A multi-scale segmentation/object relationship modelling methodology for landscape analysis

By Charles Burnett, Thomas Blaschke. 2003

640 citations recorded by the source corpus.

Subfields: Ecology, Global and Planetary Change, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/6c8a248bf553d4ea823b18cc86a12b2673bb1301

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Global and Planetary Change

In Nature and Landscape Conservation

Citations in the corpus

Object‐based land‐cover classification for the Phoenix metropolitan area: optimization vs. transportability (2008, methodology): “…between images for pixel by pixel comparisons; (4) accounting for changing spectral responses over season and time; and (5) multiple features contributing to the spectral responses of a single pixel, creating mixed pixels (Narumalani et al. 1998, Read and Lam 2002, Burnett and Blaschke 2003).”
Land-cover classification with high-resolution remote sensing images using transferable deep models (2018, background): “…RS images using the spectral features of individual pixels (Jensen and Lulla, 1986; Gong et al., 1992; Casals-Carrasco et al., 2000), but their performance is often heavily affected by intra-class spectral variations and noises (Blaschke, 2001; Burnett and Blaschke, 2003; Benz et al., 2004).”
Multivariate correlations between imagery and field measurements across scales: comparing pixel aggregation and image segmentation (2010, background): “The result is a minimization of the average object heterogeneity across the image (Burnett and Blaschke 2003).”
Remotely sensed spectral heterogeneity as a proxy of species diversity: Recent advances and open challenges (2010, background): “…of this review where the issue is discussed”. generating patches in an objective manner at a given specified scale, by maintaining the topological and hierarchical structure of the landscape overmultiple scales (Hay et al., 2001; Burnett and Blaschke, 2003; Marignani et al., 2008; Blaschke, 2010).”
Automated classification of landform elements using object-based image analysis (2006, methodology): “In this paper, we have demonstrated that a multiscale image segmentation/ object relationship modeling methodology (MSS/ORM, cf. Burnett and Blaschke, 2003) can also be efficiently used for geomorphometry and terrain classification.”
Accounting for uncertainty when mapping species distributions: The need for maps of ignorance (2011, background): “Finescale distributions are much patchier than any of the most detailed expert-drawn range maps can account for (see Graham and Hijmans, 2006; Hurlbert and Jetz, 2007), a human limit that has been already explored in other fields of cartography (Burnett and Blaschke, 2003).”
A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images (2006, background): “Moreover, other aspects considered in this analysis are: 1) that objects at the same level are logically related to each other and 2) that each object at a generic level is hierarchically related to those at the higher and lower levels [7], [8], [13], [14].”
ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data (2010, methodology): “Therefore, users should carefully decide between using either a multiscale segmentation (MSS) (Burnett and Blaschke 2003) or a one-level representation (OLR) approach (Lang and Langanke 2006), in order to use the tool appropriately.”
Object based image analysis for remote sensing (2010, methodology): “, 2001, 2003), and OBIA is inextricably linked to multiscale analysis concepts (Burnett and Blaschke, 2003; Benz et al., 2004; Lang, 2008; Hay and Castilla, 2008), even if single levels are targeted for specific applications (Lang and Langanke, 2006; Lang, 2008; Weinke et al.”
Are landscapes as crisp as we may think (2007, background): “Many studies on the effects of scale-dependence in landscape analysis are aimed at understanding the effect of arbitrarily grouped spatial phenomena on pattern-process relationships (e.g., Burnett and Blaschke, 2003).”
Simulation modelling of ecological hierarchies in constructive dynamical systems (2007, background): “The phenomenon grain corresponds to the minimum spatio-temporal size at which an object reacts to the external dynamics, and the extent as the reach or span of its interactions (Burnett and Blaschke, 2003).”
Analyzing High Resolution Topography for Advancing the Understanding of Mass and Energy Transfer Through Landscapes: A Review (2015, background): “Clearly, objects exist across a variety of scales in HRT, and so segmentation often requires a multi-scale analysis (Hay et al., 2001, 2003; Burnett and Blaschke, 2003; Schmidt and Andrew, 2005; Brodu and Lague, 2012).”
Geographic Object-Based Image Analysis – Towards a new paradigm (2014, positive): “Multi-scale segmentation has often been linked with hierarchy theory (Hay et al., 2001; Burnett and Blaschke, 2003; Lang, 2008).”
Assessment of Very High Spatial Resolution Satellite Image Segmentations (2005, background): “If the smallest PHOTOGRAMMETRIC ENGINEER ING & REMOTE SENS ING Novembe r 2005 1287 growth exceeds a heterogeneity tolerance defined by the user, the process stops (Definiens Imaging, 2003; Burnett and Blaschke, 2003; van der Sande et al., 2003).”
Geographic Object-Based Image Analysis (GEOBIA): A new name for a new discipline (2008, methodology): “E GEOBIA concepts and tools also have the potential to be used in the operationalization of existing ecological theories ( Burnett and Blaschke, 2003 ) such as the Hierarchical Patch Dynamics Paradigm (HPDP, Wu, 1999), which provides a conceptual framework for guiding and explaining the hierarchical”
Object-based contextual image classification built on image segmentation (2003, methodology): “Recently, [11] developed a five step methodology for landscape analysis built on this multiscale segmentation and called it multiscale segmentation / object relationship modeling (MSS/ORM).”
A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification (2016, methodology): “To represent HRS images on multiple scales, three main methods are utilized: image pyramid [6], wavelet transform [7] and hierarchical image partitions [8].”