C
Cem Unsalan
Researcher at Yeditepe University
Publications - 104
Citations - 1732
Cem Unsalan is an academic researcher from Yeditepe University. The author has contributed to research in topics: Change detection & Feature extraction. The author has an hindex of 18, co-authored 101 publications receiving 1577 citations. Previous affiliations of Cem Unsalan include Ohio State University & Boğaziçi University.
Papers
More filters
Journal ArticleDOI
Urban-Area and Building Detection Using SIFT Keypoints and Graph Theory
Beril Sirmacek,Cem Unsalan +1 more
TL;DR: To detect the urban area and buildings in satellite images, the use of scale invariant feature transform (SIFT) and graph theoretical tools are proposed and very promising results on automatically detecting urban areas and buildings are reported.
Journal ArticleDOI
A Probabilistic Framework to Detect Buildings in Aerial and Satellite Images
Beril Sirmacek,Cem Unsalan +1 more
TL;DR: Extensive tests indicate that the proposed novel building detection method using local feature vectors and a probabilistic framework can be used to automatically detect buildings in a robust and fast manner in Ikonos satellite and the authors' aerial images.
Proceedings ArticleDOI
Building detection from aerial images using invariant color features and shadow information
Beril Sirmacek,Cem Unsalan +1 more
TL;DR: This study presents a novel approach for building detection using multiple cues, which benefits from segmentation of aerial images using invariant color features and determines the shape of the building by a novel method.
Journal ArticleDOI
Road Network Detection Using Probabilistic and Graph Theoretical Methods
Cem Unsalan,Beril Sirmacek +1 more
TL;DR: Results indicate that the proposed automated system can be used in detecting the road network on very high resolution satellite and aerial images in a reliable and fast manner.
Journal ArticleDOI
Urban Area Detection Using Local Feature Points and Spatial Voting
Beril Sirmacek,Cem Unsalan +1 more
TL;DR: This letter proposes a method based on local feature point extraction using Gabor filters to detect the urban area using an optimal decision-making approach on the vote distribution and test the method on a diverse panchromatic aerial and Ikonos satellite image set.