Embedded computer vision based smart systems raise challenging issues in many research fields, including real-time vision processing, communication protocols or distributed algorithms. The amount of data generated by cameras using high resolution image sensors requires powerful computing systems to be processed at digital video frame rates. Consequently, the design of efficient and flexible smart cameras, with on-board processing capabilities, has become a key issue for the expansion of smart vision systems relying on decentralised processing at the image sensor node level. In this context, field programmable gate arrays (FPGA)-based platforms, supporting massive data parallelism, offer large opportunities to match real-time processing constraints compared with platforms based on general purpose processors. In this study, the authors describe the implementation, on such a platform, of a configurable object detection application, reformulated according to the dataflow model of computation. The application relies on the computation of the histogram of oriented gradients and a linear SVM-based classification. It is described using the CAPH programming language, allowing efficient hardware descriptions to be generated automatically from high level dataflow specifications without prior knowledge of hardware description languages such as VHDL or Verilog. Results show that the performance of the generated code does not suffer from a significant overhead compared with handwritten HDL code.

References

1. 1)
  - 5. Enzweiler, M., Gavrila, D.M.: ‘Monocular pedestrian detection: survey and experiments’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (12), pp. 2179–2195 (doi: 10.1109/TPAMI.2008.260).
2. 2)
  - 13. Vapnik, V.: ‘Estimation of dependences based on empirical data: Springer series in statistics (Springer Series in Statistics)’ (Springer-Verlag New York, Inc., Secaucus, NJ, USA, 1982).
3. 3)
  - 9. Sérot, J., Berry, F., Ahmed, S.: ‘Caph: a language for implementing stream-processing applications on fpgas’, in Athanas, P., Pnevmatikatos, D., Sklavos, N. (Eds.): ‘Embedded Systems Design with FPGAs’, (Springer, New York, 2013), pp. 201–224. Available at http://dx.doi.org/10.1007/978-1-4614-1362-2_9.
4. 4)
  - 7. Sérot, J., Quénot, G., Zavidovique, B.: ‘Functional programming on a dataflow architecture: applications in real-time image processing’, Mach. Vis. Appl., 1993, 7, (1), pp. 44–56. Available at http://dx.doi.org/10.1007/BF01212416.
5. 5)
  - 21. Birem, M., Berry, F.: ‘Dreamcam: a modular fpga-based smart camera architecture’, J. Syst. Archit., 2014, 60, (6), pp. 519–527 (doi: 10.1016/j.sysarc.2014.01.006).
6. 6)
  - 3. Antola, A., Santambrogio, M., Fracassi, M., et al: ‘A novel hardware/software codesign methodology based on dynamic reconfiguration with impulse c and codeveloper’. 2007 third Southern Conf. on. IEEE Programmable Logic, 2007, SPL'07.2007, pp. 221–224.
7. 7)
  - 20. Porikli, F.: ‘Integral histogram: a fast way to extract histograms in cartesian spaces’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2005, pp. 829–836.
8. 8)
  - 24. Kadota, R., Sugano, H., Hiromoto, M., et al: ‘Hardware architecture for hog feature extraction’. Proc. of the 2009 Fifth Int. Conf. on Intelligent Information Hiding and Multimedia Signal Processing, ser. IIH-MSP ’09, Washington, DC, USA: IEEE Computer Society, 2009, pp. 1330–1333. Available at http://dx.doi.org/10.1109/IIH-MSP.2009.216.
9. 9)
