8,450 Result(s)
within
**hu Li
Artificial Intelligence
Image Processing and Computer Vision
-
Chapter
Multiprocessing of Combinatorial Search Problems
This chapter presents three paradigms of representations for combinatorial search problems. Depending on the functions of the nonterminal nodes in the graphical representation, a search problem can be represen...
-
Article
Invariant surface segmentation through energy minimization with discontinuities
The computational problems in segmenting range data into surface patches based on the invariant surface properties, i.e., mean curvature H and Gaussian curvature K, are investigated. The goal is to obtain reliabl...
-
Chapter and Conference Paper
Matching and recognition of road networks from aerial images
In this paper, we develop a method of matching and recognizing aerial road network images based on road network models. We use attributed relational graphs to describe images and models. The correspondences ar...
-
Chapter and Conference Paper
Estimating mean disparity of stereo images using shift-trials of phase differences
Disparity can be estimated using the phase differences between a pair of stereo images after Gabor filtering. In this paper a simple method is proposed for target detection, which uses shift-trials of phase di...
-
Chapter and Conference Paper
Building a Model of a Road Junction Using Moving Vehicle Information
We describe a program to construct a model of a road junction using data from a single camera. The model specifies the ground plane orientation in camera coordinates and the positions of traffic lanes, and is ...
-
Article
A visual tool for user-interface development
VITUID is a visual tool for user interface development. It aims to help user-interface designers, who may be non-programmers, to specify and create interactive, graphical user interfaces through graphical inte...
-
Chapter and Conference Paper
Markov random field models in computer vision
A variety of computer vision problems can be optimally posed as Bayesian labeling in which the solution of a problem is defined as the maximum a posteriori (MAP) probability estimate of the true labeling. The pos...
-
Chapter and Conference Paper
Camera calibration of a head-eye system for active vision
In this paper, we present methods and techniques for calibrating cameras of a head-eye system, which has computer controlled focusing, zooming, and iris. The idea is to build up look-up-tables for intrinsic pa...
-
Chapter and Conference Paper
Fast computation of the fundamental matrix for an active stereo vision system
This paper investigates the problem of computing the fundamental matrix for a class of active stereo vision system, namely with common elevation platform. The fundamental matrix is derived for such a system, a...
-
Article
Aerodynamic force models for animating cloth motion in air flow
This paper is focused on the analysis of the intersection between the air-flow field around a piece of cloth and the motion of the cloth in order to animate realistically the cloth motion in the air flow. Two ...
-
Chapter and Conference Paper
Edge-preserving smoothing by convex minimization
This work presents a new approach for analyzing the problem of edge-preserving image smoothing using convex minimization and for selecting smoothing parameters. The close-form (global) solution is derived as t...
-
Chapter and Conference Paper
Easy calibration of pan/tilt camera heads and online computation of the epipolar correspondences
In this article we describe a calibration procedure of a binocular camera head with two independent pan and tilt axes. For the calibration procedure itself no separate rotations of the respective axes and no f...
-
Chapter and Conference Paper
Shape recovery from one image under multiple light sources
In this paper, we propose a rectangular light source model and a novel method for recovering surface shape from one image under multiple planar light sources using shape-from-shading(SFS). This method can be e...
-
Chapter and Conference Paper
Combining evidence in multimodal personal identity recognition systems
We develop a common theoretical framework for combining evidence in multimodal personal identity recognition systems. It is shown that many existing schemes can be considered as special cases of compound class...
-
Chapter and Conference Paper
Adaptive logic networks for facial feature detection
The task of automatic facial feature detection in frontal-view, ID-type pictures is considered. Attention is focused on the problem of eye detection. A neural network approach is tested using adaptive logic ne...
-
Chapter and Conference Paper
Toward global solution to MAP image estimation: Using Common structure of local solutions
The maximum a posteriori (MAP) principle is often used in image restoration and segmentation to define the optimal solution when both the prior and likelihood distributions are available. MAP estimation is equ...
-
Chapter and Conference Paper
Contour line extraction from color images of scanned maps
This paper reports our work on contour line extraction from color images of scanned maps. Color processing extracts the basic colors of an image by switching from RGB to L*a*b color space, projecting the image...
-
Chapter and Conference Paper
Model-based active object recognition using MRF matching and sensor planning
This paper presents an active object recognition algorithm using MAP-MRF matching and sensor planning strategy. The matching between the sensed and model object is based on surface properties. A new measure of...
-
Chapter and Conference Paper
Spherical and cylindrical light source models for shape recovery
Parallel rays of light coming from the same direction is the basic assumption for the lighting condition of the conventional shape from shading(SFS) methods. This is at best approximately true in controlled en...
-
Chapter and Conference Paper
Video compression and person authentication
In this paper, we address the possible effects of video compression on the visual quality of images, that should be considered by person authentication algorithms. We present the block based compression approa...
