Physics-Based Segmentation : Looking Beyond Color

We previously presented a framework for segmentation of complex scenes using multiple physical hypotheses for simple image regions. A consequence of that framework was a proposal for a new approach to the segmentation of complex scenes into regions corresponding to coherent surfaces rather than merely regions of similar color. Herein we present an implementation of this new approach and show example segmentations for scenes containing multicolored piece-wise uniform objects. By using this new approach we are able to intelligently senwent scenes with objects of greater complexity than previous physics-based segmentation algorithms. The results show that by using general physical models we can obtain segmentations that correspond more closely to objects in the scene than segmentations found using only color. Figure 1 Complex scene containing multiple materials and multi-colored objects

[1]  Wallace S. Rutkowski,et al.  TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2022 .

[2]  Steven A. Shafer,et al.  Using color to separate reflection components , 1985 .

[3]  Mubarak Shah,et al.  Analysis of shape from shading techniques , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Michael J. Brooks,et al.  Shape and Source from Shading , 1985, IJCAI.

[5]  Steven M. LaValle,et al.  A Bayesian Segmentation Methodology for Parametric Image Models , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Steven K. Feiner,et al.  Computer Graphics - Principles and Practice, 3rd Edition , 1990 .

[7]  Steven W. Zucker,et al.  Shading Flows and Scenel Bundles: A New Approach to Shape from Shading , 1992, ECCV.

[8]  Glenn Healey,et al.  Using color for geometry-insensitive segmentation , 1989 .

[9]  M H Brill,et al.  Image segmentation by object color: a unifying framework and connection to color constancy. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[10]  Steven A. Shafer,et al.  Physics-based segmentation: moving beyond color , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  H. Barrow,et al.  Scene modeling: a structural basis for image description , 1980 .

[12]  Alex Pentland,et al.  A simple algorithm for shape from shading , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Lawrence L. Lapin Probability and Statistics for Modern Engineering , 1983 .

[14]  Rama Chellappa,et al.  Estimation of illuminant direction, albedo, and shape from shading , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Glenn Healey,et al.  Results using random field models for the segmentation of color images of natural scenes , 1995, Proceedings of IEEE International Conference on Computer Vision.

[16]  Steven A. Shafer,et al.  A framework for segmentation using physical models of image formation , 1993, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Thomas Ertl,et al.  Computer Graphics - Principles and Practice, 3rd Edition , 2014 .