A contextual classification method for recognizing land use patterns in high resolution remotely sensed data

This paper describes a CONtextual ANalysis procedure (CONAN) which is designed to recognize land use patterns in high resolution remotely sensed data by analysis of the local frequency distribution of scene components (i.e. ground cover type classes). The procedure was tested with randomly generated synthetic data developed to simulate the frequency distribution of cover type components for four land use classes. It was found that the accuracy in discriminating between the four test classes depends upon the size of the pixel neighborhood used to compute the component frequency distribution.     

Integrating remotely sensed data,GIS and expert knowledge to update object-based land use/land cover information

Remote-sensing technology provides a powerful means for land use/land cover (LU/LC) monitoring at global and regional scales. However, it is more efficient and effective to combine remote-sensing measurements with a geographic information system (GIS) database and expert knowledge for change updating than to use remote-sensing technology alone. In this article, these different sources of information are integrated in the proposed framework, which is able to provide rapid updating of LU/LC information. An object-based data analysis is adopted for thematic mapping, taking both spectral and spatial properties into consideration. An expert knowledge coding is introduced and combined quantitatively with other evidence provided by remotely sensed data and the GIS database. A case study using Landsat Thematic Mapper (TM) datasets demonstrated an overall successful LU/LC map updating and a satisfactory change detection using the proposed change-updating framework.     

Automatic land cover analysis for Tenerife by supervised classification using remotely sensed data

Automatic land cover classification from satellite images is an important topic in many remote sensing applications. In this paper, we consider three different statistical approaches to tackle this problem: two of them, namely the well-known maximum likelihood classification (ML) and the support vector machine (SVM), are noncontextual methods. The third one, iterated conditional modes (ICM), exploits spatial context by using a Markov random field. We apply these methods to Landsat 5 Thematic Mapper (TM) data from Tenerife, the largest of the Canary Islands. Due to the size and the strong relief of the island, ground truth data could be collected only sparsely by examination of test areas for previously defined land cover classes.We show that after application of an unsupervised clustering method to identify subclasses, all classification algorithms give satisfactory results (with statistical overall accuracy of about 90%) if the model parameters are selected appropriately. Although being superior to ML theoretically, both SVM and ICM have to be used carefully: ICM is able to improve ML, but when applied for too many iterations, spatially small sample areas are smoothed away, leading to statistically slightly worse classification results. SVM yields better statistical results than ML, but when investigated visually, the classification result is not completely satisfying. This is due to the fact that no a priori information on the frequency of occurrence of a class was used in this context, which helps ML to limit the unlikely classes.     

Technical note: Rotational transformation of remotely sensed data for land use classification

In this paper, the rotational transformation process is explained as a problem of rotation of remotely sensed data in the variance-covariance space. In particular, the rotation which maximizes the covariance-variance ratio is examined in detail for various land use and land cover classes in the Bombay suburban and Thana district area in India. A statistical approach to determine transformed components and other statistical variables on different band combinations is discussed. The results are analysed, and the best possible combinations selected for accurate classification are presented.     

Use of groundtruth data to correct land cover area estimates from remotely sensed data

Estimates of area by land cover category from photo interpretation are subject to bias arising from interpretation error. Quantification of this error by groundtruth survey allows corrections to be made to the estimates. The precision of estimates of interpretation error for a fixed cost depends on the survey design; simple survey designs arc inefficient for this purpose. The penalty for using more complex designs is that a sophisticated correction method is required. We note the assumptions of existing correction methods, develop a more general method, and show how the precision of corrected estimates of area may be quantified. We demonstrate the effect of‘correcting’ area estimates under different methods, and provide an example in which use of an inappropriate method leads to substantial bias (up to 40 per cent).     

Using contextual information to improve land use classification of satellite images in central Spain

Abstract

The classification accuracy obtained from the classification of satellite images using pixel-by-pixel conventional methods can be improved if the contextual information is considered jointly with the spectral information in the same strategy of classification. A computer program has been developed to implement a contextual classifier algorithm. The accuracy improvement was evaluated and tested in two pilot zones of central Spain. Two indices were defined in order to analyse the homogeneity effect produced by the contextual classifier.     

