Representation and segmentation of a cluttered scene using fused edge and surface data

An intermediate representation based on combined edge and surface data is proposed to support the recognition of objects in cluttered scenes. The representation is based on the premise that local structure of surface and edge (wings) can be reliably sensed without higher-level models, while global edge, surface, and part structures cannot be. A sensing system for indoor scenes is discussed which allows fusion of an intensity image and an image where depth is coded using structured light. Surface patches are detected and coarsely typed according to only the 2D structure in the stripped image together with global knowledge of the stripe projection, while edges are detected from intensity gradients or boundaries of stripe patches. A set of rules is given for describing the 3D structure corresponding to each wing constructed in the intermediate scene representation. An extended set of rules is proposed for partitioning the set of sensed wings into subsets corresponding to solid-object parts. Reasonable results are reported when these rules are applied to several complex scenes.<<ETX>>

[1]  Jean Ponce,et al.  Toward a surface primal sketch , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[2]  Drew McDermott,et al.  Introduction to artificial intelligence , 1986, Addison-Wesley series in computer science.

[3]  Raimund Seidel,et al.  Efficiently Computing And Representing Aspect Graphs Of Polyhedral Objects , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[4]  J. Gibson.  The perception of the visual world , 1951 .

[5]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[6]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.

[7]  Anil K. Jain,et al.  Surface classification: hypothesis testing and parameter estimation , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Amar Mitiche,et al.  3-D Object Representation from Range Data Using Intrinsic Surface Properties , 1987 .

[9]  Charles R. Dyer,et al.  3-D multiview object representations for model-based object recognition , 1987, Pattern Recognit..

[10]  Leslie G. Ungerleider,et al.  Object vision and spatial vision: two cortical pathways , 1983, Trends in Neurosciences.

[11]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[12]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[13]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[14]  George C. Stockman,et al.  Object recognition and localization via pose clustering , 1987, Comput. Vis. Graph. Image Process..

[15]  Ramesh C. Jain,et al.  Invariant surface characteristics for 3D object recognition in range images , 1985, Comput. Vis. Graph. Image Process..

[16]  M. Livingstone.  Art, illusion and the visual system. , 1988, Scientific American.

[17]  A. Pentland.  Recognition by Parts , 1987 .

[18]  Thomas O. Binford,et al.  Inferring Surfaces from Images , 1981, Artif. Intell..

[19]  Murray H. Loew,et al.  The Entry-Exit Method of Shadow Boundary Segmentation , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  M. B. Clowes,et al.  On Seeing Things , 1971, Artif. Intell..

[21]  Frank P. Ferrie,et al.  Deriving course 3D models of objects , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Gongzhu Hu,et al.  3-D Surface Solution Using Structured Light and Constraint Propagation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[24]  J. K. Aggarwal,et al.  SHAPE RECOGNITION FROM SINGLE SILHOUETTES. , 1987 .

[25]  Alex Pentland,et al.  Part Segmentation for Object Recognition , 1989, Neural Computation.

[26]  Gongzhu Hu.  Three-dimensional scene representation using structured light , 1988 .

[27]  R. Bajcsy,et al.  Three dimensional object representation revisited , 1987 .