Image classification is a complex process that may be affected by many factors. This paper examines current practices, problems, and prospects of image classification. The emphasis is placed on the summarization of major advanced classification approaches and the techniques used for improving classification accuracy. In addition, some important issues affecting classification performance are discussed. This literature review suggests that designing a suitable image-processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map. Effective use of multiple features of remotely sensed data and the selection of a suitable classification method are especially significant for improving classification accuracy. Non-parametric classifiers such as neural network, decision tree classifier, and knowledge-based classification have increasingly become important approaches for multisource data classification. Integration of remote sensing, geographical information systems (GIS), and expert system emerges as a new research frontier. More research, however, is needed to identify and reduce uncertainties in the image-processing chain to improve classification accuracy.

/pdf/a-survey-of-image-classification-methods-and-techniques-for-5bc5ltr9dq.pdf

A survey of image classification methods and techniques for improving classification performance

Estimation of land surface temperature-vegetation abundance relationship for urban heat island studies

This paper presents an overview of multi-agent system models of land-use/cover change (MAS/LUCC models). This special class of LUCC models combines a cellular landscape model with agent-based representations of decisionmaking, integrating the two components through specification of interdependencies and feedbacks between agents and their environment. The authors review alternative LUCC modeling techniques and discuss the ways in which MAS/LUCC models may overcome some important limitations of existing techniques. We briefly review ongoing MAS/LUCC modeling efforts in four research areas. We discuss the potential strengths of MAS/LUCC models and suggest that these strengths guide researchers in assessing the appropriate choice of model for their particular research question. We find that MAS/LUCC models are particularly well suited for representing complex spatial interactions under heterogeneous conditions and for modeling decentralized, autonomous decision making. We discuss a range of possible roles for MAS/LUCC models, from abstract models designed to derive stylized hypotheses to empirically detailed simulation models appropriate for scenario and policy analysis. We also discuss the challenge of validation and verification for MAS/LUCC models. Finally, we outline important challenges and open research questions in this new field. We conclude that, while significant challenges exist, these models offer a promising new tool for researchers whose goal is to create fine-scale models of LUCC phenomena that focus on human-environment interactions.

http://www.dpi.inpe.br/cursos/tutoriais/modelagem/referencias/agents_lucc_overview.pdf

Multi-Agent Systems for the Simulation of Land-Use and Land-Cover Change: A Review

Over the last ten years, scholars in human geography have been paying increasing theoretical and empirical attention to understanding the ways in which the production of scale is implicated in the production of space. Overwhelmingly, this work reflects a social constructionist approach, which situates capitalist production (and the role of the state, capital, labor and nonstate political actors) as of central concern. What is missing from this discussion about the social construction of scale is serious attention to the relevance of social reproduction and consumption. In this article I review the important literature on scale construction and argue for enlarging our scope for understanding scale to include the complex processes of social reproduction and consumption. I base my critique on a short case study which illustrates that attention to other processes besides production and other systems of domination besides capitalism can enhance our theorizing and improve our attempts to effect real social change.

/pdf/the-social-construction-of-scale-10gu8u0ns1.pdf

The social construction of scale

Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends

Introduction: Scale, Multiscaling, Remote Sensing, and GIS, M.F. Goodchild and D.A. Quattrochi Multiscale Nature of Spatial Data in Scaling Up Environmental Models, L. Bian Scale Dependence of NDVI and its Relationship to Mountainous Terrain, S.J. Walsh, A. Moody, T.R. Allen, and D.G. Brown Understanding the Scale and Resolution Effects in Remote Sensing and GIS, C.-Y. Cao and N. S.-N. Lam Multiresolution Covariation among Landsat and AVHRR Vegetation Indices, L. De Cola Multiscaling Analysis in Distributed Modeling and Remote Sensing: An Application Using Soil Moisture, R. Dubayah, E.F. Wood, and D. Lavallee Examining the Effects of Sensor Resolution and Sub-Pixel Heterogeneity on Spectral Vegetation Indices: Implications for Biophysical Modeling, M.A. Friedl Multiscale Vegetation Data for the Mountains of Southern California: Spatial and Categorical Resolution, J. Franklin and C.E. Woodcock The Use of Remotely Sensed Surface Temperatures from an Aircraft-Based Thermal Infrared Multispectral Scanner (TIMS) to Estimate the Spatial and Temporal Variability of Latent Heat Fluxes and Thermal Response Numbers from a White Pine (Pinus strobus L.) Plantation, J.C. Luvall Scaling Predicted Pine Forest Hydrology and Productivity across the Southern United States, S.G. McNulty, J.M. Vose, and W.T. Swank Modeling Effects of Spatial Pattern, Drought, and Grazing on Rates of Rangeland Degradation: A Combined Markov and Cellular Automaton Approach, H. Li and J.F. Reynolds Scaling Land Cover Heterogeneity for Global Atmosphere-Biosphere Models, R.S. DeFries, J.R. Townshend, and S.O. Los Quadtrees: Hierarchical Multiresolution Data Structures for Analysis of Digital Images, F. Csillag Statistical Models for Multiple Scaled Analysis, D.E. Myers Image Characterization and Modeling System (ICAMS): A Geographic Information System for the Characterization and Modeling of Multiscale Remote Sensing Data, D.A. Quattrochi, N. S.-N. Lam, H.-L. Qiu, and W. Zhao Approaches to Scaling of Geo-Spatial Data, Z.-G. Xia and K.C. Clarke Multifractals and Remotely Sensed Data: Generalized Scale Invariance, Geographical Information Systems and Resolution Dependence, S. Pecknold, S. Lovejoy, D. Schertzer, and C. Hooge Index

