Distance Images and Intermediate-Level Vision

Early vision is dominated by image patches or features derived from them; high-level vision is dominated by shape representation and recognition. However there is almost no work between these two levels, which creates a problem when trying to recognize complex categories such as "airports" for which natural feature clusters are ineffective. We argue that an intermediate-level representation is necessary and that it should incorporate certain high-level notions of distance and geometric arrangement into a form derivable from images. We propose an algorithm based on a reaction-diffusion equation that meets these criteria; we prove that it reveals (global) aspects of the distance map locally; and illustrate its performance on airport and other imagery, including visual illusions.

[1]  Cordelia Schmid,et al.  Bandit Algorithms for Tree Search , 2007, UAI.

[2]  Shimon Ullman,et al.  Visual Classification by a Hierarchy of Extended Fragments , 2006, Toward Category-Level Object Recognition.

[3]  D. Kersten,et al.  The representation of perceived angular size in human primary visual cortex , 2006, Nature Neuroscience.

[4]  Sanja Fidler,et al.  Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Andrew Zisserman,et al.  Learning an Alphabet of Shape and Appearance for Multi-Class Object Detection , 2008, International Journal of Computer Vision.

[6]  Axel Pinz,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[7]  Shimon Ullman,et al.  Combined Top-Down/Bottom-Up Segmentation , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  J. Koenderink.  The structure of images , 2004, Biological Cybernetics.

[9]  Max A. Viergever,et al.  The Gaussian scale-space paradigm and the multiscale local jet , 1996, International Journal of Computer Vision.

[10]  Ali Shokoufandeh,et al.  Shock Graphs and Shape Matching , 1998, International Journal of Computer Vision.

[11]  Cordelia Schmid,et al.  Toward Category-Level Object Recognition , 2006, Toward Category-Level Object Recognition.

[12]  Andrew Zisserman,et al.  A Boundary-Fragment-Model for Object Detection , 2006, ECCV.

[13]  Ann B. Lee,et al.  Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[14]  R. Courant,et al.  Methods of Mathematical Physics , 1962 .

[15]  Pavel Dimitrov,et al.  A constant production hypothesis guides leaf venation patterning. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[16]  John P. McDermott,et al.  Rule-Based Interpretation of Aerial Imagery , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[18]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.