Building detection in complex scenes through effective seperation of buildings from trees

Awrangjeb, M, Zhang, C and Fraser, C 2012, 'Building detection in complex scenes through effective seperation of buildings from trees', Photogrammetric Engineering and Remote Sensing, vol. 78, no. 7, pp. 729-745.


Document type: Journal Article
Collection: Journal Articles

Title Building detection in complex scenes through effective seperation of buildings from trees
Author(s) Awrangjeb, M
Zhang, C
Fraser, C
Year 2012
Journal name Photogrammetric Engineering and Remote Sensing
Volume number 78
Issue number 7
Start page 729
End page 745
Total pages 17
Publisher American Society for Photogrammetry and Remote Sensing
Abstract Effective separation of buildings from trees is a major challenge in image-based automatic building detection. This paper presents a three-step method for effective separation of buildings from trees using aerial imagery and lidar data. First, it uses cues such as height to remove objects of low height such as bushes, and width to exclude trees with small horizontal coverage. The height threshold is also used to generate a ground mask where buildings are found to be more separable than in so-called normalized DSM. Second, image entropy and color information are jointly applied to remove easily distinguishable trees. Finally, an innovative rule-based procedure is employed using the edge orientation histogram from the imagery to eliminate false positive candidates. The improved building detection algorithm has been tested on different test areas and it is shown that the algorithm offers high building detection rate in complex scenes which are hilly and densely vegetated.
Subject Photogrammetry and Remote Sensing
Copyright notice © 2012 American Society for Photogrammetry and Remote Sensing
ISSN 0099-1112
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 49 times in Thomson Reuters Web of Science Article | Citations
Access Statistics: 155 Abstract Views  -  Detailed Statistics
Created: Tue, 09 Sep 2014, 12:53:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us