Infrared Dim and Small Target Detection Based on Denoising Autoencoder Network

Abstract

The method of infrared small target detection is a crucial technology for infrared early-warning tasks, infrared imaging guidance, and large field of view target monitoring, and it is very important for certain early-warning tasks. In this paper, we propose an end-to-end infrared small target detection model (called CDAE) based on denoising autoencoder network and convolutional neural network, which treats small targets as “noise” in infrared images and transforms small target detection tasks into denoising problems. In addition, we use the perceptual loss to solve the problem of background texture feature loss in the encoding process, and propose the structural loss to make up for the perceptual loss defect in which small targets appear. We compare ten methods on six sequences and one single-frame dataset. Experimental results show that our method obtains the highest SCRG value on four sequences and the highest BSF value on six sequences. From the ROC curve, we can see that our method achieves the best results in all test sets.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. 1.

    Lu H, Li Y, Mu S, Wang D, Kim H, Serikawa S (2018) Motor anomaly detection for unmanned aerial vehicles using reinforcement learning. IEEE Internet Things J 5(4):2315–2322

    Article  Google Scholar 

  2. 2.

    Chen CLP, Li H, Wei Y, Xia T, Tang YY (2014) A local contrast method for small infrared target detection. IEEE Trans Geosci Remote Sens 52(1):574–581

    Article  Google Scholar 

  3. 3.

    Qin Y, Li B (2016) Effective infrared small target detection utilizing a novel local contrast method. IEEE Geosci Remote Sens Lett 13(12):1890–1894

    Article  Google Scholar 

  4. 4.

    Chen Y, Xin Y (2016) An efficient infrared small target detection method based on visual contrast mechanism. IEEE Geosci Remote Sens Lett 13(7):962–966

    Article  Google Scholar 

  5. 5.

    Wei Y, You X, Li H (2016) Multiscale patch-based contrast measure for small infrared target detection. Pattern Recognit 58:216–226

    Article  Google Scholar 

  6. 6.

    Shi Y, Wei Y, Yao H, Pan D, Xiao G (2018) High-boost-based multiscale local contrast measure for infrared small target detection. IEEE Geosci Remote Sens Lett 15(1):33–37

    Article  Google Scholar 

  7. 7.

    Deng H, Sun X, Liu M, Ye C, Zhou X (2016) Small infrared target detection based on weighted local difference measure. IEEE Trans Geosci Remote Sens 54(7):4204–4214

    Article  Google Scholar 

  8. 8.

    Redmon J, Divvala S, Girshick R, et al (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). IEEE Computer Society

  9. 9.

    Serikawa S, Lu H (2014) Underwater image dehazing using joint trilateral filter. Comput Electr Eng 40 (1):41–50

    Article  Google Scholar 

  10. 10.

    Lu H, Li Y, Uemura T, Kim H, Serikawa S (2018) Low illumination underwater light field images reconstruction using deep convolutional neural networks. Futur Gener Comput Syst 82:142–148

    Article  Google Scholar 

  11. 11.

    Deshpande SD, Er MH, Ronda V, Chan P (1999) Max-mean and max-median filters for detection of small targets. In: Proceedings of the SPIE’s international symposium on optical science, engineering, and instrumentation, international society for optics and photonics, Denver, CO, USA, 4 October, pp 74–83

  12. 12.

    Zeng M, Li J, Peng Z (2006) The design of top-hat morphological filter and application to infrared target detection. Infrared Physics Technol 48:67–76

    Article  Google Scholar 

  13. 13.

    Yang C, Ma J, Qi S, et al (2015) Directional support value of Gaussian transformation for infrared small target detection[J]. Applied Optics 54–9

  14. 14.

    Chen CLP, Li H, Wei Y, Xia T, Tang YY (2014) A local contrast method for small infrared target detection. IEEE Trans Geosci Remote Sens 52(1):574–581

    Article  Google Scholar 

  15. 15.

    Han J, Ma Y, Zhou B, Fan F, Liang K, Fang Y (2014) A robust infrared small target detection algorithm based on human visual system. IEEE Geosci Remote Sens Lett 11(12):2168– 2172

    Article  Google Scholar 

  16. 16.

