ISSN:0143-1161    

DOI:10.1080/014311697218683

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

ISSN:0143-1161    

DOI:10.1080/014311697218692

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

Over the past decade there have been considerable increases in both the quantity of remotely sensed data available and the use of neural networks. These increases have largely taken place in parallel, and it is only recently that several researchers have begun to apply neural networks to remotely sensed data. This paper introduces this special issue which is concerned specifically with the use of neural networks in remote sensing. The feed-forward back-propagation multi-layer perceptron (MLP) is the type of neural network most commonly encountered in remote sensing and is used in many of the papers in this special issue. The basic structure of the MLP algorithm is described in some detail while some other types of neural network are mentioned. The most common applications of neural networks in remote sensing are considered, particularly those concerned with the classification of land and clouds, and recent developments in these areas are described. Finally, the application of neural networks to multi-source data and fuzzy classification are considered.

ISSN:0143-1161    

DOI:10.1080/014311697218700

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

This paper examines a number of experimental investigations of neural networks used for the classification of remotely sensed satellite imagery at the Joint Research Centre over a period of five years, and attempts to draw some conclusions about 'best practice' techniques to optimize network training and overall classification performance. The paper examines best practice in such areas as: network architecture selection; use of optimization algorithms; scaling of input data; avoidance of chaos effects; use of enhanced feature sets; and use of hybrid classifier methods. It concludes that a vast body of accumulated experience is now available, and that neural networks can be used reliably and with much confidence for routine operational requirements in remote sensing.

ISSN:0143-1161    

DOI:10.1080/014311697218719

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

Classification of multisource remote sensing and geographic data by neural networks is discussed with respect to feature extraction. Several feature extraction methods are reviewed, including principal component analysis, discriminant analysis, and the recently proposed decision boundary feature extraction method. The feature extraction methods are then applied in experiments in conjunction with classification by multilayer neural networks. The decision boundary feature extraction method shows excellent performance in the experiments.

ISSN:0143-1161    

DOI:10.1080/014311697218728

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

This paper presents a study of neural networks and version spaces for classification of remote sensing data. In the first network, precomputed textures based on the Spatial Grey Level Dependence (SGLD) method are fed to the net in conjunction with the spectral data. The second system is the sliding window network which uses all pixels in a small neighbourhood for classification of the central pixel. The third system is based on the candidate elimination implementation of the version space method for concept acquisition and is shown to achieve a performance similar to that of the neural systems but with faster training and symbolic rule generation.

ISSN:0143-1161    

DOI:10.1080/014311697218737

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

It is well known that higher dimensional information essentially leads to better accuracy in remotely sensed image classification. This paper is aimed at land cover classification from SPOT-HRV imagery by the integration of multispectral intensity and texture information. In particular, fractal dimensions are extracted using a wavelet transform as image texture. A neural network approach to classification is adopted in this paper. The underlying network is a modified multilayer perceptron trained by a Kalman filtering technique. The main advantages of this network are (1) its non-backpropagation fashion of learning which leads to a fast convergence, (2) a built-in optimization function, and (3) global scale. Saving computer storage space and a fast learning capability are in particular suitable features for remote sensing applications. Correlation analysis was subsequently performed on both the intensity and fractal images. It was found that fractal information significantly improves the discrimination capability of heterogeneous area such as in urban regions, while it slightly degrades accuracy for homogeneous areas, such as open water. The overall classification performance is superior to results obtained using reflectance only. Improvements over heterogeneous areas are demonstrated.

ISSN:0143-1161    

DOI:10.1080/014311697218746

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

The accuracy of an image classification is a function of a range of variables. To select an appropriate classification approach for a particular set of data the analyst must be aware of the significant variables which may affect classification accuracy and the nature of their effect. The effect of a variable, or small number of variables, on classification accuracy may be evaluated by straightforward comparison of classification accuracies. However, for the evaluation of the simultaneous effect of a large number of variables such an approach may be impractical. In such circumstances log-linear modelling may be used to identify the significant variables affecting classification accuracy and the nature of the effect of the significant variables elucidated from further analysis. Log-linear modelling was used here to evaluate the effect of four variables (training set size, waveband combination, classification algorithm and testing set size) on classification accuracy. Since the analyst usually has most control over the choice of classification algorithm most attention was focused on the effects of the other three variables on the accuracies of classifications derived from conventional probabilistic, fuzzy set and neural network classification algorithms. The results showed that these classification algorithms were sensitive to variations in the other three variables. Overall the neural network classifications were generally the most accurate. The accuracies of the neural network classifications were, however, most influenced by training set size, with higher accuracies obtained with the use of large training sets. Alternatively, the other classification algorithms were least affected by the training set size and more sensitive to the testing set size and the waveband combination used. The results should help an analyst design an appropriate approach for an image classification.

ISSN:0143-1161    

DOI:10.1080/014311697218755

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

Artificial neural networks are attractive for the classification of remotely sensed data. However, a wide range of factors influence the accuracy with which a data set may be classified. In this paper, the effect of four factors on the accuracy with which agricultural crops may be classified from airborne thematic mapper (ATM) data was investigated. These factors related to the dimensionality of the remotely sensed data, the neural network architecture, and the characteristics of the training and testing sets. A total of 288 classifications were performed and their accuracies evaluated. The artificial neural networks were able to classify the data to high accuracies, with kappa coefficients of up to 0.97 obtained, but the accuracy derived was highly dependent on the factors investigated. A log-linear modelling approach was used to evaluate the simultaneous effect of the factors on classification accuracy. Variations in the dimensionality of the data set, as well as the training and testing set characteristics had a significant effect on classification accuracy. The network architecture, specifically the number of hidden units and layers, did not, however, have a significant effect on classification accuracy in this investigation. This highlights the need to consider a broader set of issues than network architecture when using an artificial neural network for image classification.

ISSN:0143-1161    

DOI:10.1080/014311697218764

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor

摘要:

In this paper, we propose a pattern classification method for remote sensing data using both a neural network and knowledge-based processing. A neural network has the ability to recognize complex patterns, and classifies them to one of the classes. However,the neural network might produce misclassification. A knowledge-based system which uses human geographical knowledge improves the classification results, compared with a conventional statistical method. The disadvantage of using a knowledge-based system is that it needs a large amount of knowledge to classify the data correctly. We propose a pattern classification method that integrates the advantages of both the neural network and knowledge-based system. The proposed system is divided into two subsystems which consist of recognition and error correction. We use the neural network for classification and the knowledge-based system for correcting misclassification created by the neural network. Experimental results are shown to illustrate the performance of the proposed system.

ISSN:0143-1161    

DOI:10.1080/014311697218773

出版商:Taylor & Francis Group    

年代:1997

数据来源: Taylor