CoChat
Sign Up
Cited by 79Advanced Neural Network ApplicationsIndustrial Vision Systems and Defect DetectionImage Enhancement Techniques

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Research on Improved YOLOv5 for Low-Light Environment Object Detection

Open access
Wang, Jing, Yang, Peng, Liu, Yuansheng, Shang, Duo, Hui, Xin, Song, Jinhong, Chen, Xuehui·2023·Electronics
DOI 10.3390/electronics12143089
Open this paper in CoChat — free accountOpen PDF

Abstract

Object detection in low-light scenarios has been widely acknowledged as a significant research area in the field of computer vision, presenting a challenging task. Aiming at the low detection accuracy of mainstream single-stage object detection models in low-light scenarios, this paper proposes a detection model called DK_YOLOv5 based on YOLOv5, specifically designed for such scenarios. First, a low-light image enhancement algorithm with better results is selected to generate enhanced images that achieve relatively better visual effects and amplify target features. Second, the SPPF layer is improved to an R-SPPF module with faster inference speed and stronger feature expression ability. Next, we replace the C3 module with the C2f module and incorporate an attention mechanism to develop the C2f_SKA module, enabling richer gradient information flow and reducing the impact of noise features. Finally, the model detection head is replaced with a decoupled head suitable for the object detection task in this scenario to improve model performance. Additionally, we expand the Exdark dataset to include low-light data of underground mine scenario targets, named Mine_Exdark. Experimental results demonstrate that the proposed DK_YOLOv5 model achieves higher detection accuracy than other models in low-light scenarios, with an mAP0.5 of 71.9% on the Mine_Exdark dataset, which is 4.4% higher than that of YOLOv5.

Overview

Integrity signals

Registry

Crossref · 10.3390/electronics12143089

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

  • YOLO's performance tends to degrade significantly in domains with irregular or noisy data, such as low-light environments, underwater imaging, or thermal imagery.

    “Domain adaptability is another pressing challenge for YOLO. The model's performance tends to degrade significantly in domains with irregular or noisy data, such as low-light environments, underwater imaging, or thermal imagery [145].”

    From The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection (2024) · cites this paper as [145]

