Building extraction from multiple images

Ahmed Farouk Elaksher, Purdue University

Abstract

Building extraction in urban areas is one of the most difficult problems in image understanding and photogrammetry. Building delineations are needed in cartographic analysis, urban area planning, and visualization. Although one pair of images is adequate to find the 3D position of two visible corresponding image features, it is insufficient to extract the entire building due to hidden features that are not projected into the image pair. This thesis presents a new technique to detect and delineate buildings with complex rooftops by extracting roof polygons and matching them using multiple images. The algorithm presented in this research starts by segmenting the images into regions. Regions are then classified into roof regions and non-roof regions using a neural network. A rule-based system is then used to convert the roof boundaries to polygons. Polygon correspondence is established geometrically. All possible polygon corresponding sets are considered and the optimal set is selected. The polygon vertices correspondence problem is solved in a similar manner. Building vertices are reconstructed using the geometrical properties of urban buildings. The algorithm is tested on a number of buildings and the results are evaluated. The RMS error for the extracted building vertices is 0.80m using 1:4000 scale aerial photographs scanned at 30μm.

Degree

Ph.D.

Advisors

Bethel, Purdue University.

Subject Area

Civil engineering

Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server
.

Share

COinS