A cartographic and database approach for land cover/use mapping and generalization from remotely sensed data

Classification of remotely sensed data involves a set of generalization processes, i.e. reality is simplified to a set of a few classes that are relevant to the application under consideration. This article introduces an approach to image classification that uses a class hierarchy structure for mapping unit definition at different generalization levels. This structure is implemented as an operational relational database and allows querying of more detailed land cover/use information from a higher abstraction level, which is that viewed by the map user. Elementary mapping units are defined on the basis of an unsupervised classification process in order to determine the land cover/use classes registered in the remotely sensed data. Mapping unit composition at different generalization levels is defined on the basis of membership values of sampled pixels to land cover/use classes. Unlike fuzzy classifications, membership values are presented to the user at mapping unit level.     

The use of prior probabilities in maximum likelihood classification of remotely sensed data

The expected distribution of classes in a final classification map can be used to improve classification accuracies. Prior information is incorporated through the use of prior probabilities—that is, probabilities of occurrence of classes which are based on separate, independent knowledge concerning the area to be classified. The use of prior probabilities in a classification system is sufficiently versatile to allow (1) prior weighting of output classes based on their anticipated sizes; (2) the merging of continuously varying measurements (multispectral signatures) with discrete collateral information datasets (e.g., rock type, soil type); and (3) the construction of time-sequential classification systems in which an earlier classification modifies the outcome of a later one. The prior probabilities are incorporated by modifying the maximum likelihood decision rule employed in a Bayesian-type classifier to calculate a posteriori probabilities of class membership which are based not only on the resemblance of a pixel to the class signature, but also on the weight of the class which is estimated for the final output classification. In the merging of discrete collateral information with continuous spectral values into a single classification, a set of prior probabilities (weights) is estimated for each value which the discrete collateral variable may assume (e.g., each rock type or soil type). When maximum likelihood calculations are performed, the prior probabilities appropriate to the particular pixel are used in classification. For time-sequential classification, the prior classification of a pixel indexes a set of appropriate conditional probabilities reflecting either the confidence of the investigator in the prior classification or the extent to which the prior class identified is likely to change during the time period of interest.     

Fully fuzzy supervised classification of land cover from remotely sensed imagery with an artificial neural network

Mixed pixels are a major problem in mapping land cover from remotely sensed imagery. Unfortunately, such imagery may be dominated by mixed pixels, and the conventional hard image classification techniques used in mapping applications are unable to appropriately represent the land cover of mixed pixels. Fuzzy classification techniques can, however, accommodate the partial and multiple class membership of mixed pixels, and be used to derive an appropriate land cover representation. This is, however, only a partial solution to the mixed pixel problem in supervised image classification. It must be reognised that the land cover on the ground is fuzzy, at the scale of the pixel, and so it is inappropriate to use procedures designed for hard data in the training and testing stages of the classification. Here an approach for land cover classification in which fuzziness is accommodated in all three stages of a supervised classification is presented. Attention focuses on the classification of airborne thematic mapper data with an artificial neural network. Mixed pixels could be accommodated in training the artificial neural network, since the desired output for each training pixel can be specified. A fuzzy land cover representation was derived by outputting the activation level of the network's output units. The activation level of each output unit was significantly correlated with the proportion of the area represented by a pixel which was covered with the class associated with the unit (r>0.88, significant at the 99% level of confidence). Finally, the distance between the fuzzy land cover classification derived from the artificial neural network and the fuzzy ground data was used to illustrate the accuracy of the land cover representation derived. The dangers of hardening the classification output and ground data sets to enable a conventional assessment of classification accuracy are also illustrated; the hardened data sets were over three times more distant from each other than the fuzzy data sets.     

Technical Note: Hyperspherical direction cosine transformation of remotely sensed data for separation of topographic expression of land use classification

In this paper, the hyperspherical direction cosine transformation process of remotely-sensed data is explained. In particular, this transformation process is utilized to examine various land use and land cover classes in the Bombay suburban and Thana district area in India. A statistical approach to determine the transformed components and other statistical variables on different band combinations is discussed. The results are analysed, and the best possible combinations selected for accurate classification are presented. Separation of topographically induced illumination effects and spectral information (cover type) in digital scanner data can be accomplished by projecting measurement vectors on to a hypersphere.     

