Learning-based building outline detection from multiple aerial images

Guo, Yanlin; Sawhney, Hemant; Kumar, Ratnesh; Hsu, Sheng Teng

doi:10.1109/cvpr.2001.991010

Cited by 5 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It may have good performance, but the searching for 2/3-D evidence to verify the hypotheses generated before, is a very complex work. A learning algorithm, which is made up of initial segmentation, feature extracting, learning and refinement steps, was practiced by Guo et al [3]. A SVM-based learning scheme was implemented by Zhang et al [4], for the detection of artificial objects from remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

Self-enhanced SVM Extraction of Building Objects from High Resolution Satellite Images

Zhang

2007

Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007)

View full text Add to dashboard Cite

A self-enhanced SVM (Support Vector Machines) building detection scheme is discussed. The scheme was designed for 1-metre resolution satellite imagery analysis. The scheme is a learning based segmentation without any prior prepared training data set. In the initial stage, an adaptive two-dimension Otsu algorithm is adopted to segment the image primarily into buildings and non-buildings. Then the segmented regions are modeled as second order GMRF (Gaussian Markov Random Fields), and a six element characteristic vectors are extracted. In the final stage, a SVM classifier is trained on the characteristic vector and region label, then the trained SVM classifier re-segment the image on pixel to get an enhanced result. Experiment shows that the system is efficient and robust.

show abstract

Section: Introductionmentioning

confidence: 99%

Self-enhanced SVM Extraction of Building Objects from High Resolution Satellite Images

Zhang

2007

Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007)

View full text Add to dashboard Cite

show abstract

User interactive multiple aerial view analysis for reconstructing a large number of 3D architectural models

Lee

Nevatia

2011

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Automatic Building Detection from Aerial Images for Mobile Robot Mapping

Persson

Sandvall

Duckett

2005 International Symposium on Computational Intelligence in Robotics and Automation

View full text Add to dashboard Cite

Abstract-To improve mobile robot outdoor mapping, information about the shape and location of buildings is of interest. This paper describes a system for automatic detection of buildings in aerial images taken from a nadir view. The system builds two types of independent hypotheses based on the image contents. A segmentation process implemented as an ensemble of SOMs (Self Organizing Maps) is trained and used to create a segmented image showing different types of roofs, vegetation and sea. A second type of hypotheses is based on an edge image produced from the aerial photo. A line extraction process uses the edge image as input and extracts lines from it. From these edges, corners and rectangles that represent buildings are constructed. A classification process uses the information from both hypotheses to determine whether the rectangles are buildings, unsure buildings or unknown objects.

show abstract

Learning-based building outline detection from multiple aerial images

Cited by 5 publications

References 9 publications

Self-enhanced SVM Extraction of Building Objects from High Resolution Satellite Images

Self-enhanced SVM Extraction of Building Objects from High Resolution Satellite Images

User interactive multiple aerial view analysis for reconstructing a large number of 3D architectural models

Automatic Building Detection from Aerial Images for Mobile Robot Mapping

Contact Info

Product

Resources

About