Examining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case

By Dongmei Chen, Douglas A. Stow, Peng Gong. 2004

301 citations recorded by the source corpus.

Subfields: Ecology, Global and Planetary Change, Media Technology

View Paper: https://www.semanticscholar.org/paper/d463cc5941810ec1cc8ed31ed1eff4b7d0984e47

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Global and Planetary Change

In Media Technology

Citations in the corpus

Object-based crop identification using multiple vegetation indices, textural features and crop phenology (2011, background): “Therefore, future analysis is recommended to determine the relationships between textural properties and certain crop parameters at the field scale, also affected by object heterogeneity or image spatial resolution (Chen et al., 2004).”
Potential of texture measurements of two-date dual polarization PALSAR data for the improvement of forest biomass estimation (2012, background): “Extracting appropriate descriptions of texture also involves the selection of moving window sizes (Chen et al., 2004; Lu, 2005).”
A literature survey on smart cities (2015, methodology): “Chen et al. [115] gave a method to estimate the commercial density level of the whole city, and urban areas can use this to estimate the probability of commercial functions.”
A survey of image classification methods and techniques for improving classification performance (2007, unknown): “Spatial resolution is an important factor that affects classification details and accuracy (Chen et al. 2004) and influences the selection of classification approaches (Atkinson and Curran 1997, Atkinson and Aplin 2004).”
Using texture analysis to improve per-pixel classification of very high resolution images for mapping plastic greenhouses (2008, methodology): “Chen et al. (2004) used a 1 m resolution multispectral aerial image (R, G, B) of an urban area, which was degraded to different resolutions (4, 8, 12, 16, 20 and 24 m).”
Evaluation of UAV imagery for mapping Silybum marianum weed patches (2017, background): “The selection of a large window size has been suggested to improve classification results in cases of spectrally heterogeneous images (Chen, Stow, and Gong 2004).”
A Robust Built-Up Area Presence Index by Anisotropic Rotation-Invariant Textural Measure (2008, background): “All of these parameters are related to the spatial and spectral resolution of the image, and the spatial characteristics (dimension, shape) of the different classes to be detected [21] and [22].”
Improved forest biomass estimates using ALOS AVNIR-2 texture indices (2011, background): “…2001; Franklin et al., 1996; Marceau et al., 1990), ii) texture processing can generate a large amount of data which are difficult to manage (Chen et al., 2004; Franklin, 2001), and there is no indication which texture variables or combination of variables hold the greatest potential and…”