Learning-Based Night-Vision Image Recognition and Object Detection

  • Lianfa BaiEmail author
  • Jing Han
  • Jiang Yue


Image recognition and detection play an important role in many fields, especially in night-vision technology. Traditional methods of image recognition are largely based on information extracted from an image to classify. This requires users to select appropriate features to set feature representations for original images per the specific circumstances. Manual selection of features is a laborious and heuristic work, and the features acquired in this way usually have poor robustness. To automatically obtain more robust and stronger generalisation image features, many scholars have applied machine-learning methods. Through training with large volumes of data samples, the performance of recognition and detection is improved with better accuracy and robustness.


  1. Baldi, P., & Hornik, K. (1989). Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks, 2(1), 53–58.CrossRefGoogle Scholar
  2. Bengio, Y. (2009). Learning deep architectures for AI. Now Publishers.Google Scholar
  3. Bengio, Y., & Delalleau, O. (2011). On the expressive power of deep architectures. In International Conference on Discovery Science (p. 1). Springer-Verlag.Google Scholar
  4. Bengio, Y., Lamblin, P., Popovici, D., et al. (2007). Greedy layer-wise training of deep networks. Advances in Neural Information Processing Systems, 19, 153–160.Google Scholar
  5. Dollár, P., Appel, R., Belongie, S., & Perona, P. (2014). Fast feature pyramids for object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1532–1545.CrossRefGoogle Scholar
  6. Erhan, D., Bengio, Y., Courville, A., et al. (2010). Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, 11(3), 625–660.MathSciNetzbMATHGoogle Scholar
  7. Felzenszwalb, P., Girshick, R., McAllester, D. (2010). Cascade object detection with deformable part models. In Computer Vision and Pattern Recognition (CVPR) (pp. 2241–2248). San Francisco, CA, USA: IEEE.Google Scholar
  8. Guzmán, S., Gómez, A., Diez, G., & Fernández, D. S. (2015). Car detection methodology in outdoor environment based on histogram of oriented gradient (HOG) and support vector machine (SVM). In Networked and Electronic Media (LACNEM) (pp. 1–4). Medellin, Colombia: IET.Google Scholar
  9. Hecht-Nielsen, R. (1989). Theory of backpropagation neural networks. In International Joint Conference on Neural Networks (Vol. 1, pp. 593–605). IEEE Xplore.Google Scholar
  10. Liu, Y., Wang, H. H., Xiang, Y. L., & Lu, P. L. (2013). An approach of real-time vehicle detection based on improved Adaboost algorithm and frame differencing rule. Journal Huazhong University of Science & Technology, 41(S1), 379–382.Google Scholar
  11. Maria, G., Baccaglini, E., Brevi, D., Gavelli, M., & Scopigno, R. (2016). A drone-based image processing system for car detection in a smart transport infrastructure. In Electrotechnical Conference (MELECON) (pp. 1–5). Lemesos, Cyprus: IEEE.Google Scholar
  12. Masci, J., Meier, U., Cireşan, D., et al. (2011). Stacked convolutional autoencoders for hierarchical feature extraction. In International Conference on Artificial Neural Networks (pp. 52–59). Springer–Verlag.Google Scholar
  13. Qu, Y. Y., Jiang, L., & Guo, X. P. (2016). Moving vehicle detection with convolutional networks in UAV Videos. In Control, Automation and Robotics (ICCAR) (pp. 225–229). Hong Kong, China: IEEE.Google Scholar
  14. Rosenbaum, D., Charmette, B., Kurz, F., Suri, S., Thomas, U., & Reinartz, P. (2008). Automatic traffic monitoring from an airborne wide angle camera system. ISPRS Archives, 37(B3b), 557–562.Google Scholar
  15. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1988). Learning representations by back-propagating errors. In Neurocomputing: Foundations of research (pp. 533–536). MIT Press.Google Scholar
  16. Schölkopf, B., Platt, J., & Hofmann, T. (2006). Greedy layer-wise training of deep networks. In International Conference on Neural Information Processing Systems (pp. 153–160). MIT Press.Google Scholar
  17. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. Computer Science.Google Scholar
  18. Vincent, P., Larochelle, H., Bengio, Y., et al. (2008). Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on Machine learning (pp. 1096-1103). Google Scholar
  19. Wang, J. R. (2015). Research on multi-feature fusion of aerial photography image recognition taken by UAV. Chengdu, China: Chengdu University of Technology.Google Scholar
  20. Xu, H., Huang, Q., & Jay Kuo, C. C. (2016). Car detection using deformable part models with composite features. In Image Processing (ICIP) (pp. 3812–3816). Phoenix, AZ, USA: IEEE.Google Scholar
  21. Yang, X. F., & Yang, Y. (2014). A method of efficient vehicle detection based on HOG-LBP. Computer Engineering, 40(9), 210–214.Google Scholar
  22. Yebes, J., Bergasa, L., Arroyo, R., & Lázaro, A. (2014). Supervised learning and evaluation of KITTI’s cars detector with DPM. In Intelligent Vehicles Symposium Proceedings (pp. 768–773). Dearborn, MI, USA: IEEE.Google Scholar
  23. Zhang, W., Bai, L., Zhang, Y., et al. (2017). Integrative embedded car detection system with DPM. In International Conference on Image and Graphics (pp. 174–185). Springer.Google Scholar
  24. Zhang, J., Zhang, Y., Bai, L., et al. (2018). Lossless-constraint denoising based autoencoders. Signal Processing: Image Communication, 92–99.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Electronic and Optical EngineeringNanjing University of Science and TechnologyNanjingChina
  2. 2.School of Electronic and Optical EngineeringNanjing University of Science and TechnologyNanjingChina
  3. 3.National Key Laboratory of Transient PhysicsNanjing University of Science and TechnologyNanjingChina

Personalised recommendations