Effective Separation of Trees and Buildings for Automated Building Detection
MetadataShow full item record
Effective separation of buildings from trees is a ma jor challenge in automatic building detection from aerial imagery and Lidar data. In cases where an ado pted building detection technique cannot distinguis h between these two classes of objects, the presence of trees in the scene can increase the rates of both false positives and false negatives in the building detection process. This p aper presents an automatic building detection techn ique which exhibits improved separation of buildings from tree s. In addition to using traditional cues such as he ight, width and colour, the improved detector uses texture informat ion from both Lidar and orthoimagery. Firstly, image entropy and colour information are jointly applied to remove ea sily distinguishable trees. Secondly, a rule-based procedure using the edge orientation histogram from the imagery is followed to eliminate false positive candidates. The improved detector has been tested on a number of scenes from three different test areas and it is shown that th e algorithm performs well even in complex scenes with over 10% increase both in completeness and correctness.
32nd Asian Conference on Remote Sensing 2011
© The Author(s) 2011. The attached file is reproduced here in accordance with the copyright policy of the publisher. For information about this conference please refer to the conference’s website or contact the author[s].
Photogrammetry and Remote Sensing