Lightweight Road Damage Detection Method Based on Improved YOLOv8

被引：0
作者：
Xu, Tiefeng [1 ]
Huang, He [1 ,2 ]
Zhang, Hongmin [1 ]
Niu, Xiaofu [1 ]
机构：
[1] School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing
[2] China Merchants Chongqing Transportation Research and Design Institute Limited, Chongqing
来源：
Computer Engineering and Applications | 2024年 / 60卷 / 14期
关键词：
complex scene; lightweight; model pruning; road damage detection; YOLOv8n;
D O I：
10.3778/j.issn.1002-8331.2402-0243
中图分类号：
学科分类号：
摘要：
Aiming at the problems of large memory space occupation, high computational complexity, and difficult to meet the real-time target detection requirements of the road damage detection model in complex scenes, a lightweight road damage detection model DGE-YOLO-P is proposed for the complex natural scenes. Firstly, the C2f fusion deformable convolutional design C2f_DCNv3 module in the network is enhanced to enhance the modelling capability of object deformation and the input feature information is dimensionality reduced to effectively reduce the number of parameters and the computational complexity. The input feature information is dimensionality reduced to effectively reduce the number of model parameters and computational complexity. Then, the GS-Decoupled head detection module is designed to reduce the parameters of the detection head while realising the effective aggregation of global information. At the same time, the E-Slide Loss weight function is designed to assign higher weights to the difficult samples, fully learn the difficult sample data in road damage, and further improve the model detection accuracy. Finally, channel pruning is used to reduce the redundant channels of the model, which effectively compresses the model volume and improves the detection speed. The experimental results show that the mAP of the DGE-YOLO-P model is increased by 2.4 percentage points compared with the YOLOv8n model, while the number of model parameters, computational volume and model size are reduced by 58.1%, 66.7% and 55.5%, respectively. The detection speed FPS is increased from 34 frame/s to 51 frame/s. © 2024 Journal of Computer Engineering and Applications Beijing Co., Ltd.; Science Press. All rights reserved.
引用
收藏
页码：175 / 186
页数：11
相关论文
共 29 条
[1]  
DEVI M P A, LATHA T, SULOCHANA C H., Iterative thresholding based image segmentation using 2D improved Otsu algorithm, Proceedings of the Communication Technologies, pp. 145-149, (2015)
[2]  
XU H, LI Z B, JIANG Y Y, Et al., Pavement crack detection based on OpenCV and improved Canny operator, Computer Engineering and Design, 35, 12, pp. 4254-4258, (2014)
[3]  
HU W B, WANG W D, AI C B, Et al., Machine vision- based surface crack analysis for transportation infrastructure[J], Automation in Construction, 132, (2021)
[4]  
GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation, Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 582-587, (2014)
[5]  
GIRSHICK R., Fast R-CNN, Proceedings of the IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)
[6]  
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, 39, 6, pp. 1137-1149, (2017)
[7]  
HE K M, GKIOXARI G, DOLLAR P, Et al., Mask R-CNN, Proceedings of the IEEE International Conference on Computer Vision, pp. 2980-2988, (2017)
[8]  
SUN Z Y, PEI L L, LI W, Et al., Pavement grouting crack detection method based on improved Faster R-CNN, Journal of South China University of Technology (Natural Science Edition), 48, 2, pp. 84-93, (2020)
[9]  
NIU H Y, BAO T F, LI Y T, Et al., Pixel-level crack detection method of concrete dam based on improved mask R-CNN, Advances in Science and Technology of Water Resources, 43, 1, pp. 87-92, (2023)
[10]  
LIU W, ANGUELOV D, ERHAN D, Et al., SSD: single shot multi-box detector, Proceedings of the European Conference on Computer Vision, pp. 21-37, (2016)
123