GeoPAT: A toolbox for pattern-based information retrieval from large geospatial databases

Jasiewicz, Jarosław; Netzel, Paweł; Stepinski, T. F.

doi:10.1016/j.cageo.2015.04.002

Cited by 27 publications

(19 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we will investigate to release this QP problem to a linear problem, by using the expectation-maximization (EM) framework to release the hinge loss to a linear function. Moreover, we also plan to extend the proposed algorithm to different applications, e.g., bioinformatics [43,34,36,47], computer vision [32,37,6,31], and information retrieval [42,16,11,33].…”

Section: Discussionmentioning

confidence: 99%

Supervised learning of sparse context reconstruction coefficients for data representation and classification

Liu

Wang

Yin

et al. 2015

Neural Comput & Applic

View full text Add to dashboard Cite

Context of data points, which is usually defined as the other data points in a data set, has been found to paly important roles in data representation and classification. In this paper, we study the problem of using context of a data point for its classification problem. Our work is inspired by the observation that actually only very few data points are critical in the context of a data point for its representation and classification. We propose to represent a data point as the sparse linear combination of its context, and learn the sparse context in a supervised way to increase its discriminative ability. To this end, we proposed a novel formulation for context learning, by modeling the learning of context parameter and classifier in a unified objective, and optimizing it with an alternative strategy in an iterative algorithm. Experiments on three benchmark data set show its advantage over state-of-the-art context-based data representation and classification methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Supervised learning of sparse context reconstruction coefficients for data representation and classification

Liu

Wang

Yin

et al. 2015

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Because the presented algorithm is implemented as a module of the GeoPAT software (Jasiewicz et al, 2015) it is based on the same core concept of pattern-based analysis of categorical rasters as the rest of GeoPAT modules.…”

Section: Basic Conceptsmentioning

confidence: 99%

“…Our segmentation algorithm is implemented with two histogram-yielding signatures, one based on pattern features derived from a category co-occurrence matrix, and another based on pattern decomposition features. Both signatures are described in Jasiewicz et al (2015). Briefly, in the category co-occurrence signature (Barnsley and Barr, 1996;Chang and Krumm, 1999) pattern features are the pairs of raster categories assigned to two neighboring cells.…”

Section: Pattern Signaturementioning

confidence: 99%

“…The algorithm is implemented as a module within the Geospatial Pattern Analysis Toolbox (GeoPAT) (Jasiewicz et al, 2015) -an open source collection of GRASS GIS (Neteler et al, 2012) modules for carrying out pattern-based analysis of categorical rasters. The GeoPAT software, including the segmentation module described in this paper, can be downloaded from http://sil.uc.edu/.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-scale segmentation algorithm for pattern-based partitioning of large categorical rasters

Jasiewicz

Stepinski

Niesterowicz

2018

Computers & Geosciences

Self Cite

View full text Add to dashboard Cite

Analyzing large Earth Observation (EO) data on the broad spatial scales frequently involves regionalization of patterns. To automate this process we present a segmentation algorithm designed specifically to delineate segments containing quasi-stationary patterns. The algorithm is designed to work with patterns of a categorical variable. This makes it possible to analyze very large spatial datasets (for example, a global land cover) in their entirety. An input categorical raster is first tessellated into small square tiles to form a new, coarser, grid of tiles. A mosaic of categories within each tile forms a local pattern, and the segmentation algorithm partitions the grid of tiles while maintaining the cohesion of pattern in each segment. The algorithm is based on the principle of seeded region growing (SRG) but it also includes segment merging and other enhancements to segmentation quality. Our key contribution is an extension of the concept of segmentation to grids in which each cell has a non-negligible size and contains a complex data structure (histograms of pattern features). Specific modification of a standard SRG algorithm include: working in a distance space with complex data objects, introducing six-connected "brick wall" topology of the grid to decrease artifacts associated with tessellation of geographical space, constructing the SRG priority queue of seeds on the basis of local homogeneity of patterns, and using a content-dependent value of segment-growing threshold. The detailed description of the algorithm is given followed by an assessment of its performance on test datasets representing three pertinent themes of land cover, topography, and a high-resolution image. Pattern-based segmentation algorithm will find application in ecology, forestry, geomorphology, land management, and agriculture. The algorithm is implemented as a module of GeoPAT-an already existing, open source toolbox for performing pattern-based analysis of categorical rasters.

show abstract

“…The time from issuing a query to displaying a similarity map is about 10 sec. Such short wait time is achieved by an efficient computational engine (GeoPAT 2.0, a stand-alone extension of an original, GRASS GIS-based GeoPAT toolbox for pattern-based geoprocessing (Jasiewicz et al, 2015)), which is written in C and uses parallel computation based on the OpenMP library.…”

Section: Content-based Searchmentioning

confidence: 99%

TerraEx – a GeoWeb app for world-wide content-based search and distribution of elevation and landforms data

Netzel¹,

Jasiewicz²,

Stepinski³

2016

GIScience

Self Cite

View full text Add to dashboard Cite

Terrain Explorer (TerraEx) is the first world-wide content-based search application for landscapes. Using 3" resolution world-wide DEM as an input it finds and displays, in the form of a similarity map, locations in the world where landscapes are similar to a user-selected query. TerraEx is a freely available, full service GeoWeb application. It also doubles as the most convenient distributor of global 3" DEM data, the global map of geomorphons, and the global map of terrain relief. TerraEx opens a possibility to utilize publicly available DEM archives in their entireties for world-wide exploration through content-based search.

show abstract

GeoPAT: A toolbox for pattern-based information retrieval from large geospatial databases

Cited by 27 publications

References 43 publications

Supervised learning of sparse context reconstruction coefficients for data representation and classification

Supervised learning of sparse context reconstruction coefficients for data representation and classification

Multi-scale segmentation algorithm for pattern-based partitioning of large categorical rasters

TerraEx – a GeoWeb app for world-wide content-based search and distribution of elevation and landforms data

Contact Info

Product

Resources

About