Building detection in complex scenes thorough effective separation of buildings from trees

View/ Open
File version
Version of Record (VoR)
Author(s)
Awrangjeb, Mohammad
Zhang, Chunsun
Fraser, Clive S
Griffith University Author(s)
Year published
2012
Metadata
Show full item recordAbstract
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, ...
View more >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.
View less >
View more >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.
View less >
Journal Title
Photogrammetric Engineering and Remote Sensing
Volume
78
Issue
7
Copyright Statement
© 2012 ASPRS. Reprinted with permission from the American Society for Photogrammetry & Remote Sensing, Bethesda, Maryland, www.asprs.org. Please refer to the journal's website for access to the definitive, published version.
Subject
Computer vision
Image processing
Geomatic engineering
Photogrammetry and remote sensing