Development of Image Recognition Processor Based on Configurable Processor

Takashi Miyamori; Jun Tanabe; Yasuhiro Taniguchi; Kenji Furukawa; Tatsuo Kozakaya; Hiroaki Nakai; Yukimasa Miyamoto; Ken-ichi Maeda; Masataka Matsui

doi:10.20965/jrm.2005.p0437

single-rb.php

« previous

JRM Vol.17 No.4 pp. 437-446

doi: 10.20965/jrm.2005.p0437

(2005)

Paper:

Views over last 60 days: 467

Development of Image Recognition Processor Based on Configurable Processor

Takashi Miyamori^, Jun Tanabe^, Yasuhiro Taniguchi^,
Kenji Furukawa^, Tatsuo Kozakaya^, Hiroaki Nakai^,
Yukimasa Miyamoto^*, Ken-ichi Maeda^**,
and Masataka Matsui^*

^*SoC Research & Development Center, Semiconductor Company, Toshiba Corporation, 580-1 Horikawa-cho, Saiwai-ku, Kawasaki 212-8520, Japan

^**Corporate Research & Development Center, Toshiba Corporation, 1 Komukai Toshiba-cho, Saiwai-ku, Kawasaki 212-8582, Japan

Received:

November 30, 2004

Accepted:

February 19, 2005

Published:

August 20, 2005

Keywords:

VLIW, configurable processor, image recognition, intelligent vehicle, ITS

Abstract

We developed an image recognition processor, “Visconti,” based on a configurable processor. Three VLIW processors that execute three instructions in parallel are integrated into a single chip with peripheral modules such as video I/Os and an SDRAM controller. Each VLIW processor has a RISC processor core and a VLIW coprocessor dedicated to image processing. The coprocessor executes SIMD instructions such as 8-parallel byte. Visconti was fabricated using 0.13μm CMOS technology, operates at 150MHz, and consumes about 1W. We present actual application examples of Visconti, onboard surveillance for automobiles and face recognition. Compared to cases in which only the processor core is used, execution speed per one processor increases about 16 times for onboard surveillance and about five times per three processors for face recognition. These applications can be processed in real time.

Cite this article as:

T. Miyamori, J. Tanabe, Y. Taniguchi, K. Furukawa, T. Kozakaya, H. Nakai, Y. Miyamoto, K. Maeda, and M. Matsui, “Development of Image Recognition Processor Based on Configurable Processor,” J. Robot. Mechatron., Vol.17 No.4, pp. 437-446, 2005.

Data files:

References

[1] W. Raab et al., “A 100-GOPS Programmable Processor for Vehicle Vision Systems,” IEEE Design & Test of Computers, pp. 8-15, Jan.-Feb. 2003
[2] S. Kyo et al., “A 51.2 GOPS Scalable Video Recognition Processor for Intelligent Cruise Control Based on a Linear Array of 128 4-Way VLIW Processing Elements,” IEEE International Solid-State Circuits Conference (ISSCC) digest of technical papers, pp. 48-49, 2003.
[3] T. Miyamori, “A Configurable and Extensible Media Processor,” Embedded Processor Forum, 2002.
[4] http://www.MePcore.com/
[5] A. Peleg, and U. Weiser, “MMX technology Extension to the Intel Architecture,” IEEE Micro, pp. 42-50, Aug. 1996.
[6] A. Mizuno, “Design Methodology and System for a Configurable Media Embedded Processor Extensible to VLIW Architecture,” IEEE Int. Conf. on Computer Design, pp. 2-7, Sep. 2002.
[7] J. Tanabe et al., “Visconti: Multi-VLIW Image Recognition Processor based on Configurable Processor,” Proc. of IEEE Custom Integrated Circuits Conference (CICC), pp. 185-188, 2003.
[8] Y. Kondo et al., “A 4GOPS 3Way-VLIW Image Recognition Processor Based on a Configurable Media-processor,” IEEE International Solid-State Circuits Conference (ISSCC) digest of technical papers, pp. 148-149, 2001.
[9] H. Takano et al., “A 4GOPS 3Way-VLIW Image Recognition Processor Based on a Configurable Media-processor,” IEICE Trans. Electron., Vol.E85-C, No.2, pp. 347-351, Feb. 2002.
[10] Y. Taniguchi, and K. Okamoto, “Automatic Rear and Side Surveillance System using Image Processing,” Proc. of 6th World Congress on Intelligent Transport Systems, 1999.
[11] H. Hattori, “Stereo for 2D Visual Navigation,” Proc. IEEE Intelligent Vehicles Symposium, pp. 31-38, 2000.
[12] H. Nakai et al., “A Practical Stereo Scheme for Obstacle Detection in Automotive Use,” Proc. of Int. Conf. on Pattern Recognition (ICPR), 2004.
[13] K. Furukawa et al., “Onboard Surveillance System for Automobiles Using Image Processing LSI,” IEEE Intelligent Vehicles Symposium, pp. 555-559, 2004.
[14] O. Yamaguchi, K. Fukui, and K. Maeda, “Face Recognition Using Temporal Image Sequence,” Proc. of 3rd IEEE Int. Conf. on Automatic Face and Gesture Recognition, pp. 318-323, 1998.
[15] T. Kozakaya et al., “Development of a Face Recognition System on an Image Processing LSI chip,” Proc. of CVPR Workshop on Face Processing in Video (FPIV’04), 2004.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] W. Raab et al., “A 100-GOPS Programmable Processor for Vehicle Vision Systems,” IEEE Design & Test of Computers, pp. 8-15, Jan.-Feb. 2003

