重参数化YOLOv8路面病害检测算法

doi:10.3778/j.issn.1002-8331.2309-0354

摘要/Abstract

摘要： Road disease detection is an important way to ensure people’s traffic safety. In order to improve the accuracy of road disease detection and achieve timely and accurate road disease detection, a pavement disease detection model of re-parameterized YOLOv8 is proposed. First of all, CNX2f module is introduced into the backbone network to improve the ability of the network to extract pavement disease features, and effectively solve the problem that the pavement disease features are easily confused with the background environmental features. Secondly, RepConv and DBB reparameterization modules are introduced to enhance the capability of multi-scale feature fusion and solve the problem of large scale difference of pavement diseases. At the same time, the shared parameter structure of the head is improved, and RBB reparameterization module is introduced to solve the problem of head parameter redundancy and improve the feature extraction capability. Finally, the SPPF_Avg module is introduced to solve the problem of pavement feature loss and enrich the multi-scale feature expression. The experimental results show that the accuracy of the improved road disease detection network is 73.3%, the recall rate is 62.3% and the mAP is 69.3%, which is 2.6, 3.0 and 2.8 percentage points higher than that of the YOLOv8 network, and the detection effect of the model is improved.

关键词: 路面病害检测, 特征提取, 重参数化, 多尺度特征, YOLOv8

Abstract: Road disease detection is an important way to ensure people’s traffic safety. In order to improve the accuracy of road disease detection and achieve timely and accurate road disease detection, a pavement disease detection model of re-parameterized YOLOv8 is proposed. First of all, CNX2f module is introduced into the backbone network to improve the ability of the network to extract pavement disease features, and effectively solve the problem that the pavement disease features are easily confused with the background environmental features. Secondly, RepConv and DBB reparameterization modules are introduced to enhance the capability of multi-scale feature fusion and solve the problem of large scale difference of pavement diseases. At the same time, the shared parameter structure of the head is improved, and RBB reparameterization module is introduced to solve the problem of head parameter redundancy and improve the feature extraction capability. Finally, the SPPF_Avg module is introduced to solve the problem of pavement feature loss and enrich the multi-scale feature expression. The experimental results show that the accuracy of the improved road disease detection network is 73.3%, the recall rate is 62.3% and the mAP is 69.3%, which is 2.6, 3.0 and 2.8 percentage points higher than that of the YOLOv8 network, and the detection effect of the model is improved.

Key words: pavement disease detection, feature extraction, reparameterize, multiscale feature, YOLOv8

王海群, 王炳楠, 葛超. 重参数化YOLOv8路面病害检测算法[J]. 计算机工程与应用, 2024, 60(5): 191-199.

WANG Haiqun, WANG Bingnan, GE Chao. Re-Parameterized YOLOv8 Pavement Disease Detection Algorithm[J]. Computer Engineering and Applications, 2024, 60(5): 191-199.

参考文献

[1] 熊学堂, 谭忆秋, 唐嘉明, 等. 基于探地雷达的沥青路面内部病害快速识别[J]. 华中科技大学学报 (自然科学版), 2023, 51(11): 120-127.
XIONG X T, TANG Y Q, TANG J M, et al. Rapid recognition of asphalt pavement internal diseases based on ground penetrating radar[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2023, 51(11): 120-127.
[2] 陈卫. 基于超声波技术的公路桥梁结构病害检测方法[J]. 自动化应用, 2023, 64(7): 176-178.
CHEN W. Detection method of highway bridge structure disease based on ultrasonic technology[J]. Automation Application, 2023, 64(7): 176-178.
[3] JING P, YU H, HUA Z, et al. Road crack detection using deep neural network based on attention mechanism and residual structure[J]. IEEE Access, 2023, 11: 919-929.
[4] ANASTASIIA K, XIA K W, ARTEM K, et al. Road surface crack detection method based on conditional generative adversarial networks[J]. Sensors, 2021, 21: 7405.
[5] DENG L, ZHANG A, GUO J, et al. An integrated method for road crack segmentation and surface feature quantification under complex backgrounds[J]. Remote Sensing, 2023, 15(6): 1530.
[6] CHUN C, RYU S K. Road surface damage detection using fully convolutional neural networks and semi-supervised learning[J]. Sensors, 2019, 19(24): 5501.
[7] 安学刚, 党建武, 王阳萍, 等. 基于YOLOv4的无人机影像路面病害检测方法[J]. 无线电工程, 2023, 53(6): 1285-1294.
AN X G, DANG J W, WANG Y P, et al. Road surface disease detection method based on YOLOv4 UAV image[J]. Radio Engineering, 2023, 53(6): 1285-1294.
[8] 杜娟, 崔少华, 晋美娟, 等. 改进YOLOv7的复杂道路场景目标检测算法[J]. 计算机工程与应用, 2024, 60(1): 96-103.
DU J, CUI S H, JIN M J, et al. Improved the complex road scene object detection algorithm of YOLOv7[J]. Computer Engineering and Applications, 2024, 60(1): 96-103.
[9] 李松, 史涛, 井方科. 改进YOLOv8的道路损伤检测算法[J]. 计算机工程与应用, 2023, 59(23): 165-174.
LI S, SHI T, JING F K. Road surface disease detection method based on YOLOv4 UAV image[J]. Computer Engineering and Applications, 2023, 59(23): 165-174.
[10] 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, 2017.
[11] LIU Z, MAO H, WU C Y, et al. A convnet for the 2020s[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 11976-11986.
[12] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition, 2015.
[13] DING X, ZHANG X, MA N, et al. RepVGG: making VGG-style convnets great again[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13733-13742.
[14] DING X, ZHANG X, HAN J, et al. Diverse branch block: building a convolution as an inception-like unit[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 10886-10895.
[15] 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.
[16] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the European Conference on Computer Vision, 2016: 21-37.
[17] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767,2018.
[18] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934,2020.
[19] GE Z, LIU S, WANG F, et al. Yolox: exceeding yolo series in 2021[J]. arXiv:2107.08430,2021.
[20] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: tranable bag-of-freebies sets new state-of-the-art for real-time object de-tectors[J]. arXiv:2207.02696,2022.
[21] LYU C, ZHANG W, HUANG H, et al. Rtmdet: an empirical study of designing real-time object detectors[J]. arXiv:2212.07784,2022.
[22] XU S, WANG X, LYU W, et al. PP-YOLOE: an evolved version of YOLO[J]. arXiv:2203.16250,2022.