Localization in real world - virtual world

Abstract

The objective of this thesis is to set-up a 3D mirror world where the objects and the events that are happening in the real physical world can be visualized. The focus and the scope of this thesis is to visualize the tracking in the mirror world for the equivalent objects and people in the real world. <br><br>This thesis can be divided into two parts. The first part deals in creating a platform for the visualization of a real world environment, i.e. Communications Lab in NUS Campus. Sun Microsystems Project Wonderland (WL), an open source toolkit, is used as a basic 3D building environment. A centralized web-server is set up such that the mirror world can be accessed using a web browser. A virtual 3D model of the Communications Lab in the Department of Electrical and Computer Engineering is successfully created and imported into the WL. The WL source code (WL is open source) is modified to create a communication channel between the imported mirror world and the real-world applications. The channel is also used to exchange location information between the real world and the virtual world. The real world location information is obtained from a Wi-Fi based indoor localization system, Ekahau. A new interface is developed in Java which integrates the Ekahau localization system with the WL.<br><br>The second part of the thesis deals in proposing a new approach for the placement of access points for Wi-Fi based Fingerprinting localization such as Ekahau. The main idea behind the AP placement algorithm is to minimize the total number of similar fingerprints over the entire array of receiver locations, by varying the access points' location. To solve the optimization problem, a heuristic optimization algorithm Simulated Annealing has been implemented as simple brute force search method would be highly computationally expensive and inefficient. Numerical results are obtained for both the brute force search and the Simulated Annealing optimization approach. The proposed algorithm's output, i.e. the access points' location has been applied to a k Nearest Neighbour based localization system and location error has been analyzed.<br>