Vehicle Paint Defect Detection Based on Improved YOLOv8

doi:10.19678/j.issn.1000-3428.0070032

Abstract

Abstract:

To address the issues of low accuracy in vehicle paint defect detection, excessive parameters in detection algorithms, and the uneven distribution of easy and hard samples, a vehicle paint detection method based on an improved YOLOv8 is proposed. To enhance scratch defect detection capabilities and reduce model size, a Deformable Attention Transformer (DAT) mechanism is introduced into the backbone network, and Ghost Convolution (GhostConv) replaces the standard Convolution (Conv) modules. Subsequently, to improve feature extraction capabilities and further reduce model size, a C2f Based on Efficient Multiscale Attention (EMA) (C2f-E) module is proposed by combining the FasterBlock module and the EMA attention mechanism. Moreover, to enhance the detection performance for small objects, a network based on the Bidirectional Feature Pyramid Network (BiFPN) is designed. Additionally, by adding a small-object detection head and a multiscale feature fusion branch, a neck pyramid structure named BiFPN with Small Object Detection Head (BiFPN-D) is proposed. Finally, to address the balance issue between difficult and easy samples and improve the detection performance for small object defects, Wise-Intersection over Union version 3 (WIoUv3) is employed as the loss function for training the network. The improved network is trained on a self-built dataset of vehicle paint defect images and subjected to comparative experiments. The results show that, the improved model achieves an increase of 5.5 percentage points in terms of mean Average Precision (mAP@0.5) and a reduction of 1.4×10⁶ in terms of parameter count, compared to YOLOv8n.

Key words: YOLOv8 algorithm, vehicle paint defect, object detection, Bidirectional Feature Pyramid Network (BiFPN), loss function

摘要：

针对车辆漆面缺陷检测精度低、检测算法参数量大、难易样本不均匀等问题, 提出一种基于改进YOLOv8的车辆漆面检测算法。首先, 为了提升划痕状缺陷检测能力并降低模型规模, 将DAT(Deformable Attention Transformer)注意力机制引入主干网络来增强长距离特征依赖关系, 同时使用幻影卷积(GhostConv)替换网络中的卷积(Conv)模块。然后, 为了提升特征提取能力并进一步降低模型规模, 结合FasterBlock模块与高效多尺度注意力(EMA)机制提出C2f-E(C2f Based on EMA)模块。接着, 为了提高小目标检测性能, 基于双向特征金字塔网络(BiFPN)进行设计, 并增加小目标检测头与多尺度特征融合支路, 提出BiFPN-D(BiFPN with Small Object Detection Head)颈部金字塔结构。最后, 为了解决难易样本的平衡问题并提高针对小目标缺陷的检测性能, 使用WIoUv3(Wise-Intersection over Union version 3)作为训练网络的损失函数。在自建的车辆漆面缺陷数据集上进行训练并开展对比实验。实验结果表明, 相较于YOLOv8n, 改进模型的均值平均精度(mAP@0.5)提高了5.5百分点、规模减小了1.4×10⁶。

关键词: YOLOv算法, 车辆漆面缺陷, 目标检测, 双向特征金字塔网络, 损失函数

HAO Yousheng, WEN Zhenhui, FENG Xiaoxi, DENG Zehua, HUANG Qingbao. Vehicle Paint Defect Detection Based on Improved YOLOv8[J]. Computer Engineering, 2026, 52(4): 252-263.

郝友胜, 文贞慧, 冯小溪, 邓泽华, 黄清宝. 基于改进YOLOv8的车辆漆面缺陷检测[J]. 计算机工程, 2026, 52(4): 252-263.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070032

