Image analysis: Difference between revisions

Revision as of 08:40, 12 April 2020

Revision as of 02:19, 9 July 2020

Line 44:

[[File:Object based image analysis.jpg|thumb|Image segmentation during the

object base image analysis]]

''Object-Based Image Analysis'' (OBIA) employs two main processes, segmentation and classification. Traditional image segmentation is on a per-pixel basis. However, OBIA groups pixels into homogeneous objects. These objects can have different shapes and scale. Objects also have statistics associated with them which can be used to classify objects. Statistics can include geometry, context and texture of image objects. The analyst defines statistics in the classification process to generate for example [[land cover]]. The technique is implemented in software such as [[eCognition]] or the [[Orfeo toolbox]].

{{anchor|GEOBIA}}When applied to earth images, OBIA is known as ''Geographic Object-Based Image Analysis'' (GEOBIA), defined as "a sub-discipline of [[geoinformation]] science devoted to (...) partitioning [[remote sensing]] (RS) imagery into meaningful image-objects, and assessing their characteristics through spatial, spectral and temporal scale".<ref>G.J. Hay & G. Castilla: ''Geographic Object-Based Image Analysis (GEOBIA): A new name for a new discipline.'' In: T. Blaschke, S. Lang & G. Hay (eds.): Object-Based Image Analysis – Spatial Concepts for Knowledge-Driven Remote Sensing Applications. Lecture Notes in Geoinformation and Cartography, 18. Springer, Berlin/Heidelberg, Germany: 75-89 (2008)</ref><ref name="Blaschke Hay Kelly Lang 2014 pp. 180–191">{{cite journal | last=Blaschke | first=Thomas | last2=Hay | first2=Geoffrey J. | last3=Kelly | first3=Maggi | last4=Lang | first4=Stefan | last5=Hofmann | first5=Peter | last6=Addink | first6=Elisabeth | last7=Queiroz Feitosa | first7=Raul | last8=van der Meer | first8=Freek | last9=van der Werff | first9=Harald | last10=van Coillie | first10=Frieke | last11=Tiede | first11=Dirk | title=Geographic Object-Based Image Analysis – Towards a new paradigm | journal=ISPRS Journal of Photogrammetry and Remote Sensing | publisher=Elsevier BV | volume=87 | year=2014 | issn=0924-2716 | doi=10.1016/j.isprsjprs.2013.09.014 | pages=180–191}}</ref>

The international GEOBIA conference has been held biannually since 2006.<ref>[http://www.mdpi.com/journal/remotesensing/special_issues/geobia]</ref>

Object-based image analysis is also applied in other fields, such as cell biology or medicine. It can for instance detect changes of cellular shapes in the process of cell differentiation.<ref>{{Cite journal|last=Salzmann|first=M.|last2=Hoesel|first2=B.|last3=Haase|first3=M.|last4=Mussbacher|first4=M.|last5=Schrottmaier|first5=W. C.|last6=Kral-Pointner|first6=J. B.|last7=Finsterbusch|first7=M.|last8=Mazharian|first8=A.|last9=Assinger|first9=A.|date=2018-02-20|title=A novel method for automated assessment of megakaryocyte differentiation and proplatelet formation|journal=Platelets|volume=29|issue=4|pages=357–364|doi=10.1080/09537104.2018.1430359|issn=1369-1635|pmid=29461915|url=https://research.birmingham.ac.uk/portal/files/48276169/A_novel_method_for_automated_assessment_of_megakaryocyte_differentiation_and_proplatelet_formation.pdf}}</ref>

The technique is implemented in software such as [[eCognition]] or the [[Orfeo toolbox]].

== Land cover mapping ==