Human detection is exploited as a key operation in many applications such as automotive safety, intelligent vehicles, assisted living, and video surveillance. Consequently, there is a significant advancement in this area of research in the past years and a vast literature. In this study, the authors propose a pedestrian detection system which relies on sliding covariance matrix feature descriptor combined with a support vector machine classifier. The proposed framework is implemented onto field programmable gate array prototyping boards. Experimental results using the standard Institut National de Recherche en Informatique et en Automatique (INRIA) pedestrian benchmark dataset show that the proposed architecture achieved outstanding processing performances with high detection accuracy when compared with state-of-the-art methods.

References

1. 1)
  - 24. Negi, K., Dohi, K., Shibata, Y., et al: ‘Deep pipelined one-chip FPGA implementation of a real-time image-based human detection algorithm’. Proc. Int. Conf. Field Programmable Technology, New Delhi, December 2011, pp. 1–8.
2. 2)
  - 4. Viola, P., Jones, M., Snow, D.: ‘Detecting pedestrians using patterns of motion and appearance’, Int. J. Comput. Vis., 2005, 63, pp. 153–161 (doi: 10.1007/s11263-005-6644-8).
3. 3)
  - 22. Burges, C.J.C.: ‘A tutorial on support vector machines for pattern recognition’, Data Min. Knowl. Discov., 1998, 2, (2), pp. 121–167 (doi: 10.1023/A:1009715923555).
4. 4)
  - 30. Martelli, S., Tosato, D., Cristani, M., et al: ‘Fast FPGA-based architecture for pedestrian detection based on covariance matrices’. Proc. IEEE Int. Conf. Image Processing, Brussels, September 2011, pp. 389–392.
5. 5)
  - 25. Lee, S., Son, H., Choi, J., et al: ‘HOG feature extractor circuit for real-time human and vehicle detection’. Proc. IEEE Conf. TENCON, Cebu, November 2012, pp. 1–5.
6. 6)
  - 10. Dollár, P., Tu, Z., Perona, P., et al: ‘Integral channel features’. Proc. BMVC, 2009, pp. 1–11.
7. 7)
  - 27. Bauer, S., Kohler, S., Doll, K., et al: ‘FPGA-GPU architecture for kernel SVM pedestrian detection’. Proc. IEEE Computer Vision and Pattern Recognition Workshops, San Francisco, June 2010, pp. 61–68.
8. 8)
  - 33. ‘INRIA person dataset’. Available at http://www.pascal.inrialpes.fr/data/human/, accessed August 2015.
9. 9)
  - 19. Bąk, S., Brémond, F.: ‘Re-identification by covariance descriptors’, inGong, S., Cristani, M., Yan, S., Loy, C.C. (Eds.): Person re-identification, advances in computer vision and pattern recognition (Springer-Verlag, London, 2014, 1st edn.), pp. 71–91.
10. 10)
  - 9. Arsigny, V., Fillard, P., Pennec, X., Ayache, N.: ‘Geometric means in a novel vector space structure on symmetric positive-definite matrices’, SIAM J. Matrix Anal. Appl., 2007, 29, (1), pp. 328–347 (doi: 10.1137/050637996).
11. 11)
  - 23. Kadota, R., Sugano, H., Hiromoto, M., et al: ‘Hardware architecture for HOG feature extraction’. Proc. Int. Conf. Intelligent Information Hiding and Multimedia Signal Processing, Kyoto, September 2009, pp. 1330–1333.
12. 12)
  - 16. Wu, B., Nevatia, R.: ‘Detection of multiple, partially occluded humans in a single image by Bayesian combination of Edgelet part detectors’. Proc. IEEE Int. Conf. Computer Vision, Beijing, October 2005, pp. 90–97.
13. 13)
  - 21. Zhu, Y., Liu, Y., Zhang, D., et al: ‘Acceleration of pedestrian detection algorithm on novel C2RTL HW/SW co-design platform’. Proc. Int. Conf. Green Circuits and Systems, Shanghai, June 2010, pp. 615–620.
14. 14)
  - 20. Xie, S., Li, Y., Jia, Z., et al: ‘Binarization-based human detection for compact FPGA implementation’, inWu, C., Cohen, A. (Eds.): Lecture notes in computer science, advanced parallel processing technologies (Springer-Verlag, Berlin Heidelberg, 2013, 1st edn.), pp. 119–131.
15. 15)
  - 20. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, pp. 91–110 (doi: 10.1023/B:VISI.0000029664.99615.94).
16. 16)
