iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://doi.org/10.1007/s11042-022-13058-w
Pedestrian detection in infrared image based on depth transfer learning | Multimedia Tools and Applications Skip to main content
Springer Nature Link
Log in

Pedestrian detection in infrared image based on depth transfer learning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Because of the difficulty in feature extraction of infrared pedestrian images, the traditional methods of object detection usually make use of the labor to obtain pedestrian features, which suffer from the low-accuracy problem. With the development and the progress of science and technology, deep learning has gradually stepped into the problem of object detection, and achieved good results. In this paper, aiming at the defects of deep convolutional neural network, such as the high cost on training time and slow convergence, a new algorithm of MoblieNet V2(1.4) + SSD infrared image pedestrian detection based on transfer learning is proposed, which adopts a transfer learning method and the Adam optimization algorithm to accelerate network convergence. For the experiments, we augmented the OUS thermal infrared pedestrian dataset and our solution enjoys a higher mAP of 94.8% on the test dataset. The experimental results show that our proposed method has the characteristics of fast convergence, high detection accuracy and short detection time.

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

References

  1. Dianwei W, Yanhui H, Daxiang L et al (2018) Improved yolov3 infrared video image pedestrian detection algorithm. J Xi'an Univ Posts Telecommun 23(4):48–67

    Google Scholar 

  2. Girshick R, Donahue J, Darrell T et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Conference on Computer Vision and Pattern Recognition 580–588

  3. Jianting S, Guiqiang Z (2020) Improved yolov3 infrared image pedestrian detection algorithm. J Heilong-jiang Univ Sci Technol 30(4):442–447

    Google Scholar 

  4. Jifeng D, Yi L, Kaiming H et al (2016) R-FCN: object detection via region-based fully Convolu- tional networks. Conference on Neural Information Processing Systems

  5. Junyu Z, Yanming Z (2017) Overview of convolution neural network in image classification and target detection. Comput Eng Appl 53(13):34–41

    Google Scholar 

  6. Kai C, Zhengtao X, Yufen GC et al (2018) Research on infrared image pedestrian detection based on improved fast r-cnn. Infrared Technol 40(6):578–584

    Google Scholar 

  7. Kaiming H, Xiangyu Z, Shaoqing R et al (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. 2014 European Conference on Computer Vision 1904–1916

  8. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  9. Liang C, Xiaoming D, Mingquan Z (2016) Convolutional neural network in image understanding. Acta Automat Sin 42(9):1300–1312

    MATH  Google Scholar 

  10. Liu X, Li FM, Liu SJ (2020) An infrared image pedestrian detection algorithm based on improved SSD algorithm. Electr Opt Control 27(1):42–46 59

    Google Scholar 

  11. Ming X, Xiaosheng Y, Dongyue C et al (2018) Pedestrian detection in complex thermal infrared monitoring scene. Chin J Image Graph 23(12):1829–1837

    Google Scholar 

  12. Qi L (2018) Fruit image recognition system based on deep learning. Agric Eng 8(10):31–34

    Google Scholar 

  13. Redmon J, Divvala S, Girshick R et al (2016) You only look once: Unified, real-time object detection. 2016 IEEE Conf Comput Vis Pattern Recogn 779–788

  14. Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection withRegion proposal networks. Adv Neural Inf Proces Syst 28:1137–1149

    Google Scholar 

  15. Simon M, Rodner E (2015) Neural activation constellations: Unsupervised part model discovery with convolutional network. 2015 IEEE International Conference on Computer Vision and Pattern Recognition 1143–1151

  16. Song W, Shumin F (2019) Research and improvement of SSD (single shot multibox detector) target detection algorithm. Ind Control Comput 32(4):103–105

    Google Scholar 

  17. Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition 1–9

  18. Wang P, Wang Z, Lv D et al (2021) Low illumination color image enhancement based on Gabor filtering and Retinex theory. Multimed Tools Appl 80(12):17705–17719

    Article  Google Scholar 

  19. Xudong X, Liqian M (2018) Control chart recognition based on transfer learning and convolutional neural network. Comput Appl 38(S2):290–295

    Google Scholar 

  20. Xudong L, Mao Y, Tao L (2017) A review of target detection based on convolutional neural network. Comput Appl Res 34(10):2881–2891

    Google Scholar 

  21. Yancheng W, Hongchang C, Shaomei L, Gao G (2018) Pedestrian recognition neural network model based on heterogeneity of pedestrian attributes. Comput Eng 44(10):196–203

    Google Scholar 

  22. Yandong L, Zongbo H, Hang L (2016) A review of convolutional neural networks. Comput Appl 36(9):2508–2515

    Google Scholar 

  23. Yong LT, Ping L, Xiao GW et al (2015) Deep learning strong parts for pedestrian detection. 2015 IEEE International Conference on Computer Vision 1904–1912

  24. Zhihua Z (2016) Machine learning. Tsinghua Univ Press 121–139

  25. Zhihua Z (2016) Machine learning. Tsinghua University Press

Download references

Acknowledgments

This research was funded by the National Natural Science Foundation of China, grant number 6192007, 61462008, 61751213, 61866004; the Key projects of Guangxi Natural Science Foundation, grant number 2018GXNSFDA294001,2018GXNSFDA281009; the Natural Science Foundation of Guangxi, grant number 2018GXNSFAA294050, 2017GXNSFAA198365; 2015 Innovation Team Project of Guangxi University of Science and Technology, grant number gxkjdx201504; Research Fund of Guangxi Key Lab of Multi-source Information Mining & Security, grant number MIMS19-04; Natural Science School-level Project of Software Engineering Institute of Guangzhou, grant number ky202108; Guangxi Postgraduate Education Innovation Project, grant number GKYC202106, GKYC202104, YCSW2021320; College Students’ innovation and Entrepreneurship Project 202110594133, 202110594134.

Author information

Authors and Affiliations

  1. School of Computer Science and Telecommunication Engineering, Guangxi University of Science and Technology, Liuzhou, 545006, China

    Zhiwen Wang

  2. School of Electrical and Information Engineering, Guangxi University of Science and Technology, Liuzhou, 545006, China

    Jing Feng & Yifeng Zhang

  3. South China Institute of Software Engineering, GU, Guangzhou, 510990, Guangdong, China

    Jing Feng

Authors
  1. Zhiwen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jing Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yifeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, J.F and Z.w.W.; methodology, J.F; software, Y.h.W.; validation, J.F,Z.w.W.; formal analysis, J.F; investigation, Y.f.Z; data curation, Y.f.Z; writing—original draft preparation, J.F; writing—review and editing, Z.w.W; visualization, J.F; supervision, Y.f.Z; project administration, Z.w.W; funding acquisition, Z.w.W. All authors have read and agreed to the published version of the manuscript.”

Corresponding author

Correspondence to Zhiwen Wang.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.

Additional information

Publisher’s note

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

Appendix

Appendix

Table 11 Description of some symbols
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Z., Feng, J. & Zhang, Y. Pedestrian detection in infrared image based on depth transfer learning. Multimed Tools Appl 81, 39655–39674 (2022). https://doi.org/10.1007/s11042-022-13058-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-13058-w

Keywords

Search

Navigation