https://www.ecice06.com/EN/Y2026/V52/I4/252

Figures/Tables 18

Fig.1 Structure of improved YOLOv8 network

Fig.2 Structure of improved C2f module

Fig.3 Structure of EMA module

Fig.4 Structure of FasterBlock module

Fig.5 Structure of GhostConv module

Fig.6 Structure of DAT module

Fig.7 Structure of feature fusion module

Fig.8 Data enhancement schematic diagram

Fig.9 Examples of dataset annotations

Fig.10 Number of tags and distribution of defect sizes

Fig.11 Sample distribution of VOC-2012 dataset

Fig.12 Comparison of model detection effect

References 29

1	PERERA R , GUZZETTI D , AGRAWAL V . Optimized and autonomous machine learning framework for characterizing pores, particles, grains and grain boundaries in microstructural images. Computational Materials Science, 2021, 196, 110524. doi: 10.1016/j.commatsci.2021.110524
2	陆玉凯, 袁帅科, 熊树生, 等. 汽车漆面缺陷高精度检测系统. 吉林大学学报(工学版), 2024, 54 (5): 1205- 1213.
	LU Y K , YUAN S K , XIONG S S , et al. High precision detection system for automotive paint defects. Journal of Jilin University (Engineering and Technology Edition), 2024, 54 (5): 1205- 1213.
3	WU C X , CHEN B J , YE C S . Detecting defects on corrugated plate surfaces using a differential laser triangulation method. Optics and Lasers in Engineering, 2020, 129, 106064. doi: 10.1016/j.optlaseng.2020.106064
4	FENG X L , GAO X W , LUO L . A surface defect identification method based on improved threshold segmentation algorithm. Journal of Physics: Conference Series, 2020, 1651 (1): 012072. doi: 10.1088/1742-6596/1651/1/012072
5	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2014: 580-587.
6	HE K , ZHANG X , REN S , 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
7	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
8	圣文顺, 余熊峰, 林佳燕, 等. 融合注意力与特征金字塔的小尺度目标检测算法. 计算机工程, 2024, 50 (1): 242- 250. doi: 10.19678/j.issn.1000-3428.0066724
	SHENG W S , YU X F , LIN J Y , et al. Small-scale object detection algorithm integrating attention and feature Pyramids. Computer Engineering, 2024, 50 (1): 242- 250. doi: 10.19678/j.issn.1000-3428.0066724
9	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2016: 779-788.
10	BERG A C, FU C Y, SZEGEDY C, et al. SSD: single shot multibox detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.
11	彭菊红, 张弛, 高谦, 等. 基于改进的YOLOv8算法的钢材缺陷检测. 计算机工程, 2025, 51 (7): 152- 160. doi: 10.19678/j.issn.1000-3428.0069283
	PENG J H , ZHANG C , GAO Q , et al. Steel defect detection based on improved YOLOv8 algorithm. Computer Engineering, 2025, 51 (7): 152- 160. doi: 10.19678/j.issn.1000-3428.0069283
12	阳丽莎, 李茂军, 胡建文, 等. 基于改进YOLOv7-tiny的带钢表面缺陷检测算法. 计算机工程, 2025, 51 (1): 208- 215. doi: 10.19678/j.issn.1000-3428.0068397
	YANG L S , LI M J , HU J W , et al. Strip steel surface defect detection algorithm based on improved YOLOv7-tiny. Computer Engineering, 2025, 51 (1): 208- 215. doi: 10.19678/j.issn.1000-3428.0068397
13	周思瑜, 徐慧英, 朱信忠, 等. 基于改进YOLOv8n的手机屏幕瑕疵检测算法: PGS-YOLO. 计算机工程, 2025, 51 (5): 326- 339. doi: 10.19678/j.issn.1000-3428.0069259
	ZHOU S Y , XU H Y , ZHU X Z , et al. Mobile phone screen defect detection algorithm based on improved YOLOv8n: PGS-YOLO. Computer Engineering, 2025, 51 (5): 326- 339. doi: 10.19678/j.issn.1000-3428.0069259
14	TERVEN J , CÓRDOVA-ESPARZA D M , ROMERO-GONZÁLEZ J A . A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 2023, 5 (4): 1680- 1716. doi: 10.3390/make5040083
15	OUYANG D L, HE S, ZHANG G Z, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2023: 1-5.
16	CHEN J R, KAO S H, HE H, et al. Run, don't walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2023: 12021-12031.
17	MA X L, GUO F M, NIU W, et al. PConv: the missing but desirable sparsity in DNN weight pruning for real-time execution on mobile devices[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2020: 5117-5124.
18	CAO J S , BAO W S , SHANG H X , et al. GCL-YOLO: a GhostConv-based lightweight YOLO network for UAV small object detection. Remote Sensing, 2023, 15 (20): 4932. doi: 10.3390/rs15204932
19	GUO Y H, LI Y D, WANG L Q, et al. Depthwise convolution is all you need for learning multiple visual domains[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019: 8368-8375.
20	XIA Z F, PAN X R, SONG S J, et al. Vision Transformer with deformable attention[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2022: 4784-4793.
21	LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: hierarchical vision Transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2021: 9992-10002.
22	ZHU X, SU W, LU L, et al. Deformable DETR: Deformable Transformers for end-to-end object detection[EB/OL]. [2024-05-08]. https://arxiv.org/abs/2010.04159.
23	TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 10781-10790.
24	ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2020: 12993-13000.
25	TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB/OL]. [2024-05-08]. https://arxiv.org/pdf/2301.10051.pdf
26	ZHANG X, SONG Y, SONG T, et al. AKConv: convolutional kernel with arbitrary sampled shapes and arbitrary number of parameters[EB/OL]. [2024-05-08]. https://arxiv.org/abs/2311.11587v1.
27	HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 7132-7141.
28	HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2021: 13708-13717.
29	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the 2018 European Conference on Computer Vision. Berlin, Germany: Springer International Publishing, 2018: 3-19.

