3D Urban Reconstruction from Video

University of Kentucky and University of North Carolina, Chapel Hill

Please also visit  Official UNC Web Page

 

Project Overview

This project aims at developing a fully automated system for the accurate and rapid 3D reconstruction of urban environments from video streams. The system collects multiple video streams, as well as GPS and INS measurements in order to place the reconstructed models in geo-registered coordinates. Besides high quality in terms of both geometry and appearance, we aim at real-time performance on a combination of CPUs and GPUs.

To achieve accurate real-time 3D reconstructions one is faced with many difficulties. The core problems that need to be addressed are:

  • Estimating the motion, and possibly the parameters, of the camera.
  • Dense reconstruction of the 3D structure of the scene (Multi-view Stereo Matching).
  • Efficient implementation using GPUs.

 

Data Collection

 

We use multiple synchronized cameras on a base, such as the one seen above, to collect multiple video streams.  Three of the four cameras are horizontal, pointing forward, backward and to the side, while the fourth one is tilted upward to capture the upper parts of building facades. Additional sensors such as GPS and inertia sensors can also be integrated to give accurate position measurements. Click to watch the video captured by four cameras in Chapel Hill.

 

Reconstruction Results

Click to watch the full video of reconstructed 3D model (AVI format 28M)

 

 

 

Related Publications

Real-time Video-based Reconstruction of Urban Environments (pdf)

P. Mordohai, J.-M. Frahm, A. Akbarzadeh, B. Clipp, C. Engels, D. Gallup, P. Merrell, C. Salmi, S. Sinha, B. Talton, L. Wang, Q. Yang , H. Stew¨Śnius, H. Towles, G. Welch, R. Yang, M. Pollefeys and D. Nister

ISPRS Working Group V/4 Workshop 3D-ARCH 2007: 3D Virtual Reconstruction and Visualization of Complex Architectures, (ETH Zurich, Switzerland), July 12¨C13 2007.

 

Towards Urban 3D Reconstruction from Video (pdf)

A. Akbarzadeh, J.-M. Frahm, P. Mordohai, B. Clipp, C. Engels, D. Gallup, P. Merrell, M. Phelps, S. Sinha, B. Talton, L. Wang, Q. Yang, H. Stewenius, R. Yang, G. Welch, H. Towles, D. Nister and M. Pollefeys

Third International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT), 2006 (Invited Paper)

 

 

Acknowledgements

We would like to thank DARPA for funding our research under the UrbanScape program.
Approved for Public Release, Distribution Unlimited.