Journal of the Korean Society for Precision Engineering (한국정밀공학회지)

Korean Society for Precision Engineering (한국정밀공학회)
권호 표지
DOI QR코드

DOI QR Code

Object Recognition Method for Industrial Intelligent Robot

산업용 지능형 로봇의 물체 인식 방법

  • Kim, Kye Kyung (Department of Intelligent Cognitive Technology, Electronics and Telecommunications Research Institute) ;
  • Kang, Sang Seung (Department of Intelligent Cognitive Technology, Electronics and Telecommunications Research Institute) ;
  • Kim, Joong Bae (Department of Intelligent Cognitive Technology, Electronics and Telecommunications Research Institute) ;
  • Lee, Jae Yeon (Department of Intelligent Cognitive Technology, Electronics and Telecommunications Research Institute) ;
  • Do, Hyun Min (Department of Robotics and Mechatronics, Korea Institute of Machinery and Materials) ;
  • Choi, Taeyong (Department of Robotics and Mechatronics, Korea Institute of Machinery and Materials) ;
  • Kyung, Jin Ho (Department of Robotics and Mechatronics, Korea Institute of Machinery and Materials)
  • 김계경 (한국전자통신연구원 지능형인지기술연구부) ;
  • 강상승 (한국전자통신연구원 지능형인지기술연구부) ;
  • 김중배 (한국전자통신연구원 지능형인지기술연구부) ;
  • 이재연 (한국전자통신연구원 지능형인지기술연구부) ;
  • 도현민 (한국기계연구원 로봇메카트로닉스연구실) ;
  • 최태용 (한국기계연구원 로봇메카트로닉스연구실) ;
  • 경진호 (한국기계연구원 로봇메카트로닉스연구실)
  • Received : 2013.07.10
  • Accepted : 2013.08.12
  • Published : 2013.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

The introduction of industrial intelligent robot using vision sensor has been interested in automated factory. 2D and 3D vision sensors have used to recognize object and to estimate object pose, which is for packaging parts onto a complete whole. But it is not trivial task due to illumination and various types of objects. Object image has distorted due to illumination that has caused low reliability in recognition. In this paper, recognition method of complex shape object has been proposed. An accurate object region has detected from combined binary image, which has achieved using DoG filter and local adaptive binarization. The object has recognized using neural network, which is trained with sub-divided object class according to object type and rotation angle. Predefined shape model of object and maximal slope have used to estimate the pose of object. The performance has evaluated on ETRI database and recognition rate of 96% has obtained.

