Evaluation Of The Grey-level Co-occurrence Matrix Method For Land-cover Classification Using Spot Imagery

Marceau, Danielle J.; Howarth, Philip J.; Dubois, J M; Gratton, Denis

doi:10.1109/tgrs.1990.572937

Cited by 301 publications

(192 citation statements)

References 17 publications

Supporting

Mentioning

170

Contrasting

Unclassified

Order By: Relevance

“…The (4) BUILT-UP AREA textural features were computed on two different IKONOS data sets: the panchromatic band and the band ratio between nearinfrared and red (4-m/pixel resolution resized to 1 m/pixel), which, in remote sensing literature, is considered as a way to emphasize vegetation [1]. The spatial features were obtained from the well-known GLCM, which is widely used in landcover mapping [5], [26], [27]. A moving window of 15 × 15 IKONOS pixels (1-m/pixel resolution) is used in the computation of the GLCM, since a window of such dimensions covers the same spatial area as one ASTER pixel.…”

Section: Spatial Preprocessingmentioning

confidence: 99%

Uncertainty Analysis for the Classification of Multispectral Satellite Images Using SVMs and SOMs

Giacco

Thiel

Pugliese

et al. 2010

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-Classification of multispectral remotely sensed data with textural features is investigated with a special focus on uncertainty analysis in the produced land-cover maps. Much effort has already been directed into the research of satisfactory accuracyassessment techniques in image classification, but a common approach is not yet universally adopted. We look at the relationship between hard accuracy and the uncertainty on the produced answers, introducing two measures based on maximum probability and α quadratic entropy. Their impact differs depending on the type of classifier. In this paper, we deal with two different classification strategies, based on support vector machines (SVMs) and Kohonen's self-organizing maps (SOMs), both suitably modified to give soft answers. Once the multiclass probability answer vector is available for each pixel in the image, we studied the behavior of the overall classification accuracy as a function of the uncertainty associated with each vector, given a hard-labeled test set. The experimental results show that the SVM with one-versus-one architecture and linear kernel clearly outperforms the other supervised approaches in terms of overall accuracy. On the other hand, our analysis reveals that the proposed SOM-based classifier, despite its unsupervised learning procedure, is able to provide soft answers which are the best candidates for a fusion with supervised results.

show abstract

Section: Spatial Preprocessingmentioning

confidence: 99%

Uncertainty Analysis for the Classification of Multispectral Satellite Images Using SVMs and SOMs

Giacco

Thiel

Pugliese

et al. 2010

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Research attempting to find which texture measure-what window sizes using which wavelengths-performs better in improving biomass estimation accuracy is uncommon. Although many texture measures have been developed (Haralick et al 1973, Haralick 1979, Marceau et al 1990, there has been little research on how to effectively extract biomass texture information. This research indicates that texture information is a very important factor in improving model estimation performance, especially in a study area with fast vegetation growth rates and complex stand structure.…”

Section: Discussionmentioning

confidence: 99%

Above-Ground Biomass Estimation of Successional and Mature Forests Using TM Images in the Amazon Basin

Mausel

Brondı́zio

et al. 2002

Advances in Spatial Data Handling

View full text Add to dashboard Cite

Above-ground biomass estimation of successional and mature forests in moist tropical regions is attracting increasing attention. Because of complex stand structure and abundant vegetation species, rarely has remote-sensing research been successfully conducted in biomass estimation for moist tropical areas. In this paper, two study areas in the Brazilian Amazon basin-Altamira and Bragantina-with different biophysical characteristics were selected. Atmospherically corrected Thematic Mapper (TM) images and field vegetation inventory data were used in the analysis, and different vegetation indices and texture measures were explored. Multiple regression models were developed through integration of image data (including TM bands, different vegetation indices, and texture measures) and vegetation inventory data. These models were used for biomass estimation in both selected study areas. This study concludes that neither TM spectral bands nor vegetation indices alone are sufficient to establish an effective model for biomass estimation, but multiple regression models that consist of spectral and textural signatures improve biomass estimation performance. The models developed are especially suitable for above-ground biomass estimation of dense vegetation areas.

show abstract

“…The shape features consist of geometric features of objects, including length-width ratio, compactness, density and shape index. The textural features, including mean, variance, homogeneity, contrast, dissimilarity, entropy, angular second moment and correlation, comprise the measures of gray level co-occurrence matrices (GLCM) proposed by Haralick [42,43]. Table 1 lists the extracted features in this study.…”

Section: Multiple Features Extraction and Difference Image Generationmentioning

confidence: 99%

Object-Based Change Detection in Urban Areas from High Spatial Resolution Images Based on Multiple Features and Ensemble Learning

Wang

Liu

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:To improve the accuracy of change detection in urban areas using bi-temporal high-resolution remote sensing images, a novel object-based change detection scheme combining multiple features and ensemble learning is proposed in this paper. Image segmentation is conducted to determine the objects in bi-temporal images separately. Subsequently, three kinds of object features, i.e., spectral, shape and texture, are extracted. Using the image differencing process, a difference image is generated and used as the input for nonlinear supervised classifiers, including k-nearest neighbor, support vector machine, extreme learning machine and random forest. Finally, the results of multiple classifiers are integrated using an ensemble rule called weighted voting to generate the final change detection result. Experimental results of two pairs of real high-resolution remote sensing datasets demonstrate that the proposed approach outperforms the traditional methods in terms of overall accuracy and generates change detection maps with a higher number of homogeneous regions in urban areas. Moreover, the influences of segmentation scale and the feature selection strategy on the change detection performance are also analyzed and discussed.

show abstract

Evaluation Of The Grey-level Co-occurrence Matrix Method For Land-cover Classification Using Spot Imagery

Cited by 301 publications

References 17 publications

Uncertainty Analysis for the Classification of Multispectral Satellite Images Using SVMs and SOMs

Uncertainty Analysis for the Classification of Multispectral Satellite Images Using SVMs and SOMs

Above-Ground Biomass Estimation of Successional and Mature Forests Using TM Images in the Amazon Basin

Object-Based Change Detection in Urban Areas from High Spatial Resolution Images Based on Multiple Features and Ensemble Learning

Contact Info

Product

Resources

About