scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Remote sensing methods in medium spatial resolution satellite data land cover classification of large areas

01 Jun 2002-Progress in Physical Geography (Sage Publications)-Vol. 26, Iss: 2, pp 173-205
TL;DR: The objective of this paper is to review and assess general medium spatial resolution satellite remote sensing land cover classification approaches with the goal of identifying the outstanding issues that must be overcome in order to implement a large-area, land cover classified protocol.
Abstract: Numerous large-area, multiple image-based, multiple sensor land cover mapping programs exist or have been proposed, often within the context of national forest monitoring, mapping and modelling initiatives, worldwide. Common methodological steps have been identified that include data acquisition and preprocessing, map legend development, classification approach, stratification, incorporation of ancillary data and accuracy assessment. In general, procedures used in any large-area land cover classification must be robust and repeatable; because of data acquisition parameters, it is likely that compilation of the maps based on the classification will occur with original image acquisitions of different seasonality and perhaps acquired in different years and by different sensors. This situation poses some new challenges beyond those encountered in large-area single image classifications. The objective of this paper is to review and assess general medium spatial resolution satellite remote sensing land cover cl...
Citations
More filters
Journal ArticleDOI
TL;DR: It is suggested that designing a suitable image‐processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map and the selection of a suitable classification method is especially significant for improving classification accuracy.
Abstract: 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.

2,741 citations

Journal ArticleDOI
TL;DR: In this paper, the performance of the random forest classifier for land cover classification of a complex area is explored based on several criteria: mapping accuracy, sensitivity to data set size and noise.
Abstract: Land cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance. However, the split rules for classification are unknown, therefore RF can be considered to be black box type classifier. RF provides an algorithm for estimating missing values; and flexibility to perform several types of data analysis, including regression, classification, survival analysis, and unsupervised learning. In this paper, the performance of the RF classifier for land cover classification of a complex area is explored. Evaluation was based on several criteria: mapping accuracy, sensitivity to data set size and noise. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land categories in the south of Spain. Results show that the RF algorithm yields accurate land cover classifications, with 92% overall accuracy and a Kappa index of 0.92. RF is robust to training data reduction and noise because significant differences in kappa values were only observed for data reduction and noise addition values greater than 50 and 20%, respectively. Additionally, variables that RF identified as most important for classifying land cover coincided with expectations. A McNemar test indicates an overall better performance of the random forest model over a single decision tree at the 0.00001 significance level.

1,901 citations

Journal ArticleDOI
TL;DR: A variety of ecological applications require data from broad spatial extents that cannot be collected using field-based methods, such as identifying and detailing the biophysical characteristics of species' habitats, predicting the distribution of species and spatial variability in species richness.
Abstract: A variety of ecological applications require data from broad spatial extents that cannot be collected using field-based methods. Remote sensing data and techniques address these needs, which include identifying and detailing the biophysical characteristics of species' habitats, predicting the distribution of species and spatial variability in species richness, and detecting natural and human-caused change at scales ranging from individual landscapes to the entire world. Such measurements are subject to substantial errors that can be difficult to overcome, but corrected data are readily available and can be of sufficiently high resolution to be integrated into traditional field-based studies. Ecologists and conservation biologists are finding new ways to approach their research with the powerful suite of tools and data from remote sensing.

1,292 citations

Journal ArticleDOI
TL;DR: In this paper, a relative version of the dNBR based on field data from 14 fires in the Sierra Nevada mountain range of California, USA was presented, which can be used for landscape level analysis.

980 citations


Cites methods from "Remote sensing methods in medium sp..."

  • ...Pre-classification stratification by vegetation or cover type is a strategy that has been successfully employed to create homogeneous landscapes out of heterogeneous ones (Brewer et al., 2005; Ekstrand, 1994; Franklin & Wulder, 2002; Miller & Yool, 2002; Strahler, 1981; White et al., 1996)....

    [...]

Journal ArticleDOI
TL;DR: In this paper, pixel-based and object-based image analysis approaches for classifying broad land cover classes over agricultural landscapes are compared using three supervised machine learning algorithms: decision tree (DT), random forest (RF), and the support vector machine (SVM).

785 citations

References
More filters
Journal ArticleDOI
01 Nov 1973
TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Abstract: Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This paper describes some easily computable textural features based on gray-tone spatial dependancies, and illustrates their application in category-identification tasks of three different kinds of image data: photomicrographs of five kinds of sandstones, 1:20 000 panchromatic aerial photographs of eight land-use categories, and Earth Resources Technology Satellite (ERTS) multispecial imagery containing seven land-use categories. We use two kinds of decision rules: one for which the decision regions are convex polyhedra (a piecewise linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89 percent for the photomicrographs, 82 percent for the aerial photographic imagery, and 83 percent for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.

20,442 citations


"Remote sensing methods in medium sp..." refers background in this paper

  • ...Insight into how texture might be analysed by computer has focused on the structural and statistical properties of textures (Haralick et al., 1973; Haralick, 1986); subsequently, much effort has been expended on optimizing satellite image texture measures for the land cover mapping application…...

    [...]

  • ...Insight into how texture might be analysed by computer has focused on the structural and statistical properties of textures (Haralick et al., 1973; Haralick, 1986); subsequently, much effort has been expended on optimizing satellite image texture measures for the land cover mapping application (Shih and S....

    [...]

