Computer vision publications

A new formulation of shape from shading is presented in which surface orientation is related to image irradiance without requiring detailed knowledge of the scene illumination, or of the albedo…

Two constructive methods are presented: the first finds the orientation of parallel lines and planes and the second determines the orientation of plans by `backprojection’ of two intrinsic properties of…

Local analysis of image shading, in the absence of prior knowledge about the viewed scene, may be used to provide information about the scene.

We broadly define computational stereo as the recovery of the three-dimensional characteristics of a scene from multiple images taken from different points of view.

We describe a solution for an important special case: the interpolation of surfaces that are locally spherical or cylindrical from initial orientation values and constraints on orientation.

In this paper a structural approach to modeling is argued for that explicitly relates image appearance to the scene characteristics from which it arose.

The importance of human vision is a major motivation for the intense interest in and significant research effort devoted to machine vision.

We suggest that an appropriate role of early visual processing is to describe a scene in terms of intrinsic characteristics – such as range, orientation, reflectance, and incident illumination –…

This report describes a new procedure for tracking road segments and finding potential vehicles in imagery of approximately 1 to 3 feet per pixel ground resolution.

MSYS is a system for reasoning with uncertain information and inexact rules of inference. Its major application, to date, has been to the interpretation of visual features (such as regions)…