Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

A defect detection network for painted wall surfaces based on YOLOv5 enhanced by attention mechanism and bi-directional FPN

  • Application of soft computing
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Automatic detection of defects on painted wall surfaces (DPWSs) based on machine vision is meaningful for reducing manpower consumption and shorting lead time, which is one of the critical components of intelligent construction. Conventional detection methods suffer from some challenges due to the multi-scale defects and unstructured detection environment. In this study, a detection network for DPWSs is developed based on the enhanced You Only Look Once version 5 (YOLOv5). First, the convolutional block attention module (CBAM) is inserted into the backbone of YOLOv5 to boost the feature extraction and suppress noise, which can sufficiently extract the features of the defects with blurry edges. Then, to improve the adaptability for multi-scale defects and reduce the model size, the Bi-directional Feature Pyramid Network (BiFPN) is employed in the neck of YOLOv5 to enhance the feature fusion, where the multi-scale objects can be fully captured. Finally, the decoupled head is proposed to replace the original convolution layer in the You Only Look Once (YOLO) head, which separates the classification and localization tasks to improve detection speed and robustness. Since there is no publicly available data set, a data set of DPWSs is constructed, and a series of comparative experiments are conducted. The results show that the detection accuracy is improved by 15.6% and the model size is reduced by 30.8% compared with YOLOv5. Meanwhile, the proposed network has better adaptability to DPWSs with higher detection accuracy and smaller model sizes compared with other advanced methods. As to the general applicability aspect of the model, the proposed model holds significant academic and practical implications in the realms of intelligent construction. Besides the model’s primary application domain of construction quality control, it can also be applied to defect detection in other scenarios that have multi-scale defects and unstructured environments. This versatility benefits a wide spectrum of construction projects.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

Data that support the findings of this study are openly available in [Ai Studio] at https://aistudio.baidu.com/aistudio/datasetdetail/221411.

Notes

  1. The data set can be downloaded from https://aistudio.baidu.com/aistudio/datasetdetail/221411.

References

  • Ahmad I et al (2022) Deep learning based detector YOLOv5 for identifying insect pests. Appl Sci Basel 12(19):10167 (in English)

    Article  Google Scholar 

  • BaiTY, Ieee (2022) Analysis on two-stage object detection based on convolutional neural networkorks. In: Presented at the 2020 international conference on big data and artificial intelligence and software engineering (ICBASE 2020)

  • Bharati P, Pramanik AJCIIPRPOC (2020) Deep learning techniques—R-CNN to mask R-CNN: a survey, pp. 657–668

  • CaiZW, Vasconcelos N, Ieee (2018) Cascade R-CNN: delving into high quality object detection. presented at the 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR)

  • ChoiDC, Jeon YJ, Yun JP, Kim SW (2012) Blowhole detection algorithm using texture analysis. In: Presented at the fourth international conference on machine vision (ICMV 2011): computer vision and image analysis: pattern recognition and basic technologies

  • DaiJF, Li Y, He KM, Sun J (2016) R-FCN: object detection via region-based fully convolutional networks. In: Presented at the advances in neural information processing systems 29 (NIPS 2016)

  • Dhivya M, Devi MR (2019) Detection of structural defects in fabric parts using a novel edge detection method. Comput J 62(7):1036–1043 (in English)

    Article  Google Scholar 

  • Ding RW, Dai LH, Li GP, Liu H (2019) TDD-net: a tiny defect detection network for printed circuit boards. Caai Trans Intell Technol 4(2):110–116 (in English)

    Article  Google Scholar 

  • EsserP, Sutter E, Ommer B (2018) A variational u-net for conditional appearance and shape generation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8857–8866

  • HeKM, Gkioxari G, Dollar P, Girshick R, Ieee (2017) Mask R-CNN. In: Presented at the 2017 IEEE international conference on computer vision (ICCV)

  • HuJ, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition pp. 7132–7141

  • HuDH, Chen DF, Yan K, Cao Y (2022) Workpiece surface defects recognition based on improved lightweight YOLOv4. In: Presented at the 2022 22nd international conference on control, automation and systems (ICCAS 2022). IEEE

  • Huang J, Ren LF, Zhou XK, Yan K (2022) An improved neural network based on SENet for sleep stage classification. Ieee J Biomed Health Inform 26(10):4948–4956 (in English)

    Article  Google Scholar 

  • Jiang B, Chen S, Wang B, Luo BJNN (2022) MGLNN: semi-supervised learning via multiple graph cooperative learning neural networks. Neural Netw 153:204–214

    Article  Google Scholar 

  • LangXL, Zhang Y, Shu SB, Liang HJ, Zhang YZ (2021) Lithium battery surface defect detection based on the YOLOv3 detection algorithm. In: Presented at the tenth international symposium on precision mechanical measurements

  • Li MJ, Wang H, Wan ZB (2022) Surface defect detection of steel strips based on improved YOLOv4. Comput Electr Eng 102:1208 (in English)

    Article  Google Scholar 

  • Lin TY, Goyal P, Girshick R, He KM, Dollar P (2020) Focal loss for dense object detection. Ieee Trans Patt Anal Mach Intell 42(2):318–327 (in English)

