\CPL\Project\Graphics and Multimedia

 

 

Augmenting Aerial Earth Maps with Dynamic Information

 

 

 

Kihwan Kim, Sangmin Oh, Jeonggyu Lee and Irfan Essa,

College of Computing, School of Interactive Computing

GVU Center, Georgia Institute of Technology

 

 

* IEEE/ACM ISMAR 2009 ( International Symposium on Mixed and Augmented Reality) 2009, Orlando Florida USA

** This work was in part funded by a Google Research Award (http://research.google.com/university/relations/research_awards.html). 

[Paper (TBA): PDF | Presentation (talk at ISMAR) : PPT | BibTex]

 

 

 

 

Abstract

We introduce methods for augmenting aerial visualizations of Earth (from tools such as Google Earth or Microsoft Virtual Earth) with dynamic information obtained from videos. Our goal is to make Augmented Earth Maps that visualize the live broadcast of dynamic sceneries within a city. We propose different approaches to analyze videos of pedestrians and cars, under differing conditions and then augment Aerial Earth Maps (AEMs) with live and dynamic information. We also analyze natural phenomenon (clouds) and project information from these to the AEMs to add the visual reality.

 

 

 

 

System Overview

 

 

 

 

Result Images

 (Note that all rendered footages are generated in real-time)

 

Direct Mapping

Multiple View Blending

 

 

Unobservable region estimation and simulation

Video-driven clouds synthesis

 

 

More restuls

 

 

More Results from our prototype system using 36 videos : (1) OCCM(View Blending) : (a) 5 Cameras for soccer game (b) Two broadcasting footages of NCAA Football game (c) Three surveillance cameras. (2) SCSM(Traffic) : (d) Merging Lanes (e) Rendered traffic Scene and corresponding simulated scene (f) 8 cameras for larger scale traffic simulation including merge and split (3) DM(Pedestrians) : (g) Direct mapping of pedestrian having simple motion (4) SCCM(Clouds) : (h)Four videos for clouds and sky generation (5) Putting event to different location (i)

 

 

Videos

(1) AVI/Divx 6.8, 80MB: Download

(2) Youtube (5:21) :

 

 

 

Media coverage : CNN, New Scientist, Popular Science, Discovery Channel, Revolution MagazineTechnology Review (MIT), Engadget, Vizworld  etc.