Informative Views and Sequential Recognition Informative Views and Sequential Recognition

In this paper we introduce a method for distinguishing between informative and un-informative viewpoints as they pertain to an active observer seeking to identify an object in a known environment. The method is based on a generalized inverse theory using a probabilistic framework where assertions are represented by conditional probability density functions. Consequently, the method also permits the assessment of the beliefs associated with a set of assertions based on data acquired from a particular viewpoint. The importance of this result is that it provides a basis by which an external agent can assess the quality of the information from a particular viewpoint, and make informed decisions as to what action to take using the data at hand. To illustrate the theory we show how the characteristics of belief distributions can be exploited in a model-based recognition problem, where the task is to identify an unknown model from a database of known objects on the basis of parameter estimates. This leads to a sequential recognition strategy in which evidence is accumulated over successive viewpoints (at the level of the belief distribution) until a deenitive assertion can be made. Experimental results are presented showing how the resulting algorithms can be used to distinguish between informative and unin-formative viewpoints, rank a sequence of images on the basis of their information (e.g. to generate a set of characteristic views), and sequentially identify an unknown object. 1 R esum e Dans cet article, nous pr'esentons une m'ethode qui permet de distinguer les points de vue informatifs et non-informatifs d'un objet tels que perr cus par un observateur actif qui cherche a identiier un objet dans un environnement connu. La m'ethode repose sur une g en eralisation de la th eorie inverse utlis ee en proba-bilit e o u les hypoth eses sont repr esent es par des fonctions de densit e de probabilit e. Cons equemment, la m ethode permet aussi l'estimation de la connance associ ee a un ensemble d'hypoth eses bas es sur les donn ees obtenues d'un certain point de vue. L'importance de ce r esultat est qu'il procure une base par laquelle un agent externe peut estimer la qualit e de l'information provenant d'un point de vue et en cons equence prendre une d ecision eclair ee quant a l'action a r ealiser. Pour illustrer la th eorie, nous montrons comment les caract eristiques des fonctions de distribution de la …

[1]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

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

[3]  A. Tarantola.  Inverse problem theory : methods for data fitting and model parameter estimation , 1987 .

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

[5]  D. Kriegman,et al.  Computing exact aspect graphs of curved objects: Solids of revolution , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[6]  R. Jain,et al.  Generating aspect graphs for curved objects , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[7]  D. Eggert,et al.  Computing the orthographic projection aspect graph of solids of revolution , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[8]  Kevin W. Bowyer,et al.  Aspect graphs: An introduction and survey of recent results , 1990, Int. J. Imaging Syst. Technol..

[9]  Alex Pentland,et al.  Segmentation by minimal description , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[10]  Alex Pentland,et al.  Closed-form solutions for physically-based shape modeling and recognition , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Frank P. Ferrie,et al.  From Uncertainty to Visual Exploration , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Dmitry B. Goldgof,et al.  The scale space aspect graph , 1992, CVPR.

[13]  Anil K. Jain,et al.  Recognizing geons from superquadrics fitted to range data , 1992, Image Vis. Comput..

[14]  Frank P. Ferrie,et al.  Partitioning range images using curvature and scale , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Frank P. Ferrie,et al.  Model building and autonomous exploration , 1993, Other Conferences.

[16]  David Paul Casasent.  Intelligent Robots and Computer Vision XII: Active Vision and 3D Methods , 1993 .

[17]  Frank P. Ferrie,et al.  Active exploration: Knowing when we're wrong , 1993, 1993 (4th) International Conference on Computer Vision.

[18]  Frank P. Ferrie,et al.  Darboux Frames, Snakes, and Super-Quadrics: Geometry from the Bottom Up , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Jake K. Aggarwal,et al.  Model-based object recognition in dense-range images—a review , 1993, CSUR.

[20]  Frank P. Ferrie,et al.  Recognizing volumetric objects in the presence of uncertainty , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[21]  F. Ferrie,et al.  Informative Views and Active Recognition , 1994 .

[22]  Frank P. Ferrie,et al.  Autonomous exploration: driven by uncertainty , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[23]  David B. Cooper,et al.  Describing Complicated Objects , 1994 .

[24]  David B. Cooper,et al.  Practical Reliable Bayesian Recognition of 2D and 3D Objects Using Implicit Polynomials and Algebraic Invariants , 1996, IEEE Trans. Pattern Anal. Mach. Intell..