  - 16. Lee, S., Min, K., Suh, T.: ‘Accelerating histograms of oriented gradients descriptor extraction for pedestrian recognition’, Comput. Electr. Eng., 2013, 39, (4), pp. 1043–1048 (doi: 10.1016/j.compeleceng.2013.04.001).
10. 10)
  - 10. Sérot, J., Berry, F., Bourrasset, C.: ‘High-level dataflow programming for real-time image processing on smart cameras’, J. Real-Time Image Process., 2014, pp. 1–13. Available at : http://dx.doi.org/10.1007/s11554-014-0462-6.
11. 11)
  - 12. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’, Schmid, C., Soatto, S., Tomasi, C.(Eds.) in ‘International Conference on Computer Vision & Pattern Recognition’, (Eds.): June 2005, vol. 2, pp. 886–893. Available at http://lear.inrialpes.fr/pubs/2005/DT05.
12. 12)
  - 5. Eker, J., Janneck, J.: ‘Cal language report’. University of California at Berkeley California, Berkeley, CA 94720, USA, Technical Memorandum, 2003.
13. 13)
  - 18. Hahnle, M., Saxen, F., Hisung, M., et al: ‘Fpga-based real-time pedestrian detection on high-resolution images’. 2013 IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2013, pp. 629–635.
14. 14)
  - 22. Joachims, T.: ‘Svmlight: support vector machine’, 1999, 19, (4).
15. 15)
  - 6. Najjar, W.A., Lee, E.A., Gao, G.R.: ‘Advances in the dataflow computational model’, Parallel Comput., 1999, 25, (13–14), pp. 1907–1929. Available at http://www.sciencedirect.com/science/article/pii/S0167819199000708 (doi: 10.1016/S0167-8191(99)00070-8).
16. 16)
  - 15. Dennis, J.B.: ‘Data flow supercomputers’, Computer, 1980, 13, (11), pp. 48–56 (doi: 10.1109/MC.1980.1653418).
17. 17)
  - 8. Sérot, J., Quénot, G.M., Zavidovique, B.: ‘A visual dataflow programming environment for a real-time parallel vision machine’, J. Vis. Lang. Comput., 1995, 6, pp. 327–347 (doi: 10.1006/jvlc.1995.1019).
18. 18)
  - 4. Yankova, Y., Bertels, K., Vassiliadis, S., et al: ‘Automated hdl generation: Comparative evaluation’. IEEE Int. Symp. on Circuits and Systems, 2007. ISCAS 2007,May 2007, pp. 2750–2753.
19. 19)
  - 14. Cortes, C., Vapnik, V.: ‘Support-vector networks’, Mach. Learn., 1995, 20, (3), pp. 273–297,. Available at http://dx.doi.org/10.1007/BF00994018.
20. 20)
  - 26. Sérot, J., Berry, F., Ahmed, S.: ‘Implementing stream-processing applications on fpgas: a dsl-based approach’. 2011 Int. Conf. on Field Programmable Logic and Applications (FPL), 2011, pp. 130–137.
21. 21)
  - 25. Mizuno, K., Terachi, Y., Takagi, K., et al: ‘Architectural study of hog feature extraction processor for real-time object detection’. 2012 IEEE Workshop on Signal Processing Systems (SiPS), October 2012, pp. 197–202.
22. 22)
  - 17. Bauer, S., Kohler, S., Doll, K., et al: ‘Fpga-gpu architecture for kernel svm pedestrian detection’. 2010 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2010, pp. 61–68.
23. 23)
  - 19. Zhu, Q., Yeh, M.-C., Cheng, K.-T., et al: ‘Fast human detection using a cascade of histograms of oriented gradients’. Proc. of the 2006 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition – Volume 2, ser. CVPR ‘06.Washington, DC, USA: IEEE Computer Society, 2006, pp. 1491–1498. Available at http://dx.doi.org/10.1109/CVPR.2006.119.
24. 24)
  - 2. Frigo, J., Gokhale, M., Lavenier, D.: ‘Evaluation of the streams-c c-to-fpga compiler: an applications perspective’. Proc. of the 2001 ACM/SIGDA Ninth Int. Symp. on Field Programmable Gate Arrays, 2001, pp. 134–140.
25. 25)
  - 1. Graphics, M., Tool, H.: ‘Catapult c’, 2010.
26. 26)
  - 11. ‘The Caph Programming Language home page’. Available at http://caph.univ-bpclermont.fr.

Dataflow object detection system for FPGA-based smart camera

References

Related content