    Chen Y, Xin Y (2016) An effcient infrared small target detection method based on visual contrast mechanism. IEEE Geosci Remote Sens Lett 13(7):962–966

    Article  Google Scholar 

  17. 17.

    Bai K, Wang Y, Song Q (2016) Patch similarity based edge-preserving background estimation for single frame infrared small target detection. In: 2016 IEEE international conference on image processing (ICIP). IEEE, p 2016

  18. 18.

    Shao X, Fan H, Lu G, Xu J (2012) An improved infrared dim and small target detection algorithm based on the contrast mechanism of human visual system. Infr Phys Technol 55(5):403– 408

    Article  Google Scholar 

  19. 19.

    Han J, Ma Y, Huang J, Mei X, Ma J (2016) An infrared small target detecting algorithm based on human visual system. IEEE Geosci Remote Sens Lett 13(3):452–456

    Google Scholar 

  20. 20.

    Han J, Ma Y, Zhou B, Fan F, Liang K, Fang Y (2014) A robust infrared small target detection algorithm based on human visual system. IEEE Geosci Remote Sens Lett 11(12):2168–2172

    Article  Google Scholar 

  21. 21.

    Chenqiang G, Deyu M, Yi Y, et al (2013) Infrared patch-image model for small target detection in a single image. IEEE Trans Image Process 22(12):4996–5009

    MathSciNet  MATH  Article  Google Scholar 

  22. 22.

    Yimian D, Yiquan W, Yu S (2016) Infrared small target and background separation via column-wise weighted robust principal component analysis. Infrared Phys Technol 77:421–430

    Article  Google Scholar 

  23. 23.

    Yimian D, Yiquan W (2016) Reweighted infrared patch-tensor model with both non-local and local priors for single-frame small target detection. IEEE journal of selected topics in applied earth observations and remote sensing

  24. 24.

    Chen B, Wang W, Qin Q (2010) Infrared dim target detection based on fuzzy-ART neural network[C]. In: International conference on computational intelligence & natural computing. IEEE

  25. 25.

    Liangkui L, Shaoyou W, et al (2018) Using deep learning to detect small targets in infrared oversampling images. J Syst Eng Electron (5):947–952

  26. 26.

    Gao C, Wang L, Xiao Y, Zhao Q, Meng D (2018) Infrared small-dim target detection based on Markov random field guided noise modeling. Pattern Recogn 76:463–475

    Article  Google Scholar 

  27. 27.

    Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440–1448

  28. 28.

    Ren S, He K, Girshick R, et al (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, pp 91–99

  29. 29.

    Vincent P, Larochelle H, Bengio Y, et al (2008) Extracting and composing robust features with denoising autoencoders. International conference on machine learning, ACM

  30. 30.

    Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: European conference on computer vision. Springer, Cham, pp 694–711

Download references

Acknowledgments

The paper is supported by National Natural Science Foundation of China (61703209,61773215).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Manshu Shi.

Additional information

Publisher’s Note

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

Appendix

Appendix

Fig. 6
figure6

Results in different Scenes.The figure above is the original picture, and the figure below shows the output result of the CDAE model

Fig. 7
figure7

Shows the result of a representative images with Airplane sequence in each method. From top to bottom,left to right,The result of method are: original image,Max-median, Top-hat, DSVT,LCM, LDM, WLDM, PatchSim, CLSDM, IPI, NIPPS, RIPT, ours

Fig. 8
figure8

shows the result of a representative images with Cloudy-sky sequence in each method.The introduction as above

Fig. 9
figure9

shows the result of a representative images with Multi-target sequence in each method.The introduction as above

Fig. 10
figure10

shows the result of a representative images with Space sequence in each method.The introduction as above

Fig. 11
figure11

shows the result of a representative images with Car sequence in each method.The introduction as above

Fig. 12
figure12

shows the result of a representative images with Missile sequence in each method.The introduction as above

Fig. 13
figure13

shows the result of a representative images with Single set in each method.The introduction as above

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Shi, M., Wang, H. Infrared Dim and Small Target Detection Based on Denoising Autoencoder Network. Mobile Netw Appl 25, 1469–1483 (2020). https://doi.org/10.1007/s11036-019-01377-6

Download citation

Keywords

  • Small target detection
  • Infrared images
  • Denoising autoencoder
  • End-to-end deep model
  • Image gradient