An Object-Oriented Pattern Recognition Approach for Urban Classification

Soe Myint, Douglas Stow

Research output: Chapter in Book/Report/Conference proceedingChapter

6 Scopus citations

Abstract

In contrast to subpixel and per-pixel image classification approaches, object-based image analysis (OBIA) attempts to exploit spatially and spectrally similar groups of pixels in order to identify objects within an imaged scene. Object-based approaches are most applicable to high spatial resolution data, where objects of interest are larger than the ground resolution element. Such objects in urban scenes could be related to natural features of urban landscapes (e.g., trees and lakes) or man-made features (e.g., buildings or roads). This chapter introduces readers to the principles of OBIA and demonstrates how it can be applied to achieve satisfactory accuracy in urban mapping. We employed two case studies with two example subsets extracted from Quickbird multispectral satellite data and demonstrated two object-based analysis procedures, namely decision rule (i.e., membership function) and nearest neighbor classifiers. The object-oriented classification employed to identify urban classes in this chapter is specifically based on Definiens software and the various routines it contains to achieve OBIA. However, an overview of the object-oriented approach, parameters generally available for object analysis, image segmentation procedure, rule set approaches, nearest neighbor classifier using training samples, and limitations/uncertainties associated with object-based techniques reported in this chapter are applicable to urban mapping using any OBIA software.

Original languageEnglish (US)
Title of host publicationUrban Remote Sensing
Subtitle of host publicationMonitoring, Synthesis and Modeling in the Urban Environment
PublisherWiley-Blackwell
Pages129-140
Number of pages12
ISBN (Electronic)9780470979563
ISBN (Print)9780470749586
DOIs
StatePublished - Apr 13 2011

    Fingerprint

Keywords

  • Applicability and effectiveness of two different classification approaches - within object-oriented image analysis paradigm, a Quickbird multispectral data
  • Nearest neighbor classifier - extracting urban land covers
  • Object-based approaches, to semi-automated LULC mapping - remote sensing and image processing research
  • Object-oriented approach, additional selection - or modification of new training samples
  • Object-oriented classification - mapping urban LULC classes, Definiens software known as eCognition to achieve OBIA
  • Object-oriented pattern recognition approach - for urban classification
  • Remotely sensed image data - for identification and mapping of land-use and landcover (LULC) classes for urban environments
  • Rule set classifier, time consuming with difficulty in implementation - than identifying classes using a nearest neighbor classifier
  • Rule-based detection of swimming pools - one's expert knowledge, rule set for extracting a LULC class
  • Segmented objects, organized into image object levels - known as scale levels

ASJC Scopus subject areas

  • Engineering(all)
  • Earth and Planetary Sciences(all)

Cite this

Myint, S., & Stow, D. (2011). An Object-Oriented Pattern Recognition Approach for Urban Classification. In Urban Remote Sensing: Monitoring, Synthesis and Modeling in the Urban Environment (pp. 129-140). Wiley-Blackwell. https://doi.org/10.1002/9780470979563.ch9