Extension of environmental parameters over the land surface by improved fuzzy classification of remotely sensed data

Recent studies have shown that useful information can be derived from remotely sensed data to extend local environmental measurements over the land surface. A flexible fuzzy classification approach, in particular, was demonstrated to be superior to conventional multivariate regression methods for this purpose. This new extension methodology is described and discussed in detail. Next, some modifications are proposed in order to improve the consideration of the spectral information and to produce per-pixel estimates of the error committed. The performances of the original and modified methodologies are then evaluated in two case studies representative of different parameters to extend and satellite data. The results show the efficiency of the new strategy and, in particular, some improvements obtained by the modified method which testify to the effectiveness of the modifications proposed.     

Fully-fuzzy supervised classification of sub-urban land cover from remotely sensed imagery: Statistical and artificial neural network approaches

Fully-fuzzy classification approaches have attracted increasing interest recently. These approaches allow for multiple and partial class memberships at the level of individual pixels and accommodate fuzziness in all three stages of a supervised classification of remotely sensed imagery. A fully-fuzzy classification strategy may be deemed more objective and correct than partially-fuzzy approaches where fuzziness is only accommodated in one or two of the three classification stages. This paper describes two approaches to the fully-fuzzy classification of remotely sensed imagery: a statistical approach based on a modified fuzzy c-means clustering algorithm performed in a supervised mode and an artificial neural network based approach. This is followed by the documentation of a case study using Landsat Thematic Mapper (TM) data of an Edinburgh suburb. Both approaches were applied to derive fully-fuzzy classifications of land cover, with fuzzy ground data, critical for training and testing the classifications, derived from indicator kriging. Results confirmed the superiority of fully-fuzzy over their respective partially-fuzzy classification counterparts, which is beneficial given their more relaxed requirements for training pixels (i.e. training pixels need not be pure). Similar accuracies were obtained with the artificial neural network and statistical approaches to classification. It is suggested that due emphasis must be placed on derivation and analysis of fuzzy ground data as well as fuzzy classified data in order to further improve fully-fuzzy classifications.     

Supervised classification of remotely sensed data with ongoing learning capability

A methodology to implement an automatic system for classifying remotely sensed data with an ongoing learning capability is introduced. The Nearest Neighbour (NN) rule is employed as the central classifier and several techniques are added to cope with the increase in computational load and with the risk of incorporating noisy data into the training sample. Experimental results confirm the enhancement in classification accuracy.     

The use of the empirical line method to calibrate remotely sensed data to reflectance

To have lasting quantitative value, remotely sensed data must be calibrated to physical units of reflectance. The empirical line method offers a logistically simple means of generating acceptable estimates of surface reflectance. A review and case-study identify the ease with which this method can be applied, but also some of the pitfalls that can be encountered if it is not planned and implemented properly. A number of theoretical assumptions and practical considerations should be taken into account before applying this approach. It is suggested that the empirical line method allows the calibration of remotely sensed data to reflectance with errors of only a few percent.     

Object-oriented classification of land use/cover using digital aerial orthophotography

In automatic/semiautomatic mapping of land use/cover using very high resolution remote-sensing imagery, the major challenge is that a single class of land use contains ground targets with varied spectral values, textures, geometries and spatial features. Here we present an object-oriented strategy for automatic/semiautomatic classifications of land use/cover using very high resolution remote-sensing data. The strategy consists of character detecting, object positioning and coarse classification, then refining the classification result step by step. The strategy combines the form classification of the objects located on the same level by using spectral values, textures and geometric features with function classification by using spatial logic relationships existing among the objects on the same level or between different levels. Furthermore, it overcomes the problem of transformation from form classification to function classification and unifies land use classification and land cover classification organically. Such an approach not only achieves high classification accuracy, but also avoids the salt-and-pepper effect found in conventional pixel-based procedures. The borderlines of the classification result are clear, the patches are pure, and the classification objects exactly match the ground targets distributed across the study site. A feasible technical strategy for the large-scale application is discussed in this article.     

Contextual correction: techniques for improving land cover mapping from remotely sensed images

Large area land cover mapping is an important application of remote sensing. A digital land cover map of Great Britain has recently been compiled by supervised classification of Landsat Thematic Mapper data. The work has involved development of a range of post classification procedures to correct contextual errors associated with the use of spectral classification algorithms. This paper describes these procedures and examines their effects upon the map product including a comparison with field survey data.     

