On Computing Visual Flows with Boundaries: The Case of Shading and Edges

Authors:
Ohad Ben-Shahar;Patrick S. Huggins;Steven W. Zucker
Affiliations:
-;-;-
Venue:
BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Year:
2002

Citing 9
Cited 2

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Analyzing oriented patterns

Computer Vision, Graphics, and Image Processing
Trace Inference, Curvature Consistency, and Curve Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Computerized Flow Field Analysis: Oriented Texture Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Diffusion of General Data on Non-Flat Manifolds viaHarmonic Maps Theory: The Direction Diffusion Case

International Journal of Computer Vision
Logical/Linear Operators for Image Curves

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Perceptual Organization of Texture Flow: A Contextual Inference Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shadows and shading flow fields

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Orientation diffusions

IEEE Transactions on Image Processing

Hue geometry and horizontal connections

Neural Networks - 2004 Special issue Vision and brain
Smooth Gradient Representations as a Unifying Account of Chevreul's Illusion, Mach Bands, and a Variant of the Ehrenstein Disk

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many visual tasks depend upon the interpretation of visual structures that are flow fields, such as optical flow, oriented texture, and shading. The computation of these visual flows involves a delicate tradeoff: imaging imperfections lead to noisy and sparse initial flow measurements, necessitating further processing to infer dense coherent flows; this processing typically entails interpolation and smoothing, both of which are prone to destroy visual flow discontinuities. However, discontinuities in visual flows signal corresponding discontinuities in the physical world, thus it is critical to preserve them while processing the flow. In this paper we present a computational approach motivated by the architecture of primary visual cortex that directly incorporates boundary information into a flow relaxation network. The result is a robust computation of visual flows with the capacity to handle noisy or sparse data sets while providing stability along flow boundaries. We demonstrate the effectiveness of our approach by computing shading flows in images with intensity edges.