Journal ArticleDOI
TL;DR: A FORTRAN-IV coding of the fuzzy c -means (FCM) clustering program is transmitted, which generates fuzzy partitions and prototypes for any set of numerical data.

5,287 citations


"Remote sensing methods in medium sp..." refers background or methods in this paper

  • ...A classifier that is nonparametric and thus can use a range of data types, including ratiolevel data, would be needed in these situations (Bezdek et al., 1984; Cannon et al., 1986; Lee et al., 1987; Benediktsson et al., 1990; Peddle, 1995; Jensen et al., 1999; Trichon et al., 1999; Hall et al.,…...

    [...]

  • ...A classifier that is nonparametric and thus can use a range of data types, including ratiolevel data, would be needed in these situations (Bezdek et al., 1984; Cannon et al., 1986; Lee et al., 1987; Benediktsson et al., 1990; Peddle, 1995; Jensen et al., 1999; Trichon et al., 1999; Hall et al., 2000)....

    [...]

  • ...…al., 1990; Bolstad and Lillesand, 1991, 1992; McCaffrey and Franklin, 1993; Bauer et al., 1994 Selection of the decision rule Swain and Davis, 1978; Bezdek et al., 1984; Lee et al., 1987; Benediktsson et al., 1990; Peddle, 1995; Adams et al., 1995; Foody, 1996; Friedl et al., 1999 Validation of…...

    [...]

BookDOI
17 Sep 1998
TL;DR: This chapter discusses Accuracy Assessment, which examines the impact of sample design on cost, statistical Validity, and measuring Variability in the context of data collection and analysis.
Abstract: Introduction Why Accuracy Assessment? Overview Historical Review Aerial Photography Digital Assessments Data Collection Considerations Classification Scheme Statistical Considerations Data Distribution Randomness Spatial Autocorrelation Sample Size Sampling Scheme Sample Unit Reference Data Collection Basic Collection Forms Basic Analysis Techniques Non-Site Specific Assessments Site Specific Assessments Area Estimation/Correction Practicals Impact of Sample Design on Cost Recommendations for Collecting Reference Data ASources of Variation in Reference Data Photo Interpretation vs. Ground Visitation Interpreter Variability Observations vs. Measurements What is Correct? Labeling Map vs. Labeling the Reference Data Qualitative vs. Quantitative Analysis Local vs. Regional vs. Global Assessments Advanced Topics Beyond the Error Matrix Modifying the Error Matrix Fuzzy Set Theory Measuring Variability Complex Data Sets Change Detection Multi-Layer Assessments California Hardwood Rangeland Monitoring Project Case Study Balancing Statistical Validity with Practical Reality Bibliography

4,586 citations

OtherDOI
01 Jan 1976
TL;DR: The framework of a national land use and land cover classification system is presented for use with remote sensor data and uses the features of existing widely used classification systems that are amenable to data derived from re-mote sensing sources.
Abstract: The framework of a national land use and land cover classification system is presented for use with remote sensor data. The classification system has been developed to meet the needs of Federal and State agencies for an up-to-date overview of land use and land cover throughout the country on a basis that is uniform in categorization at the more generalized first and second levels and that will be receptive to data from satellite and aircraft remote sensors. The pro-posed system uses the features of existing widely used classification systems that are amenable to data derived from re-mote sensing sources. It is intentionally left open-ended so that Federal, regional, State, and local agencies can have flexibility in developing more detailed land use classifications at the third and fourth levels in order to meet their particular needs and at the same time remain compatible with each other and the national system. Revision of the land use classification system as presented in US Geological Survey Circular 671 was undertaken in order to incorporate the results of extensive testing and review of the categorization and definitions.

4,154 citations


"Remote sensing methods in medium sp..." refers background or methods in this paper

  • ...An example of a hierarchical land cover classification system is the Anderson et al. (1976) Land Use and Land Cover Classification System comprised of four Levels (I, II, III, IV) designed for use with a variety of remotely Table 8 The major tasks required in any large area, multiple image, land…...

    [...]

  • ...…tasks required in any large area, multiple image, land cover classification Task Key references Selection of land cover classification map legend Anderson et al., 1976; Robinove, 1981; suitable for use with satellite remote sensing data Running et al., 1995; Franklin, J. and Woodcock,…...

    [...]

Journal ArticleDOI
TL;DR: The IGBP DISCover global land cover product as mentioned in this paper is an integral component of the Global Land Cover database, which provides a unique view of the broad patterns of the biogeographical and ecoclimatic diversity of the global land surface and presents a detailed interpretation of the extent of human development.
Abstract: Researchers from the U.S. Geological Survey, University of Nebraska-Lincoln and the European Commission's Joint Research Centre, Ispra, Italy produced a 1 km resolution global land cover characteristics database for use in a wide range of continental-to global-scale environmental studies. This database provides a unique view of the broad patterns of the biogeographical and ecoclimatic diversity of the global land surface, and presents a detailed interpretation of the extent of human development. The project was carried out as an International Geosphere-Biosphere Programme, Data and Information Systems (IGBP-DIS) initiative. The IGBP DISCover global land cover product is an integral component of the global land cover database. DISCover includes 17 general land cover classes defined to meet the needs of IGBP core science projects. A formal accuracy assessment of the DISCover data layer will be completed in 1998. The 1 km global land cover database was developed through a continent-by-continent unsupervised ...

2,365 citations