Texture measures for the identification and monitoring of urban derelict land

Dawson, B. R. P.; Parsons, Anthony J.

doi:10.1080/01431169408954159

Cited by 9 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [13,14], grey-level occurrence matrix (GLOM) and grey-level co-occurrence matrix (GLCM) were introduced to recognize patterns. In [15], the standard deviation, entropy, run lengths and "fractal" roughness were investigated for their separability for urban derelict lands. In [4], the first and second order variance and homogeneity were found to be effective in distinguishing the forest age class from IKONOS imagery.…”

Section: Introductionmentioning

confidence: 99%

Individual Urban Tree Species Classification Using Very High Spatial Resolution Airborne Multi-Spectral Imagery Using Longitudinal Profiles

Zhang

2012

Remote Sensing

View full text Add to dashboard Cite

Individual tree species identification is important for urban forest inventory and ecology management. Recent advances in remote sensing technologies facilitate more detailed estimation of individual urban tree characteristics. This study presents an approach to improve the classification of individual tree species via longitudinal profiles from very high spatial resolution airborne imagery. The longitudinal profiles represent the side view tree shape, which play a very important role in individual tree species on-site identification. Decision tree classification was employed to conduct the final classification result. Using this profile approach, six major species (Maple, Ash, Birch, Oak, Spruce, Pine) of trees on the York University (Ontario, Canada) campus were successfully identified. Two decision trees were constructed, one knowledge-based and one derived from gain ratio criteria. The classification accuracy achieved were 84% and 86%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Individual Urban Tree Species Classification Using Very High Spatial Resolution Airborne Multi-Spectral Imagery Using Longitudinal Profiles

Zhang

2012

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…All six non-thermal wavebands were used for the classification as these provided the highest level of inter-class separability. To enhance the classification accuracy further variance-filtered images of bands 1 and 4 were also used as measures of image texture (Kivell, et al, 1989;Dawson and Parsons, 1990;ERDAS, 1991a). Additionally, the two spectral subclasses of despoiled land were classed separately and later amalgamated (Foody and Cutler, 1992).…”

Section: Resultsmentioning

confidence: 99%

Determining the extent and spectral separability of industrially despoiled land in South Wales from satellite sensor data

Foody

Cutler

1993

Land Degrad Dev

View full text Add to dashboard Cite

Satellite remote sensing offers the potential to accurately identify and monitor spectrally separable land-cover classes at a range of spatial and temporal scales. This paper investigates the separability of despoiled land in imagery acquired by sensors carried by the Landsat satellites. These systems offer the opportunity to map areas at large to medium scales at a relatively high temporal frequency and so provide information on environmental quality necessary for many monitoring and planning activities. From an investigation using imagery of South Wales it was found that despoiled land was separable from other classes in the Landsat TM imagery, with an accuracy of over 90 per cent. Furthermore, with Landsat TM data three spectral wavebands were found to provide a level of separability similar to that based on all wavebands available, illustrating potential savings to the analyst. Despoiled land cover was classified from Landsat TM and MSS data and these classifications were evaluated against a manually produced map of despoiled land cover derived from the interpretation of aerial photographs. Estimates of the extent of despoiled land cover in administrative units derived from the Landsat TM data were significantly correlated ( r = 0-81) with the map based estimates, although a weaker correlation was observed with Landsat MSS data.

show abstract

“…Spectral methods are based on the Fourier transform, analysing the power spectrum (Matsuyama, 1980). The third and most important group in texture analysis corresponds to that of statistical methods, which are mainly based on local statistical parameters (Sun and Qin, 1993), entropy (Haralick and Shanmugham, 1974), fractal dimension (Dawson and Parsons, 1994), and measures of the matrix of co-occurrence (Franklin and Peddle, 1987). Other studies have made use of texture transforms (Irons and Petersen, 1981) in which dierent measures of variability in digital number (DN) values are estimated within moving windows, e.g., standard deviation (Arai, 1993) or local variance (Woodcock and Harward, 1992), and some recent techniques have involved the use of geostatistical parameters deduced from the variogram function (Carr, 1996;Lark, 1996;Miranda et al, 1998).…”

Section: Introductionmentioning

confidence: 99%

Computing geostatistical image texture for remotely sensed data classification

Chica-Olmo

Abarca-Hernández

2000

Computers & Geosciences

187

View full text Add to dashboard Cite

Most classical mathematical algorithms for image classi®cation do not usually consider the spectral dependence existing between a pixel and its neighbours, i.e., spatial autocorrelation. Thus, it would be advisable for discrimination of landcover classes to add to the radiometric bands of the sensor complementary information related to the textural features of an image, which can be analysed from the autocorrelation spatial structure of the digital numbers. In this way, the results obtained from pixel-by-pixel classi®ers simultaneously taking into account both radiometric and texture information could be improved. This improvement would arise from the hypothesis that a pixel is not independent of its neighbours and, furthermore, that its dependence can be quanti®ed and incorporated into the classi®er. In this paper we present a methodology based on computing a set of univariate and multivariate textural measures of spatial variability based on several variogram estimators. Madogram and direct variogram for the univariate case, and cross and pseudo-cross variograms for the multivariate one, have been proposed. These measures are calculated for a speci®c lag of distance in a neighbourhood using a moving window on the two most representative principal components of the radiometric bands, enabling us to quantify the spatial variability of radiometric data at a local level. A computer program has been written to create a multiband image texture as output ®le that can be used within the classi®cation process as additional information. An application of this methodology to lithological discrimination is presented using a Landsat-5 TM image. 7

show abstract

Texture measures for the identification and monitoring of urban derelict land

Cited by 9 publications

References 6 publications

Individual Urban Tree Species Classification Using Very High Spatial Resolution Airborne Multi-Spectral Imagery Using Longitudinal Profiles

Individual Urban Tree Species Classification Using Very High Spatial Resolution Airborne Multi-Spectral Imagery Using Longitudinal Profiles

Determining the extent and spectral separability of industrially despoiled land in South Wales from satellite sensor data

Computing geostatistical image texture for remotely sensed data classification

Contact Info

Product

Resources

About