Automatic Generation of Building Models Using 2D Maps and
Street View Images  

We introduce a new approach for generating simple 3D building models by combining building footprints from 2D maps with street level images. Building heights are estimated by projecting building footprints onto images and comparing with image features. The height information together with building footprints produces box-like building models. The following demo shows that the method uses Google Street View images and building footprints from GIS maps for 3D model creation. To generate such models often requires aerial sensing data that are expensive to collect (e.g., LiDAR data), while we use data sources that are widely available and easy to access.


Please refer to the following paper for details.

Jiangye Yuan and Anil M. Cheriyadat, Combining Maps and Street Level Images for Building Height and Facade Estimation, ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, 2016. [pdf] 

Please address questions to yuanj at ornl dot gov.