Skip to main content
SpringerLink
Log in
Book cover

International Conference on Intelligent Robotics and Applications

ICIRA 2018: Intelligent Robotics and Applications pp 335–345Cite as

Pedestrian Detection at Night Based on Faster R-CNN and Far Infrared Images

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10985))

Abstract

This paper presents a pedestrian detection system focused on night time conditions for vehicular safety applications. For this purpose we analyze the performance of the recent deep learning detector Faster R-CNN [1] with infrared images for detecting pedestrians at night. We discovered that Faster R-CNN has drawbacks when detecting pedestrians that are far away. For this reason, we present a new Faster R-CNN architecture focused on multi scale detection, through two Region Proposal Networks RPNCD and RPNLD. Our architecture has been compared with the best models such as VGG-16 and Resnet 101. The experimental results have been development on the CVC-09 dataset [2]. These show an improvement when detecting far away pedestrians, with a \(37.73\%\) miss rate on \(10^{-2}\) FPPI and the mAP is \(85\%\).

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99. IEEE Conference Publication (2015)

    Google Scholar 

  2. CVC-09: FIR Sequence Pedestrian Dataset. http://adas.cvc.uab.es/elektra/enigma-portfolio/item-1/

  3. Koing, D., Adam, M., Jarvers, C., Layher, G., Neumann, H., Teutsch, M.: Fully convolutional region proposal networks for multispectral person detection. In: CVPR Workshop (2017)

    Google Scholar 

  4. Olmeda, D., Premebida, C., Nunes, U., Armingol, J.M., de la Escalera, A.: Pedestrian detection in far infrared images. Integr. Computer-Aided Eng. 20, 347–360 (2013)

    Article  Google Scholar 

  5. World Health Organization WHO: Road traffic injuries. http://www.who.int/violence_injury_prevention/road_traffic/en/

  6. Agencia Nacional de Transito del Ecuador: Siniestros Octubre 2015. https://www.ant.gob.ec/index.php/descargable/file/3813-siniestros-octubre-2016

  7. Yan, J., Zhang, X., Lei, Z., Liao, S., Li, S.: Robust multi-resolution pedestrian detection in traffic scenes. In: CVPR Workshop (2013)

    Google Scholar 

  8. Li, J., Liang, X., Shen, S., Xu, T., Feng J., Yan, S: Scale-aware Fast R-CNN for pedestrian detection. Cornell University (2015)

    Google Scholar 

  9. Liu, J., Zhang, S., Wang, S., Metaxas, N.: Multi-spectral deep neural networks for pedestrian detection. In: BMVC (2016)

    Google Scholar 

  10. Guan, D., Cao, Y., Yang, J., Cao, Y., Ying Yang, M.: Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection. Cornell University (2018)

    Google Scholar 

  11. Deng, L., Yu, D.: Deep learning methods and applications. Found. Trends Sig. Process. 7, 3–4 (2014)

    MathSciNet  Google Scholar 

  12. Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., Lew, M.S.: Deep learning for visual understanding: a review. In: Deep Learning for Visual Understanding, vol. 187, pp. 27–48. Neurocomputing (2015)

    Google Scholar 

  13. Ertler, C., Posseger, H., Optiz, M., Bischof, H.: Pedestrian detection in RGB-D images from an elevated viewpoint. In: Computer Vision Winter Workshop (2017)

    Google Scholar 

  14. Cao, C., Wook, J.: Robust object proposals re-ranking for object detection in autonomous driving using convolutional neural networks. Sig. Process. Image Commun. 53, 110–122 (2017)

    Article  Google Scholar 

  15. Zhang, X., Chen, G., Saruta, K., Terata, Y.: Deep convolutional neural networks for all-day pedestrian detection. In: Kim, K., Joukov, N. (eds.) ICISA 2017. LNEE, vol. 424, pp. 171–178. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-4154-9_21

    Chapter  Google Scholar 

  16. Duyoung, H., Eunju, L., Ko, C.B.: Pedestrian detection at night using deep neural networks and saliency maps. J. Imaging Sci. Technol. 61, 60403-1–60403-9 (2017)

    Google Scholar 

  17. Chen, B., Wang, W., Qin, Q.: Robust multi-stage approach for the detection of moving target from infrared imagery. SPIE Optical Eng. 51(6), 067006 (2012)

    Article  Google Scholar 

  18. Jong, K., Hyung, H., Kang, P.: Convolutional neural network-based human detection in nighttime images using visible light camera sensors. Sensors 17, 1065 (2017)

    Article  Google Scholar 

  19. Chun, Y., Cai, D.: Research of the method of quicky finding the pedestrian area of interest. J. Electr. Electron. Eng. 5, 180–185 (2017)

    Article  Google Scholar 

  20. Qi, B., John, V., Liu, Z., Mita, S.: Pedestrian detection from thermal images with a scattered difference of directional gradients feature descriptor. In: 17th International IEEE Conference on Intelligent Transportation Systems (ITSC). IEEE Press (2014)

    Google Scholar 

  21. Baek, J., Kim, J., Kim, E.: Fast and efficient pedestrian detection via the cascade implementation of an additive kernel support vector machine. IEEE Trans. Intell. Transp. Syst. 18, 902–916 (2017)

