Spatial analysis of remote sensing image classification accuracy

Abstract

The error matrix is the most common way of expressing the accuracy of remote sensing image classifications, such as land cover. However, it and the measures that can be calculated from it have been criticised for not providing any indication of the spatial distribution of errors. Other research has identified the need for methods to analyse the spatial non-stationarity of error and to visualise the spatial variation in classification uncertainty. This research uses geographically weighted approaches to model the spatial variations in the accuracy of both (crisp) Boolean and (soft) fuzzy land cover classes. Remotely sensed data were classified using a maximum likelihood classifier and a fuzzy classifier to predict Boolean and fuzzy land cover classes respectively. Field data were collected at sub-pixel locations and used to generate soft and crisp validation data. A Geographically Weighted Regression was used to analyse spatial variations in the relationships between observations of Boolean land cover in the field and land cover classified from remote sensing imagery. A geographically weighted difference measure was used to analyse spatial variations in fuzzy land cover accuracy. Maps of the spatial distribution of accuracy were created for fuzzy and Boolean classes. This research demonstrates that data collected as part of a standard remote sensing validation exercise can be used to estimate mapped, spatial distributions of accuracy that would augment standard accuracy measures reported in the error matrix. It suggests that geographically weighted approaches, and the spatially explicit representations of accuracy they support, offer the opportunity to report land cover accuracy in a more informative way.

Mapping a burned forest area from Landsat TM data by multiple methods

“…As methods of supervised and unsupervised classification are currently widely used to detect forest disturbances resulting from fires, logging and other causes (Castellana et al 2007;Comber et al 2012;Margono et al 2012), for further comparison, we also conducted an mapping of burned forest area using a supervised classification. Here, the Maximum Likelihood Classifier (MLC) (Kavzoglu & Reis 2008) was used to classify the TM surface reflectance images.…”

“…Using remote sensing data, various algorithms of supervised and unsupervised classification have been adopted to detect forest disturbances resulting from fires, logging and other causes (Comber et al 2012;Margono et al 2012). For serious stand-replacing forest disturbances, a much simpler method of threshold segmentation has also performed well, and been proven to be effective in the mapping of burned forest areas.…”

An Exploration of Some Pitfalls of Thematic Map Assessment Using the New Map Tools Resource

“…That is simply the sum of the confusion matrix diagonal divided by the sum of the entire confusion matrix. Although this is a map-level metric, it has a close relative at the category level, the "portmanteau" accuracy [13]. While overall accuracy is intuitive to grasp, it can be misused or misleading.…”

“…Thus, most of the information contained in the figure of 99.0% has nothing to do with the category of interest. At least one published accuracy metric, the 'partial portmanteau' accuracy [13], also known as the 'figure of merit' [22], is robust to this source of bias. The basic 'portmanteau' accuracy is simply overall accuracy computed on a matrix collapsed to a presence/absence matrix of the cover type of interest [13], the same calculation that gave the value of 99.0% value above.…”

An information-based criterion to measure pixel-level thematic uncertainty in land cover classifications

“…Accuracy measures have been designed to report accuracy both at the map level and at the class level [see (Story and Congalton 1986) for examples] and are typically assumed to apply uniformly over the region of interest. Yet several studies have also demonstrated that errors vary spatially (Liu et al 2004;Foody 2005;Comber et al 2012;Renier et al 2015;Liu et al 2015;Waldner et al 2015b;Feng et al 2015).…”