Skip to main content
SpringerLink
Log in

Stereo-based region of interest generation for real-time pedestrian detection

  • Published:
Peer-to-Peer Networking and Applications Aims and scope Submit manuscript

Abstract

Pedestrian detection is one of the major goals in advanced driver assistance systems (ADAS) which has become an active research area in recent years. In this paper, we present a stereo based pedestrian detection system by fusing the depth and color data provided by a stereo vision camera on a moving platform. The proposed method uses an adaptive window for region of interest (ROI) generation using dense depth map. The extracted candidates are then applied to a Histogram of Oriented Gradients (HOG) feature descriptor to refine ROIs and Support Vector Machine (SVM) is used to classify them into pedestrian and non-pedestrian classes. The system is tested on a stereo based DAS dataset and results show that our system is able to detect pedestrians with different scales and illumination conditions and in presence of partial occlusion.

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

Access this article

Log in via an institution

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
Fig. 9

Similar content being viewed by others

References

  1. Gavrila DM (2000) Pedestrian detection from a moving vehicle. In: European conference on computer vision, pp 37–49

  2. Geronimo D, Lopez AM, Sappa AD, Graf T (2010) Survey of pedestrian detection for advanced driver assistance systems. IEEE Trans Pattern Anal Mach Intell 32(7):1239–1258

    Article  Google Scholar 

  3. Shashua A, Gdalyahu Y, Hayun G (2004) Pedestrian detection for driving assistance Systems: single-frame classification and system level performance. Proc Intell Veh Symp 1–6

  4. Leibe B, Seemann E, Schiele B (2005) Pedestrian detection in crowded scenes. IEEE Conf Comput Vis Pattern Recognit (CVPR’05) 878–885

  5. Xu Y, Xu D, Lin S, Han TX, Cao X, Li X (2012) Detection of sudden pedestrian crossings for driving assistance systems. IEEE Trans Syst Man Cybern Part B 42(3):729–739

    Article  Google Scholar 

  6. Raksincharoensak P, Sakai Y, Shimizu I, Nagai M, Ulbricht D, Adomat R (2013) Development of an on-board pedestrian detection system using monocular camera for driver assistance applications. In: FISITA 2012 world automotive congress, pp 341–350

  7. Talukder A, Goldberg S, Matthies L, Ansar (2003) Real-time detection of moving objects in a dynamic scene from moving robotic vehicles. In: International Conference on intelligent robots and systems, pp 1380–1313

  8. Nam BD, Kang SI, Hong HK (2011) Pedestrian detection system based on stereo vision for mobile robot. In: Frontiers of computer vision, pp 1–7

  9. Soga M, Kato T, Ohta M, Ninomiya Y (2005) Pedestrian detection with stereo vision. In: Proceeding of the IEEE International conference on data engineering

  10. Broggi A, Fascioli A, Fedriga I, Tibaldi A, Rose MD (2003) Stereo-based preprocessing for human shape localization in unstructured environments. In: Proceeding of the IEEE Intelligent vehicles symposium, pp 410–415

  11. Gavrilla D, Munder S (2007) Multi-cue pedestrian detection and tracking from a moving vehicle. Int J Comput Vis 73(1):41–59

    Article  Google Scholar 

  12. Bajracharya M, Moghaddam B, Howard A, Brennan S, Matthies L (2009) Results from a real-time stereo-based pedestrian detection system on a moving vehicle. In: International conference on robotics and automation

  13. Bhowmick B, Bhadra S, Sinharay A (2011) Stereo vision based pedestrians detection and distance measurement for automotive application. In: Internal conference on intelligent systems, modeling and simulation, pp 25–29

  14. Viola P (2001) Rapid object detection using a boosted cascade of simple features. Conf Comput Vis Pattern Recognit, (CVPR 2001) 1:511–518

    Google Scholar 

  15. Keller CG, Enzweiler M, Gavrila DM (2011) A new benchmark for stereo-based pedestrian detection. In: Intelligent vehicles symposium, pp 691–696

  16. Keller CG, Enzweiler M, Rohrbach M, Llorca DF, Schnorr C, Gavrila DM (2011) The benefits of dense stereo for pedestrian detection. In: IEEE transactions on intelligent transportation systems, vol 12. pp 1096–1106

  17. Geronimo D, Sappa AD, Ponsa D, Lopez AM (2010) 2D-3D Based on-board pedestrian detection system. In: Computer vision and image understanding (special issue on intelligent vision systems), vol. 114. pp 583–595

  18. Keller CG, Llorca DF, Gavrila DM (2009) Dense stereo-based ROI generation for pedestrian detection. In: Proceedings of the 31st DAGM symposium on pattern recognition, pp 81–90

  19. Dalal N (2005) Histograms of oriented gradients for human detection. In: Computer vision and pattern recognition, (CVPR 2005) vol 1. pp 886–893

  20. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Intl. J Comp Vision 2:91–110

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL, USA

    Joohee Kim

  2. Multimedia Communications Laboratory, Illinois Institute of Technology, Chicago, IL, USA

    Maral Mesmakhosroshahi

Authors
  1. Joohee Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Maral Mesmakhosroshahi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joohee Kim.

Additional information

This work was supported by the Technology Development Program for Commercializing System Semiconductor funded By the Ministry of Trade, industry & Energy (MOTIE, Korea). (No. 10041126, Title: International Collaborative R&BD Project for System Semiconductor).

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kim, J., Mesmakhosroshahi, M. Stereo-based region of interest generation for real-time pedestrian detection. Peer-to-Peer Netw. Appl. 8, 181–188 (2015). https://doi.org/10.1007/s12083-013-0234-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12083-013-0234-2

Keywords

Search

Navigation