Computer vision publications
-
A Stochastic Approach To Stereo Vision
A stochastic optimization approach to stereo matching is presented. The approach provides a dense array of disparities, eliminating the need for interpolation.
-
Using Generic Geometric Knowledge To Delineate Cultural Objects In Aerial Imagery
We present a paradigm for discovering the outlines of arbitrarily complex cultural objects in aerial imagery.
-
Evidential Knowledge-Based Computer Vision
In this paper, we discuss some of the differences between the DS theory and some popular Bayesian-based approaches to effecting the reasoning task.
-
The DARPA / DMA Image Understanding Testbed System Manager’s Manual
The primary purpose of the Image Understanding (IU) Testbed is to provide a means for transferring technology from the DARPA-sponsored IU research program to DMA and other organizations in the…
-
One-Eyed Stereo: A Unified Strategy To Recover Shape From A Single Image
In this paper we contend that the distinct assumptions made in each of these schemes must be tantamount to providing a second (virtual) image of the original scene, and that…
-
Evaluation Of Stereosys Vs. Other Stereo Systems
SRI International is implementing a complete, state-of the-art stereo system that will produce dense three-dimensional (3D) data from stereo pairs of intensity images. This system forms a framework for much…
-
Description Of SRI’s Baseline Stereo System
We are implementing a baseline system for automated area-based stereo compilation.
-
Goal-Directed Textured-Image Segmentation
This report concentrates on textured-image segmentation using local texture-energy measures and user-delimited training regions. The SLICE algorithm combines knowledge of target textures or signatures with knowledge of background textures by…
-
An Inductive Approach To Figural Perception
An inductive approach consisting of two parts is presented. The first involves a scheme for describing the shapes of curves and surfaces and the second relies on a criterion for…
-
Evaluation Of Scene-Analysis Algorithms
A software evaluation methodology has been developed at SRI International for evaluating contributions to the ARPA/DMA Image Understanding Testbed. This paper describes the criteria that have shaped the evaluation methodology.
-
A Fast Surface Interpolation Technique
A method for interpolating a surface through 3-D data is presented. The method is computationally efficient and general enough to allow the construction of surfaces with either smooth or rough…
-
Image-To-Image Correspondence: Linear-Structure Matching
We examine the task of matching images of a scene when they are taken from very different vantage points, when there is considerable scale change, and when the image orientations…