[1]	LI Yiyang, LU Shenglian, WANG Jijie, CHEN Ming. Review of DETR Object Detection Algorithm Based on Transformer [J]. Computer Engineering, 2026, 52(4): 62-81.
[2]	LI Luyang, YAN Jinlong, FANG Zeru, JIN Qiqi, XUE Hongxin. 3D Small Object Detection Algorithm Based on Dynamic Feature Enhancement [J]. Computer Engineering, 2026, 52(4): 264-275.
[3]	XIE Binhong, SHI Yufei, ZHANG Rui, ZHANG Yingjun. Few-shot Object Detection Method Based on Query Guidance and Semantic Enhancement [J]. Computer Engineering, 2026, 52(3): 141-151.
[4]	CAO Jiwei, LUO Fei, DING Weichao. BS-YOLO: A Small Object Detection Algorithm Based on BSAM Attention Mechanism and SCConv [J]. Computer Engineering, 2026, 52(3): 119-127.
[5]	TANG Ke, WEI Feiming, LI Dongying, YU Wenxian. Lightweight Target Detection Algorithm for UAV Images Based on Improved YOLOv8 [J]. Computer Engineering, 2026, 52(3): 97-106.
[6]	LI Jianlang, WU Xindian, CHEN Ling, YANG Bo, TANG Wensheng. 3D Object Detection Algorithm Based on 4D Millimeter-Wave Radar and Vision Fusion [J]. Computer Engineering, 2026, 52(2): 299-310.
[7]	LI Shugang, LI Shuang, LIU Chi. Cross-Domain Fabric Defect Detection Guided by Texture Knowledge [J]. Computer Engineering, 2026, 52(1): 166-175.
[8]	ZHU Siyuan, LI Jiasheng, ZOU Danping, HE Di, YU Wenxian. Unstructured Road Defect Detection Algorithm Based on Semi-Supervised Learning [J]. Computer Engineering, 2025, 51(9): 14-24.
[9]	WANG Shumeng, XU Huiying, ZHU Xinzhong, HUANG Xiao, SONG Jie, LI Yi. Lightweight Small Object Detection Algorithm for Aerial Photography Based on Improved YOLOv8n: PECS-YOLO [J]. Computer Engineering, 2025, 51(9): 280-293.
[10]	MA Yue, HUANG Zhourui, ZHOU Wen, XU Yihan. Lightweight Forest Fire Detection Algorithm Based on Receptive Field Attention [J]. Computer Engineering, 2025, 51(9): 350-361.
[11]	MA Gan, GU Yu, PENG Dongliang. Combining Improved YOLOv5s and Dynamic Data Augmentation for Sea Surface Ship Detection [J]. Computer Engineering, 2025, 51(9): 294-305.
[12]	MIAO Ru, LI Yi, ZHOU Ke, ZHANG Yanna, CHANG Ranran, MENG Geng. A Study on Improved Faster R-CNN Model for Multi-Object Detection in Remote Sensing Images [J]. Computer Engineering, 2025, 51(8): 292-304.
[13]	SONG Jie, XU Huiying, ZHU Xinzhong, HUANG Xiao, CHEN Chen, WANG Zeyu. Improved Fall Detection Algorithm Based on YOLOv8: OEF-YOLO [J]. Computer Engineering, 2025, 51(7): 127-139.
[14]	ZHANG Jiacheng, WEI Jin, CHEN Yishi. Improved YOLOv8 Real-time Lightweight Robust Hedge Detection Algorithm [J]. Computer Engineering, 2025, 51(7): 362-374.
[15]	LUAN Mengna, ZHENG Qiumei, WANG Fenghua. Real-time Traffic Sign Detection Algorithm Based on DMC-YOLO [J]. Computer Engineering, 2025, 51(7): 90-99.

Please choose a citation manager

Content to export