Research on Expressway Pavement Crack Detection based on Improved YOLOv5s

Chunlin He; Jiaye Wu; Yujie Yang

doi:10.54097/fcis.v5i3.14020

Authors

Chunlin He
Jiaye Wu
Yujie Yang

DOI:

https://doi.org/10.54097/fcis.v5i3.14020

Keywords:

Road Crack Detection, YOLOv5s Algorithm, CBAM Attention Mechanism, Feature Fusion

Abstract

In order to address the issues of missed detection, false detection, and low accuracy of current road cracks, we propose a road crack recognition model based on improved YOLOv5. Firstly, add a CBAM attention module to the backbone network to enhance feature extraction capabilities; Then, a weighted bidirectional feature pyramid (BiFPN) is incorporated into the model for multi-scale feature fusion, replacing the traditional feature pyramid (FPN)+pixel aggregation network (PAN) structure to enhance feature fusion. The experimental results indicate that the improved model outperforms the traditional YOLOV5 model in terms of mAP@0.5 By 17.3%, the improved YOLOv5 algorithm performs well in detecting road cracks and can quickly and accurately identify and locate cracks on the road.

Downloads

Download data is not yet available.

References

CHEN F B. Analysis of the causes and hazards of cracks in concrete road pavement in my country[J]. Sichuan Cement, 2014(10): 18.

OLIVEIRA H,CORREIA P L. Automatic road crack segmentation using entropy and image dynamic thresholding[C]// 2009 17th European Signal Processing Conference, 2009: 622-626.

WANG X. Identification method of road cracks in complex environment based on wavelet transform directional component reconstruction [j]. Shanxi Science & Technology of Communications , 2021(4):52-55.

LI Y D,HAO Z B,LEI H . Review of convolutional neural network re-search[J]. Journal of Computer Applications, 2016,36 (9) : 2508-2515 ,2565.

YOU J C. Pavement crack detection based on improved Mask-RCNN[J]Video Engineering,2022,46( 6) : 7-9,19.

XU K, MA R G. Crack detection of asphalt pavement based on improved faster RCNN[J]. Computer Systems & Applications, 2022, 31 (7)341-348.

GU S H,LI X X,WANG X Y, et al. Crack detection with enhanced se-mantic information and multi-channel feature fusion [J]. Computer Engi.neering and Application, 2021,57 (10): 204-210.

YANG F, ZHANG L,YU S, et al. Feature Pyramidand Hierarchical Boosting Network for Pavement Crack DetectionJ. EEE Transactions on Intelligent Transportation Syst, 2020, (4):1525-1535.

ZHANG J, QIAN S R,TAN C. Automated Bridge Crack Detection Method Based on Lightweight Vision Models [J].Complex and Intelligent Systems, 2023,9:1639-1652.

Wang C. -Y, Mark Liao H. -Y, Wu Y. -H et al. "CSPNet: A New Backbone that can Enhance Learning Capability of CNN," 2020 1EEE/CVF Conference on Computer Visionand Pattern Recognition Workshops (CVPRW), 2020, pp. 1571-1580.

He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Spatial Pyramid Pooling in DeepConvolutional Networks for Visual Recognition. (J. IEEE transactions on pattern analysis and machine intelligence,2015,37(9).

Lin T. -Y.. Piotr D. Ross B. G., et al. Feature Pyramid Networks for Object Detection.[J]. CoRR. 2016. abs/1612.03144.

Gao Huang. Zhuang Liu, Kilian et al. Densely Connected Convolutional Networks.jJCoRR,2016abs/1608.06993.

Qiu Tianhao, Chen Shurong. Dual branch multi-scale joint learning pedestrian recognition based on EfficientNet [J]. Computer Applications, 2022,42 (7): 2065-2071.