Object-based classification with features extracted by a semi-automatic feature extraction algorithm-SEaTH

Y. Gao, P. Marpu, I. Niemeyer, D.M. Runfola, N.M. Giner, T. Hamill, R.G. Pontius Jr.

Research output: Contribution to journalArticlepeer-review

31 Scopus citations


Object-based image analysis (OBIA) uses object features (or attributes) that relate to the pixels contained by the image object to assist in image classification. These object features include spectral, shape, texture and context features. With hundreds of available features, the identification of those that can improve separability between classes is critical for OBIA. The Separability and Thresholds (SEaTH) algorithm calculates the SEaTH of object-classes for the given features. The SEaTH algorithm avoids time-consuming trial-and-error practice for seeking important features and thresholds. This article tests the SEaTH algorithm on Landsat-7 Enhanced Thematic Mapper (ETM+) imagery in a heterogeneous landscape with multiple land cover classes. The results suggest SEaTH is a strong alternative to other automated approaches, yielding an agreement of 79% with reference data. In comparison, an object-based nearest neighbour classifier yielded 66% agreement and a pixel-based maximum likelihood classifier yielded 69% agreement. © 2011 Taylor & Francis.
Original languageEnglish
Pages (from-to)211-226
Number of pages16
JournalGeocarto International
Issue number3
StatePublished - 2011

Bibliographical note

Cited By :21

Export Date: 26 December 2018

Correspondence Address: Gao, Y.; Centro de Investigaciones en Ecosistemas, UNAM, Morelia, Mexico; email: yan@census.hokudai.ac.jp


  • Feature extraction
  • Object-based classification
  • Separability and
  • algorithm
  • image analysis
  • image classification
  • Landsat thematic mapper
  • pixel


Dive into the research topics of 'Object-based classification with features extracted by a semi-automatic feature extraction algorithm-SEaTH'. Together they form a unique fingerprint.

Cite this