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 37

  1. Bao, 2022, Survey of Object Detection Algorithms Based on Deep Learning, Trans. Microsyst., 41, 5
  2. Mao, 2022, Review of YOLO Based Target Detection for Autonomous Driving, Comput. Eng. Appl., 58, 68
  3. Xia, 2018, Application of Deep Learning Techniques in Medical Imaging Research, Med. J. Peking Union Med. Coll. Hosp., 9, 10
  4. Hu, 2022, Research and application of face recognition algorithm based on lightweight CNN, Trans. Microsyst., 41, 153
  5. Jiang, 2023, Survey of Deep Learning Algorithms for Agricultural Pest Detection, Comput. Eng. Appl., 59, 30
  6. Zhu, 2022, Design of aluminum surface defect detection system based on deep learning, Trans. Microsyst., 41, 96
  7. Terven, J., and Cordova-Esparza, D. (2023). A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond. arXiv.
  8. Liu, W., Anguelov, D., and Erhan, D. (2016, January 11–14). SSD: Single Shot Multibox Detector. Proceedings of the 14th European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands. · DOI · Paper page
  9. Girshick, R., Donahue, J., and Darrell, T. (2014, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA. · DOI · Paper page
  10. Girshick, R. (2015, January 7–13). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile. · DOI · Paper page
  11. Ren, S., He, K., and Girshick, R. (2015, January 7–12). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
  12. Lu, 2019, Equipment Recognition of Mining Patrol Robot Based on Deep Learning Algorithm, Chin. J. Eng. Des., 26, 527
  13. Du, 2020, Research on Video-Assisted Driving System of Mine Trackless Rubber tire Vehicle, Coal Eng., 52, 178
  14. Xiao, 2020, Making of Night Vision: Object Detection under Low-Illumination, IEEE Access, 8, 123075, 10.1109/ACCESS.2020.3007610 · DOI
  15. Liu, S., and Huang, D. (2018, January 8–14). Receptive Field Block Net for Accurate and Fast Object Detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany. · DOI · Paper page
  16. Li, 2019, Improved Faster R-CNN for Pedestrian Detection in Underground Coal Mine, Comput. Eng. Appl., 55, 200
  17. Wei, C., Wang, W., and Yang, W. (2018). Deep Retinex Decomposition for Low-Light Enhancement. arXiv.
  18. Jiang, 2021, Enlightengan: Deep Light Enhancement without Paired Supervision, IEEE Trans. Image Process., 30, 2340, 10.1109/TIP.2021.3051462 · DOI
  19. Tekli, 2022, Comparing deep learning models for low-light natural scene image enhancement and their impact on object detection and classification: Overview, empirical evaluation, and challenges, Signal Process. Image Commun., 109, 116848, 10.1016/j.image.2022.116848 · DOI
  20. Li, 2021, Low Light Image Fusion and Detection Method Based on Lego Filter and SSD, Comput. Sci., 48, 213
  21. Zhang, 2022, Underground Pedestrian Detection Model Based on Dense-YOLO Network, J. Mine Autom., 48, 86
  22. Xu, 2021, Exploring image enhancement for salient object detection in low light images, ACM Trans. Multimed. Comput. Commun. Appl., 17, 1, 10.1145/3458281 · DOI
  23. Qiu, Y., Lu, Y., and Wang, Y. (2023). IDOD-YOLOV7: Image-Dehazing YOLOV7 for Object Detection in Low-Light Foggy Traffic Environments. Sensors, 23. · DOI
  24. Cui, Z., Qi, G.J., and Gu, L. (2021, January 10–17). Multitask aet with orthogonal tangent regularity for dark object detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada. · DOI
  25. Loh, 2019, Getting to Know Low-Light Images with the Exclusively Dark Dataset, Comput. Vis. Image Underst., 178, 30, 10.1016/j.cviu.2018.10.010 · DOI
  26. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2022). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. arXiv.
  27. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
  28. Lv, F., Lu, F., and Wu, J. (2018, January 3–6). MBLLEN: Low-Light Image/Video Enhancement Using CNNs. Proceedings of the BMVC 2018, Newcastle, UK.
  29. Zhang, Y., Zhang, J., and Guo, X. (2019, January 21–25). Kindling the darkness: A practical low-light image enhancer. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France. · DOI
  30. Guo, C., Li, C., and Guo, J. (2020, January 13–19). Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA. · DOI
  31. Li, 2021, Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation, IEEE Trans. Pattern Anal. Mach. Intell., 44, 4225
  32. Wu, W., Weng, J., and Zhang, P. (2022, January 19–24). Uretinex-net: Retinex-based deep unfolding network for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. · DOI
  33. Ma, L., Ma, T., and Liu, R. (2022, January 19–24). Toward fast, flexible, and robust low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. · DOI
  34. Zheng, S., and Gupta, G. (2022, January 3–8). Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA. · DOI
  35. Li, X., Wang, W., and Hu, X. (2019, January 15–20). Selective Kernel Networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. · DOI
  36. He, 2015, Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, IEEE Trans. Pattern Anal. Mach. Intell., 37, 1904, 10.1109/TPAMI.2015.2389824 · DOI · Paper page
  37. Ge, Z., Liu, S., and Wang, F. (2021). YOLOX: Exceeding YOLO Series in 2021. arXiv.

Cited by

Sorted by citations

Metadata

Authors
Wang, J., Yang, P., Liu, Y., Shang, D., Hui, X., Song, J., & Chen, X.
Affiliations
  • Beijing Union University (CN)
  • China Academy of Industrial Internet, Beijing 100102, China
  • Jiaojia Gold Mine of Shandong Gold Mining Co., Ltd., Laizhou 261441, China
Corresponding author
Yang, Peng
ORCID
Venue
Electronics
Publisher
MDPI AG
Published
2023-07-16
Volume
12
Issue
14
Pages
3089
ISSN
2079-9292 (ISSN-L)
DOI
10.3390/electronics12143089
OpenAlex
W4384525598
Cited by
79
References
1
Citations by year
2026: 19 · 2025: 31 · 2024: 26 · 2023: 3
FWCI
7.17
Type
journal article
Language
en
Open access
Licence
Locations
Electronics (publishedVersion, cc-by)
Funders
National Key R&D Program of China (2021YFC3001300)
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 › Computer Vision and Pattern Recognition › Image Enhancement Techniques
Keywords
low-light object detection, YOLOv5, low-light image enhancement, attention mechanism, decoupled head, underground mining safety, ExDark dataset, one-stage object 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