计算机工程, 2020, 46(7): 228-234,242.
[14]	王艺皓, 丁洪伟, 李波, 杨志军, 杨俊东. 复杂场景下基于改进YOLOv3的口罩佩戴检测算法[J]. 计算机工程, 2020, 46(11): 12-22.
[15]	夏胡云,叶学义,罗宵晗,王鹏. 多尺度空间金字塔池化PCANet的行人检测[J]. 计算机工程, 2019, 45(2): 270-277.

选择文件类型/文献管理软件名称

选择包含的内容