Skip to main content

Advertisement

Log in

Small target deep convolution recognition algorithm based on improved YOLOv4

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Most of the mainstream object detectors are unable to handle the problem of small object detection. Therefore, we proposed a small target deep convolution recognition algorithm which was based on the improved YOLOv4 network. Firstly, in order to obtain more object feature information and improve the detection efficiency of multi-scale small objects, spatial pyramid pooling with different pooling core sizes was introduced; To improve the value of the anchor frame, an improved adaptive anchor structure was proposed; finally, for enhancing the learning ability of the neural network and reduce the calculation cost, two cross stage partial parallel structures are adopted. In order to verify the feasibility of our algorithm, this paper uses small and micro electronic components in the industrial assembly line to construct a data set. Experiments show that compared with the original YOLOv4, the average detection speed and accuracy of the improved network are increased by about 30% and 7% respectively.

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

Access this article

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Explore related subjects

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

References

  1. Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems (NIPS), pp 91–99

  2. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 779–788

  3. Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 7263– 7271

  4. Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. arXiv: 1804.02767

  5. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) SSD: single shot multibox detector. In: Proceedings of the European conference on computer vision (ECCV), pp 21–37

  6. He W, Huang Z, Wei Z, Li C, Guo B (2019) TF-YOLO: an improved incremental network for real-time object detection. Appl Sci 9(16):3225

    Article  Google Scholar 

  7. Zhuang D, Jiang M, Kong J et al (2021) Spatiotemporal attention enhanced features fusion network for action recognition. Int J Mach Learn Cybern 12:823–841. https://doi.org/10.1007/s13042-020-01204-5

    Article  Google Scholar 

  8. Miao Y, Xiangbin S (2021) A deep learning model S-Darknet suitable for small target detection. J Phys Conf Ser 1871(1):012118

    Article  Google Scholar 

  9. Wang H, Hu Z, Guo Y, Yang Z, Zhou F, Xu P (2020) A real-time safety helmet wearing detection approach based on CSYOLOv3. Appl Sci 10:6732

    Article  Google Scholar 

  10. Bochkovskiy A, Wang CY, Liao HYM (2020) YOLOv4: optimal speed and accuracy of object detection. In: IEEE conference on computer vision and pattern recognition. 2020. arXiv: 2004.10934

  11. Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 40(4):834–848

  12. He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell (TPAMI) 37(9):1904–1916

    Article  Google Scholar 

  13. Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 8759–8768

  14. Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. arXiv: 1804.02767

  15. Shang R, Zhang J, Jiao L, Li Y, Marturi N, Stolkin R (2020) Multi-scale adaptive feature fusion network for semantic segmentation in remote sensing images. Remote Sens 12(5):872

    Article  Google Scholar 

  16. Yu J, Jiang Y, Wang Z, Cao Z, Huang T (2016) UnitBox: an advanced object detection network. In: Proceedings of the 24th ACM international conference on multimedia, vol 3, pp 516–520

  17. Li S, Yang L, Huang J, Hua X-S, Zhang L (2019) Dynamic anchor feature selection for single-shot object detection. In: Proceedings of the IEEE international conference on computer vision (ICCV), vol 12, pp 6609–6618

  18. Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D. (2020) Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI conference on artificial intelligence (AAAI), vol 3

  19. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167

  20. Jebadurai J, Jebadurai IJ, Paulraj GJL, Samuel NE (2019) Super-resolution of digital images using CNN with leaky ReLU. Int J Recent Technol Eng 8(2S8)

  21. Wang C-Y, Liao H-YM, Wu Y-H, Chen P-Y, Hsieh J-W, Yeh I-H (2020) CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshop (CVPR workshop), vol 2

  22. Konka P, Lingam R, Singh UA, Shivaprasad CH, Reddy NV (2020) Enhancement of accuracy in double sided incremental forming by compensating tool path for machine tool errors. Int J Adv Manuf Technol 111(3):1187–1199

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Dongyang Gao.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, F., Gao, D., Yang, Y. et al. Small target deep convolution recognition algorithm based on improved YOLOv4. Int. J. Mach. Learn. & Cyber. 14, 387–394 (2023). https://doi.org/10.1007/s13042-021-01496-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-021-01496-1

Keywords

Navigation