Accuracy assessment model for classification result of remote sensing image based on spatial sampling

Abstract

Abstract. The classification accuracy of a remote sensing image should be assessed before the classification result is used for scientific investigation and policy decision. We proposed an accuracy assessment model based on spatial sampling to reflect region sensitivity of a remote sensing image. The proposed model aims to solve the following problems: (1) what sampling size should be selected for accuracy assessment; (2) where sample points should be distributed in a region; and (3) how to analyze the result of accuracy assessment. This assessment model was proposed based on gray-level co-occurrence matrix (GLCM) and considered both sampling size calculation and sample points distribution during the assessment. The overall accuracy and kappa coefficient derived from this model were very close to the true value derived from the total assessment, suggesting that the assessment accuracy of the model is close to that of total assessment. Compared with the percent sampling model, the model could quantify the relationship between GLCM-correlation parameter and sample size, thereby allowing producer and user to determine sample size according to spatial uniformity and heterogeneity. Compared with the random sampling model, the model could ensure that the sample points are uniformly distributed in the spatial region and proportionally distributed in different types of land cover. Taken together, the proposed model is suitable for the accuracy assessment of the classification result of a remote sensing image.

Retraction of invasiveSpartina alternifloraand its effect on the habitat loss of endangered migratory bird species and their decline in YNNR using remote sensing technology

“…Accuracy assessment determines the quality of information derived from a remotely sensed data and can reduce redundancy and assures assessment precision of a remotely sensed data (Huang et al., 2017). These assessments are either for a quick comparison of remote sensed data and map (qualitative assessment) or for the attempt to quantify and identify the error (quantitative assessment) in a remotely sensed classified data to see if it all corresponds to ground truth data or what is on the ground (Training Manual Developed by CEGIS, USFS and BFD, 2014‐15 & A.T.M.P., 2013).…”

“…Accuracy assessment determines the quality of information derived from a remotely sensed data and can reduce redundancy and assures assessment precision of a remotely sensed data (Huang et al, 2017). with the correspondence between the class label and "true" class (Anupam, 2017;Anupam Anand, 2012).…”

Surface Heterogeneity-Involved Estimation of Sample Size for Accuracy Assessment of Land Cover Product from Satellite Imagery

“…The landscape index, an index for quantitative analysis of landscape patterns, can measure the type, quantity, shape, spatial distribution, and complexity of the analysis units [46,47]. In recent years, an increasing number of studies have used the landscape index to describe spatial heterogeneity information, although their focus is not on the estimation of sample size, but on the layout of sample points [45,48] or land cover extraction [49,50]. According to the target of estimating the sample size of the surface coverage data, 14 landscape indicators were selected to describe the spatial heterogeneity information of the landscape levels in the watershed units from seven categories: area metrics, contrast metrics, edge metrics, shape metrics, proximity metrics, aggregation metrics, and diversity indexes.…”

Multitemporal analysis of vegetated land cover changes related to tin mining activity in Bangka Regency using Landsat imagery

“…Accuracy assessment is important to show the degree of truth from the classification results [12]. Testing classification accuracy is done by stacking reference data and digital classification data [13,14].…”