The Sensitivity of Mapping Methods to Reference Data Quality: Training Supervised Image Classifications with Imperfect Reference Data

ISPRS International Journal of Geo-Information

Duccio Rocchini¹  Mahesh Pal²  Carol X. Garzon-Lopez³  Lucy Bastin⁴  Giles M. Foody⁵ 

[1] Department of Biodiversity and Molecular Ecology, Research and Innovation Centre, Fondazione Edmund Mach, Via E. Mach 1, 38010 San Michele all’dige TN, Italy;Department of Civil Engineering, National Institute of Technology, Kurukshetra, Haryana 136119, India;Ecology and Dynