CoChat
Sign Up
Cited by 25Advanced Neural Network ApplicationsIndustrial Vision Systems and Defect DetectionDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

YOLO_Bolt: a lightweight network model for bolt detection

Open access
Liu, Zhenyu, Lv, Haoyuan·2024·Scientific Reports
DOI 10.1038/s41598-023-50527-0PMC PMC10770306
Open this paper in CoChat — free accountOpen PDF

Abstract

Accurate, fast, and intelligent workpiece identification is of great significance to industrial production. To cope with the limited hardware resources of factory equipment, we have made lightweight improvements based on You Only Look Once v5 (YOLOv5) and proposed a lightweight YOLO named YOLO_Bolt. First, ghost bottleneck lightweight deep convolution is added to the backbone module and neck module of the YOLOv5 detection algorithm to reduce the model volume. Second, the asymptotic feature pyramid network is added to enhance the feature utilization ability, suppress interference information, and improve detection accuracy. Finally, the relationship between the loss function and the decoupling head structure was focused on, and the number of decoupling head layers was redesigned according to different tasks to further improve the detection accuracy of the workpiece detection model. We conducted experimental verification on the MSCOCO 2017 dataset and the homemade bolt dataset. The experimental results show that compared with YOLOv5s, the number of model parameters is only 6.8 M, which is half that of the original model. On the MSCOCO 2017 dataset, the mAP increased by 2.4%. FPS increased by 104 frames/s. On the homemade dataset, the mAP 0.5 increased by 4.2%, and our proposed method is 1.2% higher than the latest YOLOv8s. The improved network can provide effective auxiliary technical support for workpiece detection.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-023-50527-0

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The structure of the proposed network.
Figure 1 The structure of the proposed network.CC BY · PubMed Central
Figure 2 Ghost bottleneck.
Figure 2 Ghost bottleneck.CC BY · PubMed Central
Figure 3 Illustration of the adaptive spatial feature fusion mechanism.
Figure 3 Illustration of the adaptive spatial feature fusion mechanism.CC BY · PubMed Central
Figure 4 Comparison between Light Asymmetric Multilevel Channel Compression Decoupled Head and YOLOX's Decoupled Head.
Figure 4 Comparison between Light Asymmetric Multilevel Channel Compression Decoupled Head and YOLOX's Decoupled Head.CC BY · PubMed Central
Figure 5 Examples of partial self-built dataset images. (a) From left to right are bolt_1-bolt_7; (b) detection sample example.
Figure 5 Examples of partial self-built dataset images. (a) From left to right are bolt_1-bolt_7; (b) detection sample example.CC BY · PubMed Central
Figure 6 Comparison with other object detectors. (a) mAP 0.5 curve, (b) mAP 0.5:0.95 curve, (c) Precision curve, (d) Recall curve.
Figure 6 Comparison with other object detectors. (a) mAP 0.5 curve, (b) mAP 0.5:0.95 curve, (c) Precision curve, (d) Recall curve.CC BY · PubMed Central
Figure 7 Comparison of detection of different models in example 2. (a) The original image; (b) SSD; (c) Faster R-CNN; (d) YOLOv5s; (e) YOLOv8s; (f) YOLO_Bolt.
Figure 7 Comparison of detection of different models in example 2. (a) The original image; (b) SSD; (c) Faster R-CNN; (d) YOLOv5s; (e) YOLOv8s; (f) YOLO_Bolt.CC BY · PubMed Central
Figure 8 Comparison of detection of different models in example 3. (a) The original image; (b) SSD; (c) Faster R-CNN; (d) YOLOv5s; (e) YOLOv8s; (f) YOLO_Bolt.
Figure 8 Comparison of detection of different models in example 3. (a) The original image; (b) SSD; (c) Faster R-CNN; (d) YOLOv5s; (e) YOLOv8s; (f) YOLO_Bolt.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 2 references

Research works printed but not linked: 14

  1. Jarvis, J. F. Research directions in industrial machine vision: A workshop summary. Computer 15, 55–61 (1982). · DOI
  2. Guo, C., Fan, B., Zhang, Q., Xiang, S. & Pan, C. Augfpn: Improving multiscale feature learning for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (ed. Guo, C.) 12595–12604 (IEEE, 2020).
  3. Wong, F. & Hu, H. Adaptive learning feature pyramid for object detection. IET Comput. Vis. 13, 742–748 (2019). · DOI
  4. Li, J., Gu, J., Huang, Z. & Wen, J. Application research of improved YOLO V3 algorithm in PCB electronic component detection. Appl. Sci. 9, 3750 (2019). · DOI
  5. Ju, M. et al. Improved YOLO V3 algorithm and its application in small target detection. Acta Opt. Sin. 39, 0715004 (2019). · DOI
  6. Liu, G., Nouaze, J. C., Mbouembe, P. L. T. & Kim, J. H. YOLO-tomato: A robust algorithm for tomato detection based on YOLOv3. Sensors 20, 2145 (2020). · DOI
  7. He, W., Huang, Z., Wei, Z., Li, C. & Guo, B. TF-YOLO: an improved incremental network for real-time object detection. Appl. Sci. 9, 3225 (2019). · DOI
  8. Xing, Z. et al. Coal resources under carbon peak: Segmentation of massive laser point clouds for coal mining in underground dusty environments using integrated graph deep learning model. Energy 285, 128771 (2023). · DOI
  9. Wu, Y. et al. Detection of Foreign Objects Intrusion Into Transmission Lines Using Diverse Generation Model. IEEE Trans. Power Deliv. https://doi.org/10.1109/TPWRD.2023.3279891 (2023). · DOI
  10. Han, K. et al. GhostNets on heterogeneous devices via cheap operations. Int. J. Comput. Vis. 130, 1050–1069 (2022). · DOI
  11. Yang, Guoyu, et al. AFPN: Asymptotic Feature Pyramid Network for Object Detection. Preprint at https://arXiv.org/quant-ph/2306.15988 (2023). · DOI
  12. Huang L, Li W, Shen L, et al. YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification. Preprint at https://arXiv.org/quant-ph/2305.04170 (2023).
  13. Yang, G. et al. AFPN: asymptotic feature pyramid network for object detection. Preprint at https://arXiv.org/quant-ph/2306.15988 (2023). · DOI
  14. Liu, S., Huang, D. & Wang, Y. Learning spatial fusion for single-shot object detection. Preprint at https://arXiv.org/quant-ph/1911.09516 (2019).

Cited by

Metadata

Authors
Liu, Z., & Lv, H.
Affiliations
Shenyang University of Technology (CN)
Corresponding author
Lv, Haoyuan
ORCID
Liu, Zhenyu
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2024-01-05
Volume
14
Issue
1
Pages
656-656
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-023-50527-0
PMC
PMC10770306
OpenAlex
W4390618392
Cited by
25
References
2
Citations by year
2026: 10 · 2025: 8 · 2024: 7
FWCI
3.50
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
lightweight object detection, YOLOv5, Ghost Bottleneck, feature pyramid network, decoupled head, industrial vision, model compression, real-time detection

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review