<title>Experimental analysis and design considerations of virtual environments creation</title>

Abstract

Selecting the appropriate 3-D capture and modeling technologies to create the contents of a virtual environment (VE) remains a challenging task. One of the objectives of the environment-modeling project in our laboratory is to develop a design strategy for selecting the optimum sensor technology and its configuration to meet the requirements for virtual environment applications. This will be based on experimental evaluation of all performance aspects of several systems for creating virtual environments. The main problems include: practical sensor calibration, the registration of images particularly in large sites in the absence of GPS and control points, the complete and accurate coverage of all details, and maintaining realistic-look at real-time rate. This paper focuses on the evaluation of the performance of some approaches to virtual environment creation using specifically designed laboratory experimentation. By understanding the potentials and limitations of each method, we are able to select the optimum one for a given application.

Relevance-based Content Modeling and Object Retrieval from Multi-source Image Data

“…There has been an increased demand for range data to obtain models of objects and sites for virtual environment (VE) applications, such as virtual museums, historical sites documentation, mapping of hazardous sites and underground tunnels (mine automation), and as-built modeling of industrial and power plants for design verification and modification. A discussion on a design strategy for selecting the optimum sensor technology and its configuration to meet the requirements for VE applications can be found in [6]. A multi-spectral satellite image (Figure 1(c)) is an example of multi-dimensional data, which can be used for land cover segmentation, provision of location-based services, etc.…”

“…A typical example of the use of geometrical features is provided by CAD models, where semantic information about the product may be represented using the concept of feature-based modeling (FBM) [1]. Creation of a virtual design environment and design visualization is an important element of object retrieval and FBM [6][7][8][9]. An intermediate feature-based semi-semantic representation of the objects of interest can be subsequently translated into a semantic, application-dependent description.…”