This paper investigates a robot motion control problem with visual information. Firstly the model of the relativ erigid body motion (positions and rotations) and the method for the estimation of the relative rigid body motion are presented in order to derive the visual feedback system. Secondly we consider the velocit y observer and derive the dynamic visual feedback system which contains the m...

The visual salience is an important property of 3D mesh model. There are many metric, including methods based on geometry and ones based on images. It is difficult for the former to infer the direct relationship between geometry and visual stimuli, and the latter is affected by the viewpoint and light source. The visual salience of 3D mesh geometry elements, such as the vertex, edge and patch, ...

This work investigates one of the fundamental problems in machine vision, that of obtaining a three-dimensional (3D) digital model of a real object, from a collection of photographs. 3D computer models are a vital part of a wide range of disciplines, from the study of sculpture and architecture to archaeology, structural engineering and computer graphics. We focus on two important open question...

Accurate perception of self-motion through cluttered environments involves a coordinated set of sensorimotor processes that encode and compare information from visual, vestibular, proprioceptive, motor-corollary, and cognitive inputs. Our goal was to investigate the visual and vestibular cues to the direction of linear self-motion (heading direction). In the vestibular experiment, blindfolded p...

An approach to visual motion estimation and its stabilization suitable for longitudinal camera motion is proposed. Closed contours with their image pair-like displacements in a short image sequence are detected. The contour length change rate is estimated allowing the rst stabilization step a weighted averaging of displacements. Two further steps follow the grouping of similarly moving neighbou...

We analyze the problem of estimating 3-D motion in an optimal manner using correspondences of features in two views. The importance of having an optimal estimator is twofold: first, for the estimation itself and, second, for the bound it offers on how much sensitivity one can expect from a two-frame, point-based motion algorithm. The optimal estimator turns out to be nonlinear, and for that rea...

BACKGROUND Estimating intraoperative blood loss can be a difficult task, especially when blood is mostly absorbed by gauze. In this study, we have provided an improved method for estimating blood absorbed by gauze. OBJECTIVES To develop a guide to estimate blood absorbed by surgical gauze. MATERIALS AND METHODS A clinical experiment was conducted using aspirated blood and common surgical ga...

The autonomous navigation of a mobile vehicle can be described as the task it undertakes to move itself in the environment through a series of positions based on information gathered by its sensors. In order to accomplish this task, the vehicle has to cope with two main subtasks namely obstacle avoidance and self localization. The later implies in the ability to determine its position and orien...

We present an approach to vision-based mobile robot localization, even without an a-priori pose estimate. This is accomplished by learning a set of visual features called image-domain landmarks. The landmark learning mechanism is designed to be applicable to a wide range of environments. Each landmark is detected as a local extremum of a measure of uniqueness and represented by an appearance-ba...

Visual-to-auditory sensory substitution devices convert visual information into sound and can provide valuable assistance for blind people. Recent iterations of these rely on depth sensors. Rules converting (i.e., the sonifications) are often designed arbitrarily, with no strong evidence choosing one over another. The purpose this article is to compare understand effectiveness five sonification...