Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing

Tobin, Kenneth W.; Bhaduri, Budhendra; Bright, Eddie A; Cheriydat, Anil; Karnowski, Thomas P.; Palathingal, Paul J.; Potok, Thomas E.; Price, Jeffery R.

doi:10.14358/pers.72.5.531

Cited by 36 publications

(22 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to other domains, researchers have investigated intensity features [24], spectral (color) features [25], [26], shape features [27]- [30], structural features [31], [32], texture features [29], [30], [33]- [37], and combinations thereof such as multi-spectral texture features [38]. However, to our knowledge, ours is the first work to investigate local invariant features for geographic image retrieval.…”

Section: Introductionmentioning

confidence: 99%

Geographic Image Retrieval Using Local Invariant Features

Yang

Newsam

2013

IEEE Trans. Geosci. Remote Sensing

330

254

View full text Add to dashboard Cite

This paper investigates local invariant features for geographic (overhead) image retrieval. Local features are particularly well suited for the newer generations of aerial and satellite imagery whose increased spatial resolution, often just tens of centimeters per pixel, allows a greater range of objects and spatial patterns to be recognized than ever before. Local invariant features have been successfully applied to a broad range of computer vision problems and, as such, are receiving increased attention from the remote sensing community particularly for challenging tasks such as detection and classification. We perform an extensive evaluation of local invariant features for image retrieval of land-use/land-cover (LULC) classes in high-resolution aerial imagery. We report on the effects of a number of design parameters on a bag-of-visual-words (BOVW) representation including saliency-versus grid-based local feature extraction, the size of the visual codebook, the clustering algorithm used to create the codebook, and the dissimilarity measure used to compare the BOVW representations. We also perform comparisons with standard features such as color and texture. The performance is quantitatively evaluated using a first-of-its-kind LULC ground truth data set which will be made publicly available to other researchers. In addition to reporting on the effects of the core design parameters, we also describe interesting findings such as the performance-efficiency tradeoffs that are possible through the appropriate pairings of different-sized codebooks and dissimilarity measures. While the focus is on image retrieval, we expect our insights to be informative for other applications such as detection and classification.Index Terms-Bag of visual words, content-based image retrieval, high-resolution overhead image analysis, land cover, land use, local invariant features, remote sensing.

show abstract

Section: Introductionmentioning

confidence: 99%

Geographic Image Retrieval Using Local Invariant Features

Yang

Newsam

2013

IEEE Trans. Geosci. Remote Sensing

330

254

View full text Add to dashboard Cite

show abstract

“…We build feature vectors using statistical features derived from GLCM matrices and local edge pattern (LEP) matrices. Previous work by Tobin et al (2006) related to content-based image retrieval show that LEPs characterize urban regions effectively.…”

Section: Related Workmentioning

confidence: 97%

Mapping of settlements in high-resolution satellite imagery using high performance computing

et al. 2007

Self Cite

View full text Add to dashboard Cite

Classifying urban land cover from highresolution satellite imagery is challenging, and those challenges are compounded when the imagery databases are very large. Accurate land cover data is a crucial component of the population distribution modeling efforts of the Oak Ridge National Laboratory's (ORNL) LandScan Program. Currently, LandScan Program imagery analysts manually interpret high-resolution (1-5 m) imagery to augment existing satellite-derived medium (30 m) and coarse (1 km) resolution land cover datasets. For LandScan, the high-resolution image archives that require interpretation are on the order of terabytes. The goal of this research is to automate human settlement mapping by utilizing ORNL's high performance computing capabilities. Our algorithm employs gray-level and local edge-pattern co-occurrence matrices to generate texture and edge patterns. Areas of urban land cover correlate with statistical features derived from these texture and edge patterns. We have parallelized our algorithms for implementation on a 64-node system using a single instruction multiple data programming model (SIMD) with Message Passing Interface (MPI) as the communication mode. Our parallel-configured classifier performs 30-40 times faster than stand-alone alternatives. We have tested our system on IKONOS imagery. The early results are promising, pointing towards future large-scale classification of human settlements at high-resolution.

show abstract

“…This data model is amenable for the seamless integration with the data in any other RDF repository over the web, and thus, EO data can be put into the global data space (the Web of Data). To achieve this task, we have added external RDF links in the SIIM RDF repository, which links the data from our repository to other, such as GeoNames 5 repository, DBpedia, 6 and linked geo data. 7 Section III gives the more details on this semantic modeling of the EO data in SIIM and the examples on how the linked EO data repository is developed and implemented in SIIM.…”

Section: Framework For Semantics-enabled Spatial Image Informatiomentioning

confidence: 99%

“…Furthermore, to incorporate formal semantics into an image retrieval system [intelligent interactive image knowledge retrieval (I3KR)], an ontology, and a SVM-based machine learning approach was developed to model the domain-dependent semantics for enhanced knowledge-driven exploration and the retrieval of images [2]. A region-based image retrieval (RBIR) system was developed, which extracts low-level features from regions and indexed by a k-D tree to retrieve the RS images [6]. The geospatial information retrieval system (GeoIRIS) [7] facilitated a query-by-example and query-by-geographic/man-made features to query RS image archives.…”

mentioning

confidence: 99%

Semantics-Enabled Framework for Spatial Image Information Mining of Linked Earth Observation Data

Kurte

Durbha

King

et al. 2017

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Recent developments in sensor technology are contributing toward the tremendous growth of remote sensing (RS) archives (currently, at the petabyte scale). However, this data largely remain unexploited due to the current limitations in the data discovery, querying, and retrieval capabilities. This issue becomes exacerbated in disaster situations, where there is a need for rapid processing and retrieval of the affected areas. Furthermore, the retrieval of images based on the spatial configurations of affected regions [land use/cover (LULC) classes] in an image is important in disaster situations such as floods and earthquakes. The majority of existing Earth observation (EO) image information mining (IIM) systems does not consider the spatial relations among image regions during image retrieval (aka spatial semantic gap). In this work, we have specifically addressed two issues, i.e., explicit modeling of topological and directional relationships between image regions, and development of a resource description framework (RDF)-based spatial semantic graphs (SSGs). This enables more intuitive querying and reasoning on the archived data. A spatial IIM (SIIM) framework isproposed, which integrates a logic-based reasoning mechanism to extract the hidden spatial relationships (both topological and directional) and enables image retrieval based on spatial relationships. The system is tested using several spatial relations-based queries on the RS image repository of flood-affected areas to check its applicability in post flood scenario. Precision, recall, and F-measure metrics were used to evaluate the performance of the SIIM system, which showed good potential for spatial relations-based image retrieval.Index Terms-Description logic (DL), direction relations, image retrieval, linked data, reasoning, region connection calculus (RCC-8), resource description framework (RDF), semantic web rules language (SWRL), SPARQL, spatial image information mining (SIIM), spatial relations, topological relations, Web ontology language (OWL).

show abstract

Automated Feature Generation in Large-Scale Geospatial Libraries for Content-Based Indexing

Cited by 36 publications

References 9 publications

Geographic Image Retrieval Using Local Invariant Features

Geographic Image Retrieval Using Local Invariant Features

Mapping of settlements in high-resolution satellite imagery using high performance computing

Semantics-Enabled Framework for Spatial Image Information Mining of Linked Earth Observation Data

Contact Info

Product

Resources

About