Nothing Special   »   [go: up one dir, main page]

Skip to main content
Log in

IMAPCAR: A 100 GOPS In-Vehicle Vision Processor Based on 128 Ring Connected Four-Way VLIW Processing Elements

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

This paper presents IMAPCAR, a 100GOPS programmable highly parallel vision processor LSI consuming less than 2 W of power for in-vehicle vision tasks of driver assistance systems. First, requirements of vision processors for driver assistance systems as well as the characteristics of vision tasks for safety are summarized. Next, features in the design of IMAPCAR are described in detail, which comparing with a previous design, improved the performance for major vision tasks by a factor of 2.5 while reduced 50% of power. Design choices taken by other in-vehicle vision processors are also compared and analyzed. Finally, technology perspectives of future in-vehicle vision processors are discussed.

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

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Hart, J., et al. (2005). Implementation of a 4th-Generation 1.8 GHz Dual-Core SPARC V9 Microprocessor. ISSCC Digest of Technical Papers, 10(3), 186–187.

    Google Scholar 

  2. Ikai, H., Usami, M., Ohta, M., Ohue, K., & Hidano, F. (2006). Obstacle sensor using stereo vision. In Proc. of ITS Congress.

  3. Kuroda, I., & Kyo, S. (2007). Media processing LSI architectures for automotives—challenges and future trends—. IEICE Transactions on Electronics, E 90-C(10), 1850–1857.

    Article  Google Scholar 

  4. Kondo, Y., et al. (2001). A 4GOPS 3Way-VLIW image recognition processor based on a configurable media-processor. ISSCC Digest of Technical Papers, 2001, 148–149.

    MathSciNet  Google Scholar 

  5. Kyo, S., Sakurai, K., & Okazaki, S. (1999). A robust vehicle detecting and tracking system for wet weather conditions using the IMAP-VISION image processing board. Proc. of IEEE International Conference on ITS, pp. 423–428.

  6. Kyo, S., Koga, T., Okazaki, S., Uchida, R., Yoshimoto, S., & Kuroda, I. (2003). A 51.2GOPS scalable video recognition processor for intelligent cruise control based on a linear array of 128 4-way VLIW processing elements. ISSCC Digest of Technical Papers, 1, 48–49.

    Article  Google Scholar 

  7. Kyo, S., Arai, T., & Okazaki, S. (2005). An integrated memory array processor architecture for embedded image recognition systems, Proc. of the 32nd Annual International Symposium on Computer Architecture (ISCA), pp. 132–145.

  8. Kyo, S., Koga, T., Lieske, H., Nomoto, S., & Okazaki, S. (2007). A mixed-mode parallel processor architecture for embedded systems. Proc. of ACM International Conference on Supercomputing, pp. 253–262, June.

  9. Muramatsu, S., Otsuka, Y., Takenaga, H., Kobayashi, Y., Furusawa, I., & Monji, T. (2002). Image processor device for automotive vision systems. IEEE Intelligent Vehicle Symposium, 1, 121–126.

    Google Scholar 

  10. Naffziger, S., et al. (2005). The implementation of a 2-core multi-threaded itanium-family processor. ISSCC Digest of Technical Papers, 10(1), 182–183.

    Google Scholar 

  11. Okazaki, S., Kyo, S., & Hidano, F. (2006). IMAPCAR: a highly parallel integrated memory array processor for in vehicle image recognition applications. In Proc. of ITS Congress.

  12. Shiota, T., et al. (2005). A 51.2 GOPS 1.0GB/s-DMA single-chip multi-processor integrating quadruple 8-way VLIW processors. ISSCC Digest of Technical Papers, 10(7), 194–195.

    Google Scholar 

  13. Sakurai, K., Kyo, S., & Okazaki, S. (2006). Implementation of overtaking vehicle detection using the IMAPCAR highly parallel image processor. In Proc. of ITS Congress.

  14. Sun, Z., Bebis, G., & Miller, R. (2006). On-road vehicle detection: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(5), 694–711 May.

    Article  Google Scholar 

  15. Tanabe, J., et al. (2003). Visconti: multi-VLIW image recognition processor based on configurable processor. IEEE Custom Integrated Circuits Conference, 185–188.

  16. Abbo, A., et al. (2007). XETAL-II:A 107 GOPS, 600 mW massively-parallel processor for video scene analysis. ISSCC Digest of Technical Papers, 270–271.

  17. Chen, C., et al. (2008). iVisual: An intelligent visual sensor SoC with 2790fps CMOS image sensor and 205GOPS/W vision processor. ISSCC Digest of Technical Papers, pp. 306–307.

  18. Kleihost, R. P., et al. (2001). Xetal: a low-power high performance smart camera processor. IEEE International Symposium on Circuits and Systems, 5, 215–218.

    Google Scholar 

  19. Raab, W., et al. (2003). A 100-GOPS programmable processor for vehicle vision systems. IEEE Design & Test of Computers, 20(1), 8–16. doi:10.1109/MDT.2003.1173047.

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank Dr. Kuroda of NEC Electronics Corporation, and Dr. Nishiwaki and Mr. Takahashi of NEC Corporation for their valuable inputs. The authors would also like to thank Mr. Koga of NEC Electronics Corporation for his help in designing the IMAPCAR chip, and the members of NEC Micro Systems., Ltd. for their help in the IMAPCAR chip verification and fabrication.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Shorin Kyo.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Kyo, S., Okazaki, S. IMAPCAR: A 100 GOPS In-Vehicle Vision Processor Based on 128 Ring Connected Four-Way VLIW Processing Elements. J Sign Process Syst 62, 5–16 (2011). https://doi.org/10.1007/s11265-008-0297-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-008-0297-0

Keywords

Navigation