Staff Members - Benha University
Combining statistical and neural classifiers using Dempster-Shafer theory of evidence for improved building detection
• 2010
Publication Information
Authors
John Trinder, Mahmoud Salah,Ahmed Shaker, Mahmoud Hamed, Ali Elsagheer
Keywords
Not Available
Journal
Not Available
Publisher
Not Available
Volume
Not Available
Issue
Not Available
Pages
Not Available
publication.type
International
Paper Link
Not Available
Supplementary Materials
Not Available
Abstract
This paper describes an approach for building detection from multispectral
aerial images and lidar data by combining the results derived from statistical
and neural network classifiers, which offer complementary information, based
on Dempster-Shafer Theory of Evidence. Four study areas with different
sensors and scene characteristics were used. First, we filtered the lidar point
clouds to generate a Digital Terrain Model (DTM), and then the Digital Surface
Model (DSM) and the Normalised Digital Surface Model (nDSM) were
generated. After that a total of 25 uncorrelated feature attributes have been
generated from the aerial images, the lidar intensity image, DSM and nDSM.
Then, three different classification algorithms were used to detect buildings from
aerial images, lidar data and the generated attributes. The classifiers used
include: Self-Organizing Map (SOM); Classification Trees (CTs); and Support
Vector Machines (SVMs). The Dempster-Shafer theory of evidence was then applied for combining measures of evidence from the three classifiers. A considerable amount of the misclassified building pixels were recovered by the combination process.
aerial images and lidar data by combining the results derived from statistical
and neural network classifiers, which offer complementary information, based
on Dempster-Shafer Theory of Evidence. Four study areas with different
sensors and scene characteristics were used. First, we filtered the lidar point
clouds to generate a Digital Terrain Model (DTM), and then the Digital Surface
Model (DSM) and the Normalised Digital Surface Model (nDSM) were
generated. After that a total of 25 uncorrelated feature attributes have been
generated from the aerial images, the lidar intensity image, DSM and nDSM.
Then, three different classification algorithms were used to detect buildings from
aerial images, lidar data and the generated attributes. The classifiers used
include: Self-Organizing Map (SOM); Classification Trees (CTs); and Support
Vector Machines (SVMs). The Dempster-Shafer theory of evidence was then applied for combining measures of evidence from the three classifiers. A considerable amount of the misclassified building pixels were recovered by the combination process.