Multiband compact texture unit descriptor for intra-band and inter-band texture analysis

Safia, Abdelmounaime; He, Dong-Chen

doi:10.1016/j.isprsjprs.2015.04.003

Cited by 13 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high resolution might enable to discriminate fine details of land use/land cover such as farmland, urban areas, quality of road surfaces, and health of plants. The multiple spectral bands yield inter-band spectral information to discriminate texture features [45,46]. for green and blue bands, different sectors and other cities will be reported in a forthcoming work.…”

Section: Data and Resultsmentioning

confidence: 99%

Atlas of urban scaling laws

Carbone

Murialdo

Pieroni³

et al. 2022

J. Phys. Complex.

View full text Add to dashboard Cite

Accurate estimates of the urban fractal dimension D f are obtained by implementing the detrended moving average algorithm on high-resolution multi-spectral satellite images from the WorldView2 (WV2) database covering the largest European cities. Fractal dimension D f varies between 1.65 and 1.90 with high values for highly urbanised urban sectors and low ones for suburban and peripheral ones. Based on recently proposed models, the values of the fractal dimension D f are checked against the exponents β s and β i of the scaling law Y ∼ N β , respectively for socio-economic and infrastructural variables Y, with N the population size. The exponents β s and β i are traditionally derived as if cities were zero-dimensional objects, with the relevant feature Y related to a single homogeneous population value N, thus neglecting the microscopic heterogeneity of the urban structure. Our findings go beyond this limit. High sensitive and repeatable satellite records yield robust local estimates of the urban scaling exponents. Furthermore, the work discusses how to discriminate among different scaling theories, shedding light on the debated issue of scaling phenomena contradictory perspectives and pave paths to a more systematic adoption of the complex system science methods to urban landscape analysis.

show abstract

Section: Data and Resultsmentioning

confidence: 99%

Atlas of urban scaling laws

Carbone

Murialdo

Pieroni³

et al. 2022

J. Phys. Complex.

View full text Add to dashboard Cite

show abstract

“…The high resolution might enable to discriminate fine details of Land Use/Land Cover (LULC) such as farmland, urban areas, quality of road surfaces, and health of plants. The multiple spectral bands yield inter-band spectral information to discriminate features of texture [40,41].…”

Section: Data and Resultsmentioning

confidence: 99%

Atlas of Urban Scaling Laws

Carbone,

Murialdo,

Pieroni

et al. 2021

Preprint

View full text Add to dashboard Cite

Highly accurate estimates of the urban fractal dimension D f are obtained by implementing the Detrended Moving Average algorithm (DMA) on WorldView2 satellite high-resolution multi-spectral images covering the largest European cities. Higher fractal dimensions are systematically obtained for urban sectors (centrally located areas) than for suburban and peripheral areas, with Df values ranging from 1.65 to 1.90 respectively.The exponents βs and βi of the scaling law N β with N the population size, respectively for socio-economic and infrastructural variables, are evaluated for different urban and suburban sectors in terms of the fractal dimension D f .Results confirm the range of empirical values reported in the literature. Urban scaling laws have been traditionally derived as if cities were zero-dimensional objects with the relevant feature related to a single homogeneous population value, thus neglecting the microscopic heterogeneity of the urban structure. Our findings allow one to go beyond this limit. High sensitive and repeatable satellite records yield robust local estimates of the Hurst and scaling exponents. Furthermore, the approach allows one to discriminate among different scaling theories, shedding light on the open issue of scaling phenomena, reconciling contradictory scientific perspectives and pave paths to the systematic adoption of the complex system science approach to urban landscape analysis.

show abstract

“…Figure 4. Extraction of the multiband C-TU descriptor for a three-band image using a 3 x 3 pixel multispectral neighborhood (Safia and He, 2015).…”

Section: Multiband C-tu Descriptormentioning

confidence: 99%

Object-based VHSR image classification using multiband compact texture unit descriptor

Djerriri¹,

Safia²,

Cheriguene³

et al. 2016

GEOBIA 2016: Solutions and Synergies

View full text Add to dashboard Cite

In remote sensing, texture is commonly used to support spectral information particularly when spectral signatures of class of interest are similar. It is usually extracted using panchromatic band instead of multispectral bands. This is because panchromatic band has rich texture content due to its fine spatial resolution. Recent space-borne and pansharpening techniques can deliver multispectral images with a submetric resolution which are also good candidates for texture analysis. The difficulty in extracting texture in multispectral images is the fact that existing and widely used methods are limited to analyzing spatial relationship between pixels in a single band at a time. When multispectral images are used texture characterization is usually performed by analyzing spatial relationships in each spectral band independently. This ignores inter-band spatial relationships which can be a source of valuable source of information. This paper evaluates the capability of a recently proposed method named multiband compact texture unit. This method extracts texture by characterizing simultaneously spatial relationship in the same band and across the different bands. This evaluation is performed in the context of object-based classification paradigm using WorldView-2 image of a forest area. For that image-objects were generated through superpixel segmentation. Classification in the object-feature space is performed suing K nearest neighbor algorithm. The proposed approach is compared to two groups of methods. The first group includes texture methods that use only spatial relationships in the same band: Gabor features wavelets and Granulometry. The second group includes methods that use intra-band and inter-band spatial relationships: integrative gray-level co-occurrence matrix, opponent Gabor features and opponent local binary patterns. Experimental results show that texture extracted using both intra-band and inter-band spatial relationship improves the classification accuracy compared to when it is extracted in each spectral band independently. Among the methods of the second group that use both intra-band and inter-band spatial relationships, the multiband compact texture unit method produces the best results.

show abstract

Multiband compact texture unit descriptor for intra-band and inter-band texture analysis

Cited by 13 publications

References 44 publications

Atlas of urban scaling laws

Atlas of urban scaling laws

Atlas of Urban Scaling Laws

Object-based VHSR image classification using multiband compact texture unit descriptor

Contact Info

Product

Resources

About