A Penman-Monteith evapotranspiration model with bulk surface conductance derived from remotely sensed spatial contextual information

ABSTRACT

A novel approach involving the use of the contextual information in a scatter plot of Moderate Resolution Imaging Spectrometer (MODIS) derived Land Surface Temperature versus Fraction of Vegetation (LST vs. F_v) has been proposed in this study to obtain pixel-wise values of bulk surface conductance (G_s) for use in the Penman-Monteith (PM) model for latent heat flux (λ_ET) estimation. Using a general expression for G_s derived by assuming a two-source total λ_ET (canopy transpiration plus soil evaporation) approach proposed by previous researchers, minimum and maximum values of G_s for a given region can be inferred from a trapezoidal scatter plot of pixel-wise values of LST and corresponding F_v. Using these as limiting values, G_s values for each pixel can be derived through interpolation and subsequently used with the PM model to estimate λ_ET for each pixel. The proposed methodology was implemented in 5 km × 5 km areas surrounding each of four flux towers located in tropical south-east Asia. Using climate data from the tower and derived G_s values the PM model was used to obtain pixel-wise instantaneous λ_ET values on six selected dates/times at each tower. Excellent comparisons were obtained between tower measured λ_ET and those estimated by the proposed approach for all four flux tower locations (R² = 0.85–0.96; RMSE = 18.27–33.79 W m^–2). Since the LST- F_v trapezoidal method is simple, calibration-free and easy to implement, the proposed methodology has the potential to provide accurate estimates of regional evapotranspiration with minimal data inputs.     

Assessing the accuracy of land surface characteristics estimated from multi-angular remotely sensed data

New missions and technically advanced sensors are being developed by researchers to monitor our planet from space at different spatial and spectral resolutions. Characterizing the terrestrial biomes on a global scale is a key issue in understanding climate change and the evolution of the Earth's atmosphere system. New advanced models on radiation in plant stands and more heterogeneous biomes are used to interpret satellite- and airborne sensor data and identify information on the Earth's surface. This paper presents an investigation on estimation of canopy and leaf level quantities by multidirectional remotely sensed data in three spectral bands. The purpose is to evaluate the goodness of a model in a controlled environment, using artificial input data. The results of the experiment indicate that the required information on leaf optical properties can be derived with a good accuracy within the constraints of the experiment. Estimated stand structure characteristics are more prone to error. Scaling issues, including temporal, spectral and spatial resolution, and surface heterogeneity are not addressed in this experiment.     

Estimating the spatial distribution of the population of Riyadh,Saudi Arabia using remotely sensed built land cover and height data

This paper investigates the use of Landsat ETM+, remotely sensed height data, ward-level census population, and dwelling units to downscale population in Riyadh, Saudi Arabia. Regression analysis is used to model the relationship between density of dwelling units and built area proportion at the block level and the coefficients used to downscale density of dwelling units to the parcel level. The population distribution is estimated based on average population per dwelling unit. Seven models were fitted and compared. First, a conventional approach, using ISODATA-classified built land cover alone as a covariate, is used as a benchmark against which to evaluate six more sophisticated models. The conventional model results in low accuracy measured by overall relative error (ORE) (+116%). Approaches for potentially increasing accuracy are explored, incorporating above-surface height data into the downscaling process. These include masking out zero and near-zero height areas when estimating built area; using height to estimate the number of floors; replacing the ISODATA model with a support vector machine; estimating volume-adjusted habitable space; stratifying the study area into different building categories; and preservation of the dependent variable for the best model. These approaches result in large increases in accuracy in the density of dwelling unit estimates. However, while the height data accounts for the vertical dimension (primarily through the number of floors), it is not possible to account for variation in dwelling density which arises due to other factors such as living standards, affluence and other spatially varying factors, without further data.     

The application of the coalescence clustering algorithm to remotely sensed multispectral data

The coalescence clustering concept of Watanabe has been implemented for the purpose of unsupervised classification of remotely sensed multispectral data. Modifications on the original algorithm were made to enable clustering of limited range discrete data. Application to simulated overlapping Gaussian distributions show that optimal separation of boundaries is achieved at almost every point. Clustering of real data from LANDSAT satellites also yields very meaningful results. Significance of the range parameter and computer requirements are also discussed.