PhD Candidacy Exam PDF Print E-mail
Written by Nicholas Shorter   
Monday, 28 July 2008 01:58

Presentation Title

Autonomous 3D Reconstruction From Irregular LiDAR and Aerial Imagery

Presentation Purpose

Presenting, for approval from PhD Candidacy Committee, proposed research work for PhDEE dissertation

Presentation Date

May 11, 2007

PhD Committee Members

Dr. Takis Kasparis (Committee Chair)
Dr. Georgios Anagnostopoulos
Dr. Michael Georgiopoulos
Dr. Andy Lee
Dr. Wasfy Mikhael

Presentation Abstract

As more data sources have become abundantly available, an increased interest in 3D reconstruction has emerged in the image processing academic community. Applications for 3D reconstruction of urban and residential buildings consist of urban planning, network planning for mobile communication, tourism information systems, spatial analysis of air pollution and noise nuisance, microclimate investigations, and Geographical Information Systems (GISs). Previous, classical, 3D reconstruction algorithms solely utilized aerial photography. With the advent of LIDAR systems, current algorithms explore using captured LIDAR data as an additional feasible source of information for 3D reconstruction.
This proposal presents an outline for the development of an autonomous 3D reconstruction algorithm. The algorithm will analyze key features extracted from both LiDAR data and aerial imagery of a given scene and, without user intervention, isolate building structures and then reconstruct 3D models depicting those building structures. The motivations behind already determining several key characteristics about the design of the reconstruction algorithm (such as using a data dependent as opposed to model based algorithm) are presented. Comparisons to previous works contrasting design methodologies are also included.

Presentation Files

PhD Candidacy Proposal (pdf)
PhD Candidacy Presentation (pdf)
PhD Candidacy Presentation (ppt)

Related Journal Papers

1. Xu., R.; and Wunch, D.; II, “Survey of Clustering Algorithms”, IEEE Transactions on Neural Networks, Vol. 16, No. 3, pp. 645-678., May 2005
2. Wang, Kai; Lo, Chor Pang; Brook, George; Arabnia, Hamid; “
Comparison of existing triangulation methods for regularly and irregularly spaced height fields.INT. J. Geographical Information Science, vol. 15, no. 8, pp 743-762, 2001
3. Garland, M.; Heckbert, P. S.; “
Fast polygonal approximation of terrains and height fields.Technical Report, Department of Computer Science, Carnegie Mellon University, 1995.
4.
Vosselman, G.; Gorte, B.G.H.; Sithole, G.; Rabbani, T.; "Recognising structure in laser scanner point clouds." International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 46, part 8/W2, Freiburg, Germany, October 4-6, (2004) pp. 33-38.
5. Clode, S.P.; Kootsookos, P.J; and Rottensteiner, F. “
Accurate Building Outlines from ALS Data.12th Australasian Remote Sensing and Photogrammetry Conference, 2004
6. Morgan, Michel; Habib, Ayman; “
Interpolation of LIDAR Data and Automatic Building Extraction.” ACSM-ASPRS2002 Annual Conference Proceedings, 2002

 

Proposed Algorithm System Block Diagram:

 
 
Last Updated on Monday, 28 July 2008 02:06