Discipline: Computer Sciences and Information Management
Subcategory: Computer Science & Information Systems
Veda Lakshmi Swetha Dasari - Bowie State University
Co-Author(s): Sharad Sharma, Bowie State University, MD
The goal of our project is to develop an Augmented Reality (AR) mobile application to help people evacuate a building. The system gives a visual representation of a building in 3D space, allowing people to see where exits are in the building. Our hypothesis is that the AR mobile application will help users to evacuate buildings faster in case of emergency. The methodology involved in development of the AR mobile application involves the following steps. First, we modeled the 3D building using Sketch up make. To make the 3D model compatible in Unity 3D gaming environment, 3D building models were converted to .fbx model. Next, the model was imported to unity 3D model and Vuforia plugin was imported to Unity 3D to make use of it. Vuforia is an Augmented Reality Software Development Kit (SDK) for mobile devices that enables the creation of Augmented Reality applications. It uses Computer Vision technology to recognize and track planar images (Image Targets) and simple 3D objects, such as boxes, in real-time. 3D characters available in Unity 3D were used to show how people can evacuate the building in case of an emergency. Way path algorithms were used to make avatars move and run towards the exits in the building model. Once the application design and development was done, the project was tested using the markers. The result of the application included giving the demo to the users so that people during emergency evacuation may make better decisions. Our proposed solution includes putting the markers at key spots in the building, such that the user can use their smart phones to view the 3D representation of the building and exits. Future work of this application will involve increasing the frame rate for agent’s animation and inclusion of GPS capability.
Not SubmittedFunder Acknowledgement(s): The authors would like to thank the National Science Foundation for supporting the project. This work is funded by the Grant Award number HRD-1238784. The authors would also like to acknowledge the support of the Virtual Reality Laboratory at Bowie State University.
Faculty Advisor: Sharad Sharma, ssharad@gmail.com