[2] [2] S. Kyo et al., “A 51.2 GOPS Scalable Video Recognition Processor for Intelligent Cruise Control Based on a Linear Array of 128 4-Way VLIW Processing Elements,” IEEE International Solid-State Circuits Conference (ISSCC) digest of technical papers, pp. 48-49, 2003.

[3] [3] T. Miyamori, “A Configurable and Extensible Media Processor,” Embedded Processor Forum, 2002.

[4] [4] http://www.MePcore.com/

[5] [5] A. Peleg, and U. Weiser, “MMX technology Extension to the Intel Architecture,” IEEE Micro, pp. 42-50, Aug. 1996.

[6] [6] A. Mizuno, “Design Methodology and System for a Configurable Media Embedded Processor Extensible to VLIW Architecture,” IEEE Int. Conf. on Computer Design, pp. 2-7, Sep. 2002.

[7] [7] J. Tanabe et al., “Visconti: Multi-VLIW Image Recognition Processor based on Configurable Processor,” Proc. of IEEE Custom Integrated Circuits Conference (CICC), pp. 185-188, 2003.

[8] [8] Y. Kondo et al., “A 4GOPS 3Way-VLIW Image Recognition Processor Based on a Configurable Media-processor,” IEEE International Solid-State Circuits Conference (ISSCC) digest of technical papers, pp. 148-149, 2001.

[9] [9] H. Takano et al., “A 4GOPS 3Way-VLIW Image Recognition Processor Based on a Configurable Media-processor,” IEICE Trans. Electron., Vol.E85-C, No.2, pp. 347-351, Feb. 2002.

[10] [10] Y. Taniguchi, and K. Okamoto, “Automatic Rear and Side Surveillance System using Image Processing,” Proc. of 6th World Congress on Intelligent Transport Systems, 1999.

[11] [11] H. Hattori, “Stereo for 2D Visual Navigation,” Proc. IEEE Intelligent Vehicles Symposium, pp. 31-38, 2000.

[12] [12] H. Nakai et al., “A Practical Stereo Scheme for Obstacle Detection in Automotive Use,” Proc. of Int. Conf. on Pattern Recognition (ICPR), 2004.

[13] [13] K. Furukawa et al., “Onboard Surveillance System for Automobiles Using Image Processing LSI,” IEEE Intelligent Vehicles Symposium, pp. 555-559, 2004.

[14] [14] O. Yamaguchi, K. Fukui, and K. Maeda, “Face Recognition Using Temporal Image Sequence,” Proc. of 3rd IEEE Int. Conf. on Automatic Face and Gesture Recognition, pp. 318-323, 1998.

[15] [15] T. Kozakaya et al., “Development of a Face Recognition System on an Image Processing LSI chip,” Proc. of CVPR Workshop on Face Processing in Video (FPIV’04), 2004.

Development of Image Recognition Processor Based on Configurable Processor

Takashi Miyamori*, Jun Tanabe*, Yasuhiro Taniguchi**, Kenji Furukawa**, Tatsuo Kozakaya**, Hiroaki Nakai**, Yukimasa Miyamoto*, Ken-ichi Maeda**, and Masataka Matsui*

Takashi Miyamori^, Jun Tanabe^, Yasuhiro Taniguchi^,
Kenji Furukawa^, Tatsuo Kozakaya^, Hiroaki Nakai^,
Yukimasa Miyamoto^*, Ken-ichi Maeda^**,
and Masataka Matsui^*