Using local features to measure land development in urban regions

Authors:
Beril Sırmaçek;Cem ínsalan
Affiliations:
Computer Vision Research Laboratory, Department of Electrical and Electronics Engineering, Yeditepe University, Kayışdagı, İstanbul 34755, Turkey;Computer Vision Research Laboratory, Department of Electrical and Electronics Engineering, Yeditepe University, Kayışdagı, İstanbul 34755, Turkey
Venue:
Pattern Recognition Letters
Year:
2010

Citing 5
Cited 1

Wavelets and subband coding

Wavelets and subband coding
Simple Gabor feature space for invariant object recognition

Pattern Recognition Letters
A Novel Framework for Urban Change Detection Using VHR Satellite Images

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Image Processing, Analysis, and Machine Vision

Image Processing, Analysis, and Machine Vision
Image change detection algorithms: a systematic survey

IEEE Transactions on Image Processing

Multiscale quality assessment of Global Human Settlement Layer scenes against reference data using statistical learning

Pattern Recognition Letters

Quantified Score

Hi-index	0.10

Visualization

Abstract

Monitoring urban development in a given region provides valuable information to researchers. Currently available, very high resolution satellite images can be used for this purpose. However, manually monitoring land development using these large and complex images is time consuming and prone to errors. To handle this problem, an automated system is needed to measure development in urban regions. Therefore, in this study we propose such an automated method to measure land development in a given urban region imaged in different times. We benefit from novel land development measures for this purpose. They are based on local features obtained from sequential images. As a novel contribution, we represent these local features in a spatial voting matrix. Then, we propose five different land development measures on the formed voting matrix. We test our method on 19 sets of sequential panchromatic Ikonos images. Our test results indicate the possible use of our method in measuring land development automatically.