The Transactions of the Korean Institute of Electrical Engineers D (대한전기학회논문지:시스템및제어부문D)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Neural Network Approach to Sensor Fusion System for Improving the Recognition Performance of 3D Objects

3차원 물체의 인식 성능 향상을 위한 감각 융합 신경망 시스템

  • 동성수 (용인대학교 디지털전자정보과) ;
  • 이종호 (인하대 공대 정보통신공학부) ;
  • 김지경 (인하대 공대 정보통신대학원)
  • Published : 2005.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

Human being recognizes the physical world by integrating a great variety of sensory inputs, the information acquired by their own action, and their knowledge of the world using hierarchically parallel-distributed mechanism. In this paper, authors propose the sensor fusion system that can recognize multiple 3D objects from 2D projection images and tactile informations. The proposed system focuses on improving recognition performance of 3D objects. Unlike the conventional object recognition system that uses image sensor alone, the proposed method uses tactual sensors in addition to visual sensor. Neural network is used to fuse the two sensory signals. Tactual signals are obtained from the reaction force of the pressure sensors at the fingertips when unknown objects are grasped by four-fingered robot hand. The experiment evaluates the recognition rate and the number of learning iterations of various objects. The merits of the proposed systems are not only the high performance of the learning ability but also the reliability of the system with tactual information for recognizing various objects even though the visual sensory signals get defects. The experimental results show that the proposed system can improve recognition rate and reduce teeming time. These results verify the effectiveness of the proposed sensor fusion system as recognition scheme for 3D objects.

Keywords

References

  1. Tae-Woo Lee, Chang-Ik Jun, 'A Study on the Pattern Recognition of EMG Signals for Head Motion Recognition', Trans. KIEE, Vol.49D, No.2, pp.103-110, JUL.2004
  2. In-Seok Cho, Jin-Hyun Park, 'A Study on Dynamic Hand Gesture Recognition Using Neural Networks', Trans. KIEE, Vol.53D, No.1, pp.22-31, JAN.2004
  3. Young-Jae Ryoo, Eui-Sun Kim, 'Recognition of Road Direction for Magnetic Sensor Based Autonomous Vehicle', Trans. KIEE, Vol.52D, No.9, pp.526-532, SEP.2003
  4. Ho-Seon Choi, Won-Kyu Jang, 'Snorer-Dependent Snore Recognition Using LPC Cepstral Coefficients', Trans. KIEE, Vol.52D, No.9, pp.554-559, SEP.2003
  5. In-Mo Ahn, Kee-Sang Lee, 'Recognition of Patterns and Marks on the Glass Panel of Computer Monitor', Trans. KIEE, Vol.52D, No.9, pp.35-41, SEP.2003
  6. Young-No Kim, Jae-Chul Kim, 'The Detection of Partial Discharge Signal by the Measurement of an Electromagnetic Wave and Pattern Recognition Technique', Trans. KIEE, Vol.51A, No.6, pp.276-283,2002
  7. Bongkyu Lee, Yohan Yang, 'An Implementation of Generalized Second-Order Neural Networks for Pattern Recognition', Trans. KIEE, Vol.51D, No.10, pp.446-452, OCT.2002
  8. Hyun-Chul Cho, Keeseong Lee, 'The 3-D Underwater Object Recognition Using Neural Networks and Ultrasonic Sensor Fabricated with 1-3 Type Piezoelectric Composites', Trans. KIEE, Vol.50C, No.7, pp.324-328, JUL.2001
  9. Sung-Soo Kim, 'Pulse Code Signal Recognition using Integra-Normalizer', Trans. KIEE, Vol.49D, N0.8, pp.491-494, AUG.2000
  10. Chung-Soo Lim, Chong-Ho Lee, 'Neural Network Design for Spatio-temporal Pattern Recognition', Trans. KIEE, Vol.49D, No.7, pp.1464-1471, JUL.1999
  11. Y. Sato, S.Tamamura, '3D object recognition using parameterized model', Trans. Inf. Soc. Japan, vol. 31, pp. 56-67, 1990
  12. S. Yamane, M. Izumi, K. Fukunaga, 'Modelbased object position and orientation prediction', Trans. IEICE, vol. J79-D-II,pp. 165-173, 1996
  13. H. Murase, SK. Nayar, '3D object recognition from appearance', Trans. IEEE, vol. J77-D-D, pp.2179-2187, 1994
  14. T. Amano, S. Hiura, A. Yamaguchi, 'Eigen space approach for pose detection with range images', Trans. IEICE, vol. J80-D-II, pp. 1136-1143, 1997
  15. AY. Cheng, DS. Yeung, 'Sensitivity analysis of neocognitron', Trans. IEEE, Syst. Man. Cybern., vol. 29, pp. 238-249, August 1999 https://doi.org/10.1109/5326.760568
  16. S. Sato, J. Kuroiwa, H. Aso, S. Miyake, 'A rotation invariant neocognitron', Trans. IEICE, vol. J81-D-II, pp.1365-1374, 1998
  17. Wen-han Quain, Hong Quio, S.K. Tso, 'Synthesizing two-fingered grippers for positioning and identifying objects', Trans. IEEE, Syst. Man. Cybern., vol. 31, pp. 602-614, 2001 https://doi.org/10.1109/3477.938263
  18. Makoto Kaneko, Tatsuya Shirai, Toshio Tsuji, 'Scale-Dependent grasp', Trans. IEEE, Syst. Man. Cybem., vol. 30, pp.806-816, November 2000 https://doi.org/10.1109/3468.895903
  19. R. Murphy, 'Biological and cognitive foundations of intelligent sensor fusion', Trans. IEEE, Syst. Man. Cybern., vol. 26, pp. 42-51, January 1996 https://doi.org/10.1109/3468.477859
  20. R. Murphy, 'Dempster-shafter theory for sensor fusion in autonomous mobile robot', Trans. IEEE, Robot. Automat., vol. 14, pp. 197-206, April 1999 https://doi.org/10.1109/70.681240
  21. Haykin, Neural Networks, Prentice Hall, 1999
  22. DI. Perrett, MV. Ormam, E. Ashbridge, 'An account of generalization of recognition with mental transformations', Cognition, vol. 67, pp.111-145, 1998 https://doi.org/10.1016/S0010-0277(98)00015-8