AUTOMATIC BUILDING DETECTION WITH FEATURE SPACE FUSION USING ENSEMBLE LEARNING


Senaras C., Yuksel B., Ozay M., Yarman-Vural F.

IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Munich, Almanya, 22 - 27 Temmuz 2012, ss.6713-6716 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/igarss.2012.6352058
  • Basıldığı Şehir: Munich
  • Basıldığı Ülke: Almanya
  • Sayfa Sayıları: ss.6713-6716
  • Anahtar Kelimeler: remote sensing, pattern recognition, multi-layer classification, stacked generalization, building detection, decision fusion, fuzzy k-nn classification, PERFORMANCE, IMAGES
  • Orta Doğu Teknik Üniversitesi Adresli: Hayır

Özet

This paper proposes a novel approach to building detection problem in satellite images. The proposed method employs a two layer hierarchical classification mechanism for ensemble learning. After an initial segmentation, each segment is classified by N different classifiers using different features at the first layer. The class membership values of the segments, which are obtained from different base layer classifiers, are ensembled to form a new fusion space, which forms a linearly separable simplex. Then, this simplex is partitioned by a linear classifier at the meta layer. The paper presents the performance results of the proposed model and comparisons with the state of the art classifiers.