Computer vision publications
-
Registration without Correspondences
We present a method for registering images of complex 3-D surfaces that does not require explicit correspondences between features across the images.
-
Using 3-Dimensional Meshes to Combine Image-Based and Geometry Constraints
A unified framework for 3-D shape reconstruction allows us to combine image-based and geometry-based information sources. The image information is akin to stereo and shape-from-shading, while the geometric information may…
-
Learning Control Parameters of a Vision Process Using Contextual Information
This paper presents a method for the system itself to learn how to select among its algorithms and to set their parameters, reducing the need for operator expertise while improving…
-
Building and Using Scene Repesentations In Image Understanding
The analysis side is the processing of sensory data for such tasks as recognition and navigation, and a number of techniques are discussed here for dealing with these two-, three-,…
-
Overview Of The SRI Cartographic Modeling Environment
The SRI Cartographic Modeling Environment has been created to support research on interactive, semi-automated, and automated computer-based cartographic activities. The underlying image manipulation capabilities are provided by the SRI ImagCalc…
-
Fast Parallel Surface Interpolation With Applications To Digital Cartography
In this paper, we present a surface interpolation algorithm based on variational splines which is well suited to massively parallel computers.
-
Recognizing Objects In A Natural Environment: A Contextual Vision (CVS)
We identify a number of weaknesses in current recognition systems and propose specific mechanisms for dealing with some of these problems.
-
The Vision Problem: Exploiting Parallel Computation
This technical report consists of papers presented at the session wherein the major problems in computer vision are outlined, and the "signals to symbols"and the "monolithic computing" (MC) approaches to…
-
Integrated Split/Merge Image Segmentation
The KNIFE segmentation algorithm splits regions along object boundaries, thus avoiding rectangular quadtree artifacts and establishing a context for good statistical decisions.
-
Classification-Based Tracking Of Objects and Material
SRI’s KNIFE image analysis system can be used for tracking objects and material classes from one image to another.
-
Coarse Coding For Material and Object Identification
A new coarse-coding technique is presented for labeling image pixels and regions to match exemplars or multivariate material signatures.
-
Learning and Recognition In Natural Environments
We present a system for learning descriptions of objects, and for subsequently recognizing learned objects, that functions in outdoor, natural environments.