As people become increasingly acquainted with information technology, they demand continuous availability of services related to their work or leisure. The era of ubiquitous computing announced long ago is currently turning into an everyday reality at an ever-increasing pace. Alongside the evolution of ubiquitous and nomadic computing, the need of people to access vast amounts of information in a comprehensive and efficient way gives rise to the areas of information visualization and augmented-reality. Such technologies allow for the comprehensive presentation of visual information equally addressing the needs of different categories of people.
In the past 5 years, we have been active in a set of European Research Projects addressing the above-mentioned research directions, with the long-term goal to develop a software platform that will enable context-aware services deploying advanced visualization technology in a series of application domains, such as cultural heritage dissemination, interactive television and retail industry. The multitude of the application domains addressed, as well as the multidisciplinary expertise necessary to create a generic platform was successfully addressed in complementary research activities. In this paper, we present the idea of a platform for context-aware services by exploiting advanced visualization technology and subsequently we briefly review the research projects that delivered valuable pieces in the overall puzzle. Emphasis is put on the practical issues of the implementation and deployment in different application scenarios. 相似文献
The calibration of camera distortion plays an important role in the field of industrial machine vision application. In this paper, a novel approach for calibrating camera radial distortion is presented based on cross-ratio invariability for perspective projection. Assumed to be with one-order radial distortion, the image coordinates and the cross-ratio of only four collinear points in space are needed in this approach. The cross-ratio, easily known from a calibration target, is identical with that of the four corresponding image points. This is called the cross-ratio invariability for perspective projection. A monadic two-order equation is built based on the cross-ratio invariability, which gives an accurate solution to radial distortion coefficients. A digital simulation and a practical image correction prove this approach to be simple, accurate, efficient and time saving. 相似文献
Achieving good signal-to-noise ratio (SNR) against solar illumination is a basic requirement for the light source of active vision sensors in outdoor applications. The article examines the high power stripe-lighting setup, constructed with a cylindrical lens and a rectangular emitting source placed at the focal line of the lens. This source type is capable of illuminating a very high total power because of the large surface size of the emitter; thus it is advantageous for outdoor applications. A detailed radiometric analysis of this setup is presented resulting in an integral for the calculation of the spatial irradiance distribution within the stripe. The achievable SNRs against solar illumination are calculated by applying the radiometric integral for different rectangular emitters built of LED arrays, laser diode arrays and incandescent sources. The article proposes stripe illuminators applying all the analyzed emitter types that are suitable for operation in direct sunshine. 相似文献
A stereo disparity-based range finding technique was developed for measuring three-dimensional coordinates of object points. It used an image-matching algorithm which functionally consisted of scene reduction, epipolar line selection, and features matching. Experiments implementing this technique were performed on an industrial vision system. An error analysis indicated that image resolution was the major source of measurement inaccuracy. 相似文献
The key modules in a typical reverse engineering system consist of the acquisition, registration, and the integration of range images of three-dimensional objects with complex geometry. We first present a self-made optical digitizer that is employed for quickly acquiring range data from multiple views, then introduce a visualized registration procedure that can provide a reliable estimate for the fine registration of multiple range images in a unified coordinate system. Experiment results are given to show the effectiveness of this approach in 3-D imaging and multiple range image registration for the applications of reverse engineering. 相似文献