Segmentation between overlapping parts: the moving shadows approach

A method for segmenting three-dimensional overlapping surfaces is presented that is based on moving a light source in a horizontal plane relative to the surfaces to be segmented. Using a camera that is placed above the surfaces. The shadows cast by the surfaces at each light source angle are recorded and analyzed. The segmentation algorithm is simple and based on Boolean processing of the data. A set of experimental results demonstrates the robustness and usefulness of the method. >

[1]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[3]  Richard A. Volz,et al.  Recognizing partially hidden objects , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[4]  C. S. George Lee,et al.  Computer Recognition of Two Overlapping Parts Using a Single Camera , 1985, Computer.

[5]  R.B. Kelley,et al.  Three vision algorithms for acquiring workpieces from bins , 1983, Proceedings of the IEEE.