    Article  Google Scholar 

  • Lin CY, Chen CH, Yang CY, Akhyar F, Hsu CY, Ng HF (2020) Cascading convolutional neural network for steel surface defect detection. In: Presented at the advances in artificial intelligence, software and systems engineering

  • Liu ST, Huang D, Wang YH (2018) Receptive Field block net for accurate and fast object detection. In: Presented at the COMPUTER VISION-ECCV 2018, PT XI

  • Liu W et al (2016) Ssd: single shot multibox detector. In: Computer vision–ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, pp. 21–37: Springer

  • LiuS, Qi L, Qin HF, Shi JP, Jia JY, Ieee (2018) Path aggregation network for instance segmentation. In: Presented at the 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR)

  • LuJ, Wu PF, Xue JW, Qiu M, Peng F (2015) Detecting defects on citrus surface based on circularity threshold segmentation. In: Presented at the 2015 12th international conference on fuzzy systems and knowledge discovery (FSKD)

  • Lv N, Xiao J, Qiao YJ (2022) Object detection algorithm for surface defects based on a novel YOLOv3 model. Processes 10(4):701 (in English)

    Article  Google Scholar 

  • ParkH, Yoo Y, Seo G, Han D, Yun S, Kwak NJAPA (2018) C3: concentrated-comprehensive convolution and its application to semantic segmentation

  • RedmonJ, Divvala S, Girshick R, Farhadi A, Ieee (2016) You only look once: unified, real-time object detection. In: Presented at the 2016 IEEE conference on computer vision and pattern recognition (CVPR)

  • RenSQ, He KM, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Presented at the advances in neural information processing systems 28 (NIPS 2015)

  • Roy AM, Bhaduri JJAEI (2023) DenseSPH-YOLOv5: an automated damage detection model based on DenseNet and swin-transformer prediction head-enabled YOLOv5 with attention mechanism. Adv Eng Inform 56:102007

    Article  Google Scholar 

  • Roy AM, Bose R, Bhaduri JJNC (2022) A fast accurate fine-grain object detection model based on YOLOv4 deep neural network. Neural Comput Appl 34:1–27

    Article  Google Scholar 

  • Shi YK, Wang ZW, Du XJ, Ling GB, Jia WC, Lu YR (2022) Research on the membrane fouling diagnosis of MBR membrane module based on ECA-CNN. J Environ Chem Eng 10(3):107649 (in English)

    Article  Google Scholar 

  • TanM, Pang R, Le QV (2020) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition pp. 10781–10790

  • Teng S, Liu ZC, Li XD (2022) Improved YOLOv3-based bridge surface defect detection by combining high- and low-resolution feature images. Buildings 12(8):1225 (in English)

    Article  Google Scholar 

  • WangCY et al. (2020) CSPNet: a new backbone that can enhance learning capability of CNN. In: Presented at the 2020 IEEE/CVF conference on computer vision and pattern recognition workshops (CVPRW 2020)

  • Woo SH, Park J, Lee JY, Kweon IS (2018) CBAM: convolutional block attention module. In: Presented at the COMPUTER VISION-ECCV 2018, PT VII

  • WuXJ, Xiong HJ, Wen PZ (2016) A defect detection method based on sub-image statistical feature for texture surface. In: Presented at the eighth international conference on digital image processing (ICDIP 2016)

  • Yan X, Wu GX, Zuo YB (2023) YOLOV4-based wind turbine blade crack defect detection. In: Presented at the proceedings of income-vi and tepen 2021: performance engineering and maintenance engineering

  • Yu XK, Wang ZW, Wang YH, Zhang CL (2021) Edge detection of agricultural products based on morphologically improved canny algorithm. Math Probl Eng 2021:6664970 (in English)

    Article  Google Scholar 

Download references

Funding

The financial support for the present research was provided by the Key R&D Program of Shandong Province (Grant No. 2022CXGC010101), Natural Science Foundation of Shandong Province (Grant No. ZR2021QE128), Colleges 20 Items Project of Jinan Science and Technology Bureau (Grant No. 2019CXR037).

Author information

Authors and Affiliations

  1. School of Mechanical and Electronic Engineering, Shandong Jianzhu University, Jinan, 250101, People’s Republic of China

    Hongyang Zhang, Yingxin Ye, Hepeng Ni & Buyao Liu

  2. School of Mechanical Engineering, Shandong University, Jinan, 250061, People’s Republic of China

    Shuai Ji

  3. School of Architecture and Urban Planning, Shandong Jianzhu University, Jinan, 250101, People’s Republic of China

    Xiaoming Gao

Authors
  1. Hongyang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shuai Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yingxin Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hepeng Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaoming Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Buyao Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Shuai Ji or Yingxin Ye.

Ethics declarations

Conflict of interest

All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.

Ethical approval

This article does not contain any studies with human participants performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, H., Ji, S., Ye, Y. et al. A defect detection network for painted wall surfaces based on YOLOv5 enhanced by attention mechanism and bi-directional FPN. Soft Comput 28, 10391–10402 (2024). https://doi.org/10.1007/s00500-024-09799-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-024-09799-5

Keywords

Search

Navigation