The amount of scientific literature on (Geographic) Object-based Image Analysis – GEOBIA has been and still is sharply increasing. These approaches to analysing imagery have antecedents in earlier research on image segmentation and use GIS-like spatial analysis within classification and feature extraction approaches. This article investigates these development and its implications and asks whether or not this is a new paradigm in remote sensing and Geographic Information Science (GIScience). We first discuss several limitations of prevailing per-pixel methods when applied to high resolution images. Then we explore the paradigm concept developed by Kuhn (1962) and discuss whether GEOBIA can be regarded as a paradigm according to this definition. We crystallize core concepts of GEOBIA, including the role of objects, of ontologies and the multiplicity of scales and we discuss how these conceptual developments support important methods in remote sensing such as change detection and accuracy assessment. The ramifications of the different theoretical foundations between the ‘per-pixel paradigm’ and GEOBIA are analysed, as are some of the challenges along this path from pixels, to objects, to geo-intelligence. Based on several paradigm indications as defined by Kuhn and based on an analysis of peer-reviewed scientific literature we conclude that GEOBIA is a new and evolving paradigm.

Most of the largest rivers on Earth have multiple active channels connected at bifurcations and confluences. At present a method to describe a channel network pattern and changes in the network beyond the simplistic braiding index is unavailable. Our objectives are to test a network approach to understand the character, stability and evolution of a multi‐channel river pattern under natural discharge conditions. We developed a semi‐automatic method to derive a chain‐like directional network from images that represent the multi‐channel river and to connect individual network elements through time. The Jamuna River was taken as an example with a series of Landsat TM and ETM+ images taken at irregular intervals between 1999 and 2004. We quantified the overall importance of individual channels in the entire network using a centrality property. Centrality showed that three reaches can be distinguished along the Jamuna with a different network character: the middle reach has dominantly one important channel, while upstream and downstream there are about two important channels. Temporally, relatively few channels changed dramatically in both low‐flow and high‐flow periods despite the increase of braiding index during a flood. Based on the centrality we calculated a weighted braiding index that represents the number of important channels in the network, which is about two in the Jamuna River and which is larger immediately after floods. We conclude that the network measure centrality provides a novel characterization of river channel networks, highlighting properties and tendencies that have morphological significance. Copyright © 2013 John Wiley & Sons, Ltd.

The Vietnamese Mekong delta is subsiding due to a combination of natural and human-induced causes. Over the past several decades, large-scale anthropogenic land-use changes have taken place as a result of increased agricultural production, population growth and urbanization in the delta. Land-use changes can alter the hydrological system or increase loading of the delta surface, amplifying natural subsidence processes or creating new anthropogenic subsidence. The relationships between land use histories and current rates of land subsidence have so far not been studied in the Mekong delta. We quantified InSAR-derived subsidence rates for the various land-use classes and past land-use changes using a new, optical remote sensing-based, 20-year time series of land use. Lowest mean subsidence rates were found for undeveloped land-use classes, like marshland and wetland forest (~6-7mmyr), and highest rates for areas with mixed-crop agriculture and cities (~18-20mmyr). We assessed the relationship strength between current land use, land-use history and subsidence by predicting subsidence rates during the measurement period solely based on land-use history. After initial training of all land-use sequences with InSAR-derived subsidence rates, the land-use-based approach predicted 65-92% of the spatially varying subsidence rates within the measurement error range of the InSAR observations (RMSE=5.8mm). As a result, the spatial patterns visible in the observed subsidence can largely be explained by land use. We discuss in detail the dominant land-use change pathways and their indirect, causal relationships with subsidence. Our spatially explicit evaluation of these pathways provides valuable insights for policymakers concerned with land-use planning in both subsiding and currently stable areas of the Mekong delta and similar systems.

In recent years, object-oriented image analysis has been widely adopted by the remote sensing community. Much attention has been given to its application, while the fundamental issue of scale, here characterized by spatial object-definition, seems largely neglected. In the case of vegetation parameters like aboveground biomass and leaf area index (LAI), fundamental objects are individual trees or shrubs, each of which has a specific value. Their spatial extent, however, does not match pixels in size and shape, nor does it fit the requirements of regional studies. Estimation of vegetation parameters consequently demands larger observation units, like vegetation patches, which are better represented by variably shaped objects than by square pixels. This study aims to investigate optimal object definition for biomass and LAI. We have data from 243 field plots in our test site in southern France. They cover a vegetation range from landes to garrigue to maquis, which is considered to be the climax vegetation in the area. A HyMap image covers the area. The image is subjected to a Minimum Noise Fraction (MNF) transformation, after which it is segmented with ten different heterogeneities. The result is ten object sets, each having a different mean object size. These object sets are combined with the original image with the mean band values serving as object attributes. Field observations are linked to the corresponding objects for each object set. Using Ridge regression, relations between field observations and spectral values are identified. The prediction error is determined for each object set by cross validation. The overall lowest prediction error indicates the optimal heterogeneity for segmentation. Results show that the scale of prediction affects prediction accuracy, that increasing the object size yields an optimum in prediction accuracy, and that aboveground biomass and LAI can be associated with different optimal object sizes. Furthermore, it is shown that the accuracy of parameter estimation is higher for object-oriented analysis than for per-pixel analysis.

No abstract