IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Efficient Implementation of Candidate Region Extractor for Pedestrian Detection System with Stereo Camera based on GP-GPU

스테레오 영상 보행자 인식 시스템의 후보 영역 검출을 위한 GP-GPU 기반의 효율적 구현

  • Received : 2012.11.13
  • Accepted : 2013.01.17
  • Published : 2013.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

There have been various research efforts for pedestrian recognition in embedded imaging systems. However, many suffer from their heavy computational complexities. SVM classification method has been widely used for pedestrian recognition. The reduction of candidate region is crucial for low-complexity scheme. In this paper, We propose a real time HOG based pedestrian detection system on GPU which images are captured by a pair of cameras. To speed up humans on road detection, the proposed method reduces a number of detection windows with disparity-search and near-search algorithm and uses the GPU and the NVIDIA CUDA framework. This method can be achieved speedups of 20% or more compared to the recent GPU implementations. The effectiveness of our algorithm is demonstrated in terms of the processing time and the detection performance.

Keywords

References

  1. Y. Chen, S. LI, X. LIN, "Fast Hog Feature Computation Based On CUDA," Proceedings on IEEE International Conference of Computer Science and Automation Engineering, Vol. 4, pp.748-751, 2011.
  2. C. Premebida, O. Ludwig, U. Nunes, "Lidar and vision-based pedestrian detection system," Journal of Field Robotics, Vol. 26, No. 9, pp.696-711, 2009. https://doi.org/10.1002/rob.20312
  3. S.H. Kang, H.R. Byun, S.W. Lee, "Real-time Pedestrian Detection Using Support Vector Machines," International Journal of Pattern Recognition and Artificial Intelligence, Vol. 17, No. 3, pp.405-416, 2003. https://doi.org/10.1142/S0218001403002435
  4. H. Hattori, A. Seki, M. Nishiyama, T. Watanabe, "Stereo-based Pedestrian Detection using Multiple Patterns," Proceedings on BMVC, pp.1-10, 2009.
  5. S. Nedevschi, S. Bota, C. Tomiuc, "Stereo-Based Pedestrian Detection for Collision-Avoidance Applications," IEEE Transactions, Intelligent Transportation Systems, Vol. 10, No. 3, pp.380-391, 2009. https://doi.org/10.1109/TITS.2008.2012373
  6. I.P. Alonso, D.F. Llorca, M.A. Sotelo, "Combination of Feature Extraction Methods for SVM Pedestrian Detection," IEEE Transactions Intelligent Transportation Systems, Vol. 8, No. 2, pp.292-307, 2007. https://doi.org/10.1109/TITS.2007.894194
  7. A. Ess, B. Leibe, L.V. Gool, "Depth and appearance for mobile scene analysis," Proceedings on ICCV, 2007.
  8. D.H. Yeo, J.H. Kim, S.Y. Suk, "Pedestrian Detection System in Car Driving Situations," Proceedings on Fall Conference of IEMEK, Vol. 1, No. 1, pp.282-284, 2012 (in Korean).
  9. N. Dalal, B. Triggs, "Histograms of Oriented Gradientes for Human Detection," Proceedings on IEEE International Conference of Computer Vision and Pattern Recognition, Vol. 1, pp.886-839, 2005.
  10. T. Joaschims, Advances in Kernel Method - Support Vector Learning, The MIT Press, Cambridge, M.A, USA, 1999.
  11. P. Kelly, N.E. O'Commor, A.F. Smeaton, "Robust Pedestrian Detection and Tracking in Crowded Scenes," Image and Vision Computing, Vol. 27, No. 10, pp.1445-1458, 2009. https://doi.org/10.1016/j.imavis.2008.04.006
  12. K. Tarui, S. Kumada, H. Terada, "Cascaded HOG on GPU," Proceedings on GPU Technology Conference, 2010.
  13. V.A. Prisacariu, I. Reid, "fast HOG-a real-time GPU implementation of HOG," Technical Report, No. 2310/09, Oxford University, 2009.