Supervised methods of image segmentation accuracy assessment in land cover mapping

Abstract

Land cover mapping via image classification is sometimes realized through object-based 6 image analysis. Objects are typically constructed by partitioning imagery into spatially 7 contiguous groups of pixels through image segmentation and used as the basic spatial unit of 8 analysis. As it is typically desirable to know the accuracy with which the objects have been 9delimited prior to undertaking the classification, numerous methods have been used for accuracy assessment. This paper reviews the state-of-the-art of image segmentation accuracy 11 assessment in land cover mapping applications. First the literature published in three major 12 remote sensing journals during 2014-2015 is reviewed to provide an overview of the field. This revealed that qualitative assessment based on visual interpretation was a widely-used method, but a range of quantitative approaches is available. In particular, the empirical discrepancy or supervised methods that use reference data for assessment are thoroughly 16 reviewed as they were the most frequently used approach in the literature surveyed.Supervised methods are grouped into two main categories, geometric and non-geometric, and are translated here to a common notation which enables them to be coherently and 19 unambiguously described. Some key considerations on method selection for land cover 20 mapping applications are provided, and some research needs are discussed.

Normalization in Unsupervised Segmentation Parameter Optimization: A Solution Based on Local Regression Trend Analysis

“…First, we computed segmentation goodness metrics (discrepancy measures) to directly measure the quality of each segmentation method. These metrics are based on overlaying operations between produced segments and reference objects and are extensively described in several studies [4,16,[40][41][42]. We manually digitized 20 objects of interest in each ROI for the buildings and tree categories to serve as reference polygons.…”

OIC-MCE: A Practical Land Cover Mapping Approach for Limited Samples Based on Multiple Classifier Ensemble and Iterative Classification

“…In order to avoid the "Salt and Pepper Noise" often existing in pixel-based classification results, and to take fully into consideration spectral, shape, and texture features, the object-oriented classification method was adopted [44][45][46]. The multi-resolution segmentation algorithm, adopted by the eCognition Developer 8.7, was adopted in this study.…”

Expansion of Rural Settlements on High-Quality Arable Land in Tongzhou District in Beijing, China

“…Aside from the error matrix, several other approaches have been proposed for accuracy assessment [59], such as the approach of fuzzy sets [60], an error model developed by Michael et al [61], and a weighted analysis of variance adjustment approach [62]. It can be seen that there is no standard method for accuracy assessment [59]. Considering the wide adoption of an error matrix, we assessed the accuracy of our maps based on an error matrix [56,63,64].…”