  - 7. Cheng, H., Zheng, N., Qin, J.: ‘Pedestrian detection using sparse Gabor filter and support vector machine’. Proc. IEEE Intelligent Vehicles Symp., Las Vegas, June 2005, pp. 583–587.
17. 17)
  - 34. ‘OpenCV library’. Available at http://www.opencv.org, accessed February 2014.
18. 18)
  - 2. Mohamed, H., Fatih, P., Larry, D.: ‘A comprehensive evaluation framework and a comparative study for human detectors’, IEEE Trans. Intell. Transp. Syst., 2009, 10, (3), pp. 417–427 (doi: 10.1109/TITS.2009.2026670).
19. 19)
  - 8. Zheng, Y., Shen, C., Huang, X.: ‘Pedestrian detection using center symmetric local binary patterns’. Proc. IEEE Int. Conf. Image Processing, Hong Kong, September 2010, pp. 3497–3500.
20. 20)
  - 28. Schapire, R., Singer, Y.: ‘Improved boosting algorithms using confidence-rated predictions’, Mach. Learn., 1999, 37, (3), pp. 297–336 (doi: 10.1023/A:1007614523901).
21. 21)
  - 11. Dollár, P., Wojek, C., Schiele, B., et al: ‘Pedestrian detection: a benchmark’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Miami, June 2009, pp. 304–311.
22. 22)
  - 10. Viola, P., Jones, M.: ‘Robust real-time face detection’, Int. J. Comput. Vis., 2004, 2, (57), pp. 137–154 (doi: 10.1023/B:VISI.0000013087.49260.fb).
23. 23)
  - 22. Hiromoto, M., Miyamoto, R.: ‘Hardware architecture for high-accuracy real-time pedestrian detection with CoHOG features’. Proc. IEEE Computer Vision Workshops, Kyoto, September 2009, pp. 894–899.
24. 24)
  - 35. ‘LIBSVM – a library for support vector machines. By Chih-Chung Chang and Chih-Jen Lin’. Available at http://www.csie.ntu.edu.tw/~cjlin/libsvm/, accessed February 2014.
25. 25)
  - 26. Komorkiewicz, M., Kluczewski, M., Gorgon, M.: ‘Floating point HOG implementation for real-time multiple object detection’. Proc. Int. Conf. Field Programmable Logic and Applications, Oslo, August 2012, pp. 711–714.
26. 26)
  - 1. Gerónimo, D., López, A.M.: ‘Vision-based pedestrian protection systems for intelligent vehicles’ (Springer-Verlag, New York, 2014, 1st edn.).
27. 27)
  - 13. Tuzel, O., Porikli, F., Meer, P.: ‘Region covariance: a fast descriptor for detection and classification’. Proc. European Conf. on Computer Vision ECCV, Graz, Austria, May 2006, pp. 589–600.
28. 28)
  - 15. Wu, B., Nevatia, R.: ‘Optimizing discrimination efficiency tradeoff in integrating heterogeneous local features for object detection’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, June 2008, pp. 1–8.
29. 29)
  - 32. Tosato, D., Farenzena, M., Cristani, M., et al: ‘Multiclass classification on Riemannian manifolds for video surveillance’. Proc. European Conf. on Computer Vision, Heraklion, Greece, September 2010, pp. 378–391.
30. 30)
  - 14. Oncel, T., Fatih, P., Peter, M.: ‘Pedestrian detection via classification on Riemannian manifolds’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (10), pp. 1713–1727 (doi: 10.1109/TPAMI.2008.75).
31. 31)
  - 29. Abid, N., Loukil, K., Ayedi, W., et al: ‘Optimized parallel model of covariance based person detection’. Proc. Int. Conf. Image Analysis and Processing, Genoa, Italy, September 2015, pp. 287–298.
32. 32)
  - 3. Oren, M., Papageorgiou, C., Sinha, P., et al: ‘Pedestrian detection using wavelet templates’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Juan, June 1997, pp. 193–199.
33. 33)
  - 9. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Diego, June 2005, pp. 886–893.
34. 34)
  - 28. Calum, B., Neil, M.R., Danny, H.: ‘Characterising a heterogeneous system for person detection in video using histograms of oriented gradients: power vs. speed vs. accuracy’, IEEE J. Emerging Sel. Top. Circuits Syst., 2013, 3, (2), pp. 236–247 (doi: 10.1109/JETCAS.2013.2256821).
35. 35)
  - 12. Benenson, R., Omran, M., Hosang, J., et al: ‘Ten years of pedestrian detection, what have we learned?’. Proc. European Conf. on Computer Vision ECCV Workshops, Zurich, September 2014, pp. 613–627.

Efficient and high-performance pedestrian detector implementation for intelligent vehicles

References

Related content