The Representation Space Paradigm of Concurrent Evolving Object Descriptions

A representation paradigm for instantiating and refining multiple, concurrent descriptions of an object from a sequence of imagery is presented. It is designed for the perception system of an autonomous robot that needs to describe many types of objects, initially detects objects at a distance and gradually acquires higher resolution data, and continuously collects sensory input. Since the data change significantly over time, the paradigm supports the evolution of descriptions, progressing from crude 2-D 'blob' descriptions to complete semantic models. To control this accumulation of new descriptions, the authors introduce the idea of representation space, a lattice of representations that specifies the order in which they should be considered for describing an object. A system, TraX, that constructs and refines models of outdoor objects detected in sequences of range data is described. >

[1]  Thomas O. Binford,et al.  Ignorance, myopia, and naiveté in computer vision systems , 1991, CVGIP Image Underst..

[2]  Robert C. Bolles,et al.  Generalizing Epipolar-Plane Image Analysis on the spatiotemporal surface , 2004, International Journal of Computer Vision.

[3]  Thomas O. Binford,et al.  Computer Description of Curved Objects , 1973, IEEE Transactions on Computers.

[4]  Peter Cheeseman,et al.  A stochastic map for uncertain spatial relationships , 1988 .

[5]  Rodney A. Brooks,et al.  Symbolic Reasoning Among 3-D Models and 2-D Images , 1981, Artif. Intell..

[6]  Olivier D. Faugeras,et al.  Maintaining representations of the environment of a mobile robot , 1988, IEEE Trans. Robotics Autom..

[7]  Ann Patricia Fothergill,et al.  Forming Models Of Plane-And-Cylinder Faceled Bodies From Light Stripes , 1975, IJCAI.

[8]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[9]  Alex Pentland,et al.  Learning and recognition in natural environments , 1989 .

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

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

[12]  Takeo Kanade,et al.  The cycle of uncertainty and constraint in robot perception , 1988 .

[13]  Yoshiaki Shirai,et al.  A scene description method using three-dimensional information , 1979, Pattern Recognit..

[14]  Andrew P. Witkin,et al.  Scale-space filtering: A new approach to multi-scale description , 1984, ICASSP.

[15]  Robert C. Bolles,et al.  Perceptual Organization and the Curve Partitioning Problem , 1983, IJCAI.

[16]  H. Keith Nishihara,et al.  Intensity, Visible-Surface, and Volumetric Representations , 1981, Artif. Intell..

[17]  James L. Crowley.  World modeling and position estimation for a mobile robot using ultrasonic ranging , 1989, Proceedings, 1989 International Conference on Robotics and Automation.