Distance images and intermediate-level vision

Authors:
Pavel Dimitrov;Matthew Lawlor;Steven W. Zucker
Affiliations:
Computer Science and Applied Mathematics, Yale University, New Haven, CT;Computer Science and Applied Mathematics, Yale University, New Haven, CT;Computer Science and Applied Mathematics, Yale University, New Haven, CT
Venue:
SSVM'11 Proceedings of the Third international conference on Scale Space and Variational Methods in Computer Vision
Year:
2011

Citing 9
Cited 1

The Gaussian scale-space paradigm and the multiscale local jet

International Journal of Computer Vision
Shock Graphs and Shape Matching

International Journal of Computer Vision
Laplacian Eigenmaps for dimensionality reduction and data representation

Neural Computation
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Learning an Alphabet of Shape and Appearance for Multi-Class Object Detection

International Journal of Computer Vision
Combined Top-Down/Bottom-Up Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
From Images to Shape Models for Object Detection

International Journal of Computer Vision
Rule-Based Interpretation of Aerial Imagery

IEEE Transactions on Pattern Analysis and Machine Intelligence
A boundary-fragment-model for object detection

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II

From a Non-Local Ambrosio-Tortorelli Phase Field to a Randomized Part Hierarchy Tree

Journal of Mathematical Imaging and Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.