Scale in remote sensing and GIS

We investigate the direct relationship between detailed urban land cover classes, derived from fine resolution QuickBird satellite data, and land surface temperatures (Celsius), generated from ASTER imagery, over Phoenix, Arizona. Using daytime and nighttime temperatures in both winter and summer and all observation points (n = 11,025), we develop linear, non-linear and multiple regression models to explore the relationship. Conventional wisdom suggests that all urban features result in increased temperatures. Rather, our results show that a mass of buildings is not necessarily or holistically responsible for extreme heat in desert cities. It is the construction of other impervious dark surfaces (i.e., asphalt roads) associated with buildings that result in extreme heat. Moreover, our results suggest that buildings, especially commercial buildings with high albedo roofs, actually reduce temperatures. The addition of trees and shrubs, as opposed to grass, around buildings can further mitigate extreme heat by providing more cooling during the summer and increasing nighttime temperatures in the winter. In conclusion, the compositional design of and avoidance of dark impervious materials in desert cities help mitigate extreme temperatures. It is important to note, however, that design choices that reduce extreme heat must be made within the broader context of tradeoffs and unintended consequences to ensure the sustainability of these cities.

/pdf/the-impact-of-distinct-anthropogenic-and-vegetation-features-gzp0w0w8bu.pdf

The impact of distinct anthropogenic and vegetation features on urban warming

Previously, we developed an integrated software package called ICAMS (Image Characterization and Modeling System) to provide specialized spatial analytical functions for interpreting remote sensing data. This paper evaluates three fractal dimension measurement methods that have been implemented in ICAMS: isarithm, variogram, and a modified version of triangular prism. To provide insights into how the fractal methods compare with conventional spatial techniques in measuring landscape complexity, the performance of two spatial autocorrelation methods, Moran's I and Geary's C, is also evaluated. Results from analyzing 25 simulated surfaces having known fractal dimensions show that both the isarithm and triangular prism methods can accurately measure a range of fractal surfaces. The triangular prism method is most accurate at estimating the fractal dimension of surfaces having higher spatial complexity, but it is sensitive to contrast stretching. The variogram method is a comparatively poor estimator for all ...

An evaluation of fractal methods for characterizing image complexity

Two Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) hyperspectral images selected from the Los Angeles area, one representing urban and the other, rural, were used to examine their spatial complexity across their entire spectrum of the remote sensing data. Using the ICAMS (Image Characterization And Modeling System) software, we computed the fractal dimension values via the isarithm and triangular prism methods for all 224 bands in the two AVIRIS scenes. The resultant fractal dimensions reflect changes in image complexity across the spectral range of the hyperspectral images. Both the isarithm and triangular prism methods detect unusually high D values on the spectral bands that fall within the atmospheric absorption and scattering zones where signature to noise ratios are low. Fractal dimensions for the urban area resulted in higher values than for the rural landscape, and the differences between the resulting D values are more distinct in the visible bands. The triangular prism method is sensitive to a few random speckles in the images, leading to a lower dimensionality. On the contrary, the isarithm method will ignore the speckles and focus on the major variation dominating the surface, thus resulting in a higher dimension. It is seen where the fractal curves plotted for the entire bandwidth range of the hyperspectral images could be used to distinguish landscape types as well as for screening noisy bands.

Fractal Characterization of Hyperspectral Imagery

In their report entitled ‘State of the World Cities 2006/7’ (United Nations, 2006) the UN predicts that globally, 2007 will see more people living in urban rather than rural areas. The number of urban dwellers is predicted to rise to almost 5 billion by 2030, which will be 62% of the estimated global population of 8.1 billion. Cities and urban areas will have to expand to accommodate such increases in population, resulting in a variety of social and environmental problems. The key to successfully survive the rapid urbanization of the countryside is to provide accurate and timely spatial information that will assist decisionmakers in understanding, managing, and planning the continuously changing environment. The synoptic view of cities afforded by Earth Observation (EO)1 offers great potential for data collection over urban areas. With some major paradigm shifts in EO technology over the last 30 years, it is appropriate to examine how EO can now be better harnessed to assist urban planners and managers, and what issues should be exploited by the research and academic community to further its practical application. To this end, a workshop on Earth Observation for Urban Planning and Management was held on November 20-21st 2006 in Hong Kong. Hong Kong’s status as possibly the world’s most densely built modern city, and thus being in need of the most innovative and efficient planning procedures available, provided the catalyst for this meeting. Critical issues were examined with Hong Kong being the point of reference. Delegates comprised an international group of researchers and practitioners from Hong Kong government departments, providing a mixture of top-down demonstrations and case studies, with bottom-up feedback from user groups. The workshop addressed 4 major application areas: environmental monitoring, land use/cover mapping, planning, and geotechnical monitoring. Resulting from the workshop, observations were made on current and potential applications of EO technology, current data qualities and acquisition technologies, major impediments to their more widespread use, and recommendations for future development. This article discusses the Workshop's proceedings, findings, and observations dealing with the aforementioned issues.

Dale A. Quattrochi

Papers

Scale in remote sensing and GIS

The impact of distinct anthropogenic and vegetation features on urban warming

An evaluation of fractal methods for characterizing image complexity

Fractal Characterization of Hyperspectral Imagery

Earth Observation for Urban Planning and Management: State of the Art and Recommendations for Application of Earth Observation in Urban Planning