3-D Object Recognition Based on Integration of Range Image and Gray-scale Image

In this paper, we propose a practical object recognition system which consists of two functional modules. The first is object extraction module using a range image, and the second is a precise position measurement module using a grayscale intensity image. Both high-reliability and high-accuracy can be achieved by effective image integration. We also propose an idea of stereo vision with random-dot pattern projection as an effective way to obtain a range image. This method enables reliable stereo matching, even for objects with no texture. Through an experiment with real images, we have demonstrated that our system has 99.8% recognition reliability and processing time is approximately 5 seconds per image; as a result, the system can be applied to practical industrial robot vision.

[1]  S. Inokuchi,et al.  Three-dimensional surface measurement by space encoding range imaging , 1985 .

[2]  T. Yada,et al.  Miniature optical scanning range sensor utilizing a silicon micromachined scanner , 1997, Proceedings of International Solid State Sensors and Actuators Conference (Transducers '97).

[3]  Shinjiro Kawato,et al.  High-speed template matching algorithm using contour information , 1992, Electronic Imaging.

[4]  Andreas F. Koschan,et al.  Color stereo vision using hierarchical block matching and active color illumination , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5]  Paul P. L. Regtien,et al.  Multi-sensor recognition of electronic components , 2001, Machine Vision and Applications.

[6]  Mark R. Stevens,et al.  Localized Scene Interpretation from 3D Models, Range, and Optical Data , 2000, Comput. Vis. Image Underst..

[7]  Katsushi Ikeuchi,et al.  Sensor Modeling, Probabilistic Hypothesis Generation, and Robust Localization for Object Recognition , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Jake K. Aggarwal,et al.  Experiments in Intensity Guided Range Sensing Recognition of Three-Dimensional Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Anil K. Jain,et al.  BONSAI: 3D Object Recognition Using Constrained Search , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Takeo Kanade,et al.  A multibaseline stereo system with active illumination and real-time image acquisition , 1995, Proceedings of IEEE International Conference on Computer Vision.

[11]  Gang Xu,et al.  A Region-Based Stereo Algorithm , 1989, IJCAI.

[12]  Hiroshi Murase,et al.  Appearance matching of occluded objects using coarse-to-fine adaptive masks , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  K. Ikushima,et al.  3D shape recognition by distributed sensing of range images and intensity images , 1997, Proceedings of International Conference on Robotics and Automation.

[14]  David G. Lowe,et al.  Visual Recognition from Spatial Correspondence and Perceptual Organization , 1985, IJCAI.

[15]  Robert C. Bolles,et al.  3DPO: A Three- Dimensional Part Orientation System , 1986, IJCAI.

[16]  Manabu Hashimoto,et al.  Vision System for Depalletizing Robot Using Genetic Labeling , 1995, IEICE Trans. Inf. Syst..