Keywords

References

  1. Lee, D. H., Bae, S. G., Seo, D. H., Kang, H. S., and Bae, J. M., "Development of an HTM Network Training System for Recognition of Molding Parts," Journal of Korea Multimedia Society, Vol. 13, No 11, pp. 1643-1656, 2010.
  2. Lee, S. H., Seo, M. H., and Jung, T. C., "Development of Automatic Nut Inspection System using Image Processing," Journal of Korea Information Processing Society A, Vol. 11-A, No. 4, pp. 235-242, 2004. https://doi.org/10.3745/KIPSTA.2004.11A.4.235
  3. Kim, J. Y. and Cho, H. S., "Design of a visual sensing system for flexible parts assembly," Korean Journal of Optics and Photonics, Vol. 13, No. 4, pp. 283-288, 2002. https://doi.org/10.3807/KJOP.2002.13.4.283
  4. Lee, W. H., Cho, S. H., Seol, K. H., Ju, D. H., and Kim, D. Y., "A Study on Watershed Region Extraction Based on Edge Information," IPIU, The institute of Electronics Engineering of Korea, pp. 449-452, 2003.
  5. Lee, J. Y., Kim, S. Y., and Ko, K. S., "Recognition of partially occluded object using property of vector on the boundary segments," Signal Processing, The institute of Electronics Engineering of Korea, Vol. 6, No. 1, pp. 371-374, 1993.
  6. Ha, S. S., Park, S. B., Lee, B. H., Han, Y. J., and Han, H. S., "The development on a recognition system of assembly parts using a hardware independent image module," The institute of Electronics Engineering of Korea, Vol. 29, No. 1, pp. 969-970, 2006.
  7. Bae, S. G., Lee, D. H., Cho, G. H., Nam, H. B., Sung, G. Y., Bae, J. M., and Kang, H. S., "Development of an HTM-Based Parts Image Recognition System for Small Scale Manufacturing Industry," Journal of Korea Information Processing Society D, Vol. 16-D, No. 4, pp. 613-620, 2009. https://doi.org/10.3745/KIPSTD.2009.16-D.4.613
  8. Oh, J. K., Lee, S. H., and Lee, C. H., "Stereo Vision Based Automation for a Bin-Picking Solution," International Journal of Control, Automation, and Systems, Vol. 10, No. 2, pp. 362-373, 2012. https://doi.org/10.1007/s12555-012-0216-9
  9. Kazuya, O., Toshihiro, H., Masakazu, F., Nobuhiro, S., and Mitsuharu, S., "Development for Industrial Robotics Applications," IHI Engineering review, Vol. 42, No. 2, pp. 103-107, 2009.
  10. Rahardja, K. and Kosaka, A., "Vision-based binpicking: Recognition and localization of multiple complex objects using simple visual cues," Proc. of IEEE International Conference on Intelligent Robots and System, Vol. 3, pp. 1448-1457, 1996.
  11. Belongie, S., Malik, J., and Puzicha, J., "Shape matching and object recognition using shape contexts," IEEE Trans. on Pattern Anal. Mach. Intel., Vol. 24, No. 24, pp. 509-522, 2004.
  12. Lu, C., Adluru, N., Ling, H., Zhu, G., and Latecki, L. J., "Contour based object detection using part bundle," Journal of Computer Vision and Image Understanding, Vol. 114, No. 7, pp. 827-834, 2010. https://doi.org/10.1016/j.cviu.2010.03.009
  13. Ferrari, V., Fevrier, L., Jurie, F., and Schmid, C., "Groups of adjacent contour segments for object detection," IEEE Trans. on Pattern Anal. Mach. Intel., Vol. 30, No. 1, pp. 36-51, 2008. https://doi.org/10.1109/TPAMI.2007.1144
  14. Felzenszwalb, P. F. and Schwartz, J., "Hierarchical matching of deformable shapes," Computer Vision and Pattern Recognition, pp. 1-8, 2007.
  15. Lee, D. and Nixon, M. S., "Vision-based finger action recognition by angle detection and contour analysis," ETRI Journal, Vol. 33, No. 3, pp. 415-422, 2011. https://doi.org/10.4218/etrij.11.0110.0313
  16. Ferrari, V., Jurie, F., and Schmid, C., "Accurate object detection with deformable shape models learnt from images," Computer Vision and Pattern Recognition, pp. 1-8, 2007.
  17. Felzenszwalb, P., "Representation and detection of deformable shapes," PAMI, Vol. 27, No. 2, pp. 208- 220, 2005. https://doi.org/10.1109/TPAMI.2005.35
  18. Martin, D., Fowlkes, C., and Malik, J., "Learning to detect natural image boundaries using local brightness, color, and texture cues," PAMI, Vol. 26, No. 5, pp. 530-549, 2004. https://doi.org/10.1109/TPAMI.2004.1273918
  19. Ueda, N. and Suzuki, S., "Learning visual models from shape contours using multiscale convex/concave structure matching," PAMI, Vol. 15, No. 4, pp. 337- 352, 1993. https://doi.org/10.1109/34.206954
  20. Shafait, F., Keysers, D., and Breuel, T. M., "Efficient implementation of local adaptive thresholding techniques using integral images," Proc. of Efficient implementation of local adaptive thresholding techniques using integral images, Vol. 6815, pp. 10- 16, 2008.
  21. Kosko, B., "Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence," Prentice-Hall International, pp. 197-211, 1992.

Cited by

  1. Output Characteristic of a Flexible Tactile Sensor Manufactured by 3D Printing Technique vol.31, pp.2, 2014, https://doi.org/10.7736/KSPE.2014.31.2.149
  2. A Method for Rear-side Vehicle Detection and Tracking with Vision System vol.31, pp.3, 2014, https://doi.org/10.7736/KSPE.2014.31.3.233
  3. Evaluation of Robot Vision Control Scheme Based on EKF Method for Slender Bar Placement in the Appearance of Obstacles vol.32, pp.5, 2015, https://doi.org/10.7736/KSPE.2015.32.5.471