    Article  Google Scholar 

  22. Jeong, M., Kwak, J., Son, J., Ko, B., Nam, J.: Fast pedestrian detection using a night vision system for safety driving. In: 11th International Conference on Computer Graphics, Imaging and Visualization, pp. 69–72. IEEE Press (2014)

    Google Scholar 

  23. Tome, D., Monti, F., Baroffio, L., Bondi, L., Tagliasacchi, M., Tubaro, S.: Deep convolutional neural networks for pedestrian detection. Sig. Process. Image Commun. 47, 482–489 (2016)

    Article  Google Scholar 

  24. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks. In: CVPR (2014)

    Google Scholar 

  25. Perlina, H., Lopes, H., Tagliasacchi, M., Tubaro, S.: Extracting human attributes using a convolutional neural network approach. Pattern Recogn. Lett. 68, 250–259 (2016)

    Article  Google Scholar 

  26. Ribeiro, D., Nascimento, J., Bernardino, A., Carneiro, G.: Improving the performance of pedestrian detectors using convolutional learning. Pattern Recogn. 61, 641–649 (2017)

    Article  Google Scholar 

  27. Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: CVPR (2013)

    Google Scholar 

  28. Kim, J., Baek, J., Kim, E.: A novel on-road vehicle detection method using \(\pi \)-HOG. IEEE Trans. Intell. Transp. Syst. 16, 3414–3429 (2015)

    Article  Google Scholar 

  29. Piniarski, K., Pawłowski, P., Dąbrowski, A.: Pedestrian detection by video processing in automotive night vision system. In: Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), pp. 104–109. IEEE Press (2014)

    Google Scholar 

  30. Chang, S., Yang, F., Wu, W., Cho, Y., Chen, S.: Nighttime pedestrian detection using thermal imaging based on HOG feature. In: Proceedings 2011 International Conference on System Science and Engineering. IEEE Press (2011)

    Google Scholar 

  31. Cao, J., Pang, Y., Li, X.: Learning multilayer channel features for pedestrian detection. IEEE Trans. Image Process. 26, 3210–3220 (2016)

    Article  MathSciNet  Google Scholar 

  32. Sun, H., Wang, C., Wang, B.: Night vision pedestrian detection using a forward-looking infrared camera. In: International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping (M2RSM), pp. 1–4. IEEE Press (2011)

    Google Scholar 

  33. Govardhan, P., Pati, C.: NIR image based pedestrian detection in night vision with cascade classification and validation. In: IEEE International Conference on Advanced Communications, Control and Computing Technologies, pp. 1438–1438. IEEE Press (2011)

    Google Scholar 

  34. Girshick, R., Donahue, J., Darrell, T., Malik, J: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition, pp. 580–587. IEEE Press (2014)

    Google Scholar 

  35. Girshick, R.: Fast R-CNN. In: Computer Vision and Pattern Recognition, pp. 1440–1448. IEEE Press (2015)

    Google Scholar 

  36. Zhang, L., Lin, L., Liang, X., He, K.: Is faster R-CNN doing well for pedestrian detection? In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 443–457. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_28

    Chapter  Google Scholar 

  37. Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354–370. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_22

    Chapter  Google Scholar 

  38. Konecny, J., Liu, J., Richtarik, P., Takac, M.: Mini-batch semi-stochastic gradient descent in the proximal setting. IEEE J. Sel. Top. Sig. Process. 10, 242–255 (2016)

    Article  Google Scholar 

  39. Kingma, D., Lei Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations. ICLR, San Diego (2015)

    Google Scholar 

  40. Dollár, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34, 743–761 (2012)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Carrera de Eléctrica y Electrónica, Universidad de las Fuerzas Armadas-ESPE, Sangolquí, Pichincha, Ecuador

    Michelle A. Galarza-Bravo

  2. Departamento de Electrónica, Automatización y Control, Universidad de las Fuerzas Armadas-ESPE, Sangolquí, Pichincha, Ecuador

    Marco J. Flores-Calero

Authors
  1. Michelle A. Galarza-Bravo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marco J. Flores-Calero
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Michelle A. Galarza-Bravo .

Editor information

Editors and Affiliations

  1. University of Newcastle, Callaghan, New South Wales, Australia

    Zhiyong Chen

  2. University of Newcastle, Callaghan, New South Wales, Australia

    Alexandre Mendes

  3. University of Newcastle, Callaghan, New South Wales, Australia

    Yamin Yan

  4. Shenzhen Institutes of Advanced Technology, Shenzhen, China

    Shifeng Chen

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Galarza-Bravo, M.A., Flores-Calero, M.J. (2018). Pedestrian Detection at Night Based on Faster R-CNN and Far Infrared Images. In: Chen, Z., Mendes, A., Yan, Y., Chen, S. (eds) Intelligent Robotics and Applications. ICIRA 2018. Lecture Notes in Computer Science(), vol 10985. Springer, Cham. https://doi.org/10.1007/978-3-319-97589-4_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-97589-4_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-97588-7

  • Online ISBN: 978-3-319-97589-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation