Vision platform for mobile intelligent robot based on 81.6 GOPS object recognition processor

ABSTRACT

To enable power-efficient object recognition of mobile intelligent robots, 81.6GOPS object recognition processor is proposed. Based on analysis of Scale Invariant Feature Transform (SIFT) algorithm, architecture of the proposed processor is designed to support both task and data level parallelism. 10 Processing Elements (PEs) are integrated for task parallelism, and each PE is equipped with SIMD instruction for data parallelism as well. In addition, Visual Image Processing memory replaces complex local maximum pixel search operation with a single read operation for further performance gain. With the proposed processor, we also realized vision platform for real-time SIFT computation of mobile robots. The chip operation is tested up to 200MHz and consumes 540mW in the vision platform at 1.8V supply voltage and 100 MHz operation frequency.

REFERENCES

• 1: Sunghwan Ahn, et. al., "Data Association Using Visual Object Recognition for EKF-SLAM in Home Environment," Proceedings of IEEE Intl. Conf. on Intelligent Robots and Systems, pp. 2760--2765, 2006.
• 2: Patric Jensfelt, et. al., "Augmenting SLAM with Object Detection in a Service Robot Framework," IEEE Intl. Symposium on Robot and Human Interactive Communication, pp. 741--746, 2006.
• 3: Bertolli F., Jensfelt P., Christensen H. I., "SLAM using Visual Scan-Matching with Distinguishable 3D Points," IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4042--4047, Oct., 2006.
• 4: Zhang Nan, Li Maohai, Hong Bingrong, "Active Mobile Robot Simultaneous Localization and Mapping," IEEE International Conference on Robotics and Biomimetics, pp.1671--1681, Dec., 2006.
• 5: David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, v.60 n.2, p.91-110, November 2004 [doi>10.1023/B:VISI.0000029664.99615.94]
• 6: Bertolli F., Jensfelt P., Christensen H. I., "SLAM using Visual Scan-Matching with Distinguishable 3D Points," IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4042--4047, Oct., 2006.
• 7: Susan J. Eggers , Joel S. Emer , Henry M. Levy , Jack L. Lo , Rebecca L. Stamm , Dean M. Tullsen, Simultaneous Multithreading: A Platform for Next-Generation Processors, IEEE Micro, v.17 n.5, p.12-19, September 1997 [doi>10.1109/40.621209]
• 8: Lin C. Y., Jo P. C. and Tseng C. K., "Multi-Functional Intelligent Robot DOC-2," IEEE-RAS International Conference on Humanoid Robots, pp.530--535, Dec., 2006.
• 9: Yongguo Mei, et al., "A Case Study of Mobile Robot's Energy Consumption and Conservation Techniques," Proceedings of the IEEE Intl. Conf. of Advanced Robotics, pp. 492--497, 2005.
• 10: Shorin 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," Digest of Technical Papers, IEEE Intl. Solid-State Circuits Conf, Vol. 1, pp. 48--477, 2003.
• 11: Wolfgang Raab , Nico Bruels , Ulrich Hachmann , Jens Harnisch , Ulrich Ramacher , Christian Sauer , Axel Techmer, A 100-GOPS Programmable Processor for Vehicle Vision Systems, IEEE Design & Test, v.20 n.1, p.8-16, January 2003 [doi>10.1109/MDT.2003.1173047]
• 12: Jun Tanabe, et. al., "Visconti: Multi-VLIW Image Recognition Processor based on Configurable Processor," Proceedings of the IEEE Custom Integrated Circuits Conf., pp. 185--188, 2003.
• 13: Donghyun Kim , Kwanho Kim , Joo-Young Kim , Seung-Jin Lee , Hoi-Jun Yoo, Solutions for Real Chip Implementation Issues of NoC and Their Application to Memory-Centric NoC, Proceedings of the First International Symposium on Networks-on-Chip, p.30-39, May 07-09, 2007 [doi>10.1109/NOCS.2007.40]
• 14: Donghyun Kim, et al., "An 81.6 GOPS Object Recognition Processor Based on NoC and Visual Image Processing Memory," Proceedings of the IEEE Custom Integrated Circuits Conference, pp.443--446, Sep., 2007.
• 15: Donghyun Kim, et al., "Implementations of Memory-Centric NoC for 81.6 GOPS Object Recognition Processor," Proceedings of the IEEE Asian Solid States Circuits Conference, pp.47--50, Nov., 2007.
• 16: Kangmin Lee , Se-Joong Lee , Hoi-Jun Yoo, Low-power network-on-chip for high-performance SoC design, IEEE Transactions on Very Large Scale Integration (VLSI) Systems, v.14 n.2, p.148-160, February 2006 [doi>10.1109/TVLSI.2005.863753]
• 17: Joo-Young Kim and Hoi-Jun Yoo, "Bitwise Competition Logic for Compact Digital Comparator," Proceedings of the IEEE Asian Solid States Circuits Conference, pp.59--62, Nov., 2007.
• 18: Joo-Young Kim, Donghyun Kim, et al., "Visual Image Processing RAM for Fast 2-D Data Location Search," Proceedings of the IEEE European Solid-State Circuits Conference, pp.324--327, Sep., 2007.
• 19: Shorin 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," Digest of Technical Papers, IEEE Intl. Solid-State Circuits Conf, Vol. 1, pp. 48--477, 2003.
• 20: Wolfgang Raab , Nico Bruels , Ulrich Hachmann , Jens Harnisch , Ulrich Ramacher , Christian Sauer , Axel Techmer, A 100-GOPS Programmable Processor for Vehicle Vision Systems, IEEE Design & Test, v.20 n.1, p.8-16, January 2003 [doi>10.1109/MDT.2003.1173047]
• 21: Jun Tanabe, et. al., "Visconti: Multi-VLIW Image Recognition Processor based on Configurable Processor," Proceedings of the IEEE Custom Integrated Circuits Conf., pp. 185--188, 2003.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.3 SPECIAL-PURPOSE AND APPLICATION-BASED SYSTEMS

General Terms:
Design, Measurement, Performance, Verification

Keywords:
multi-processor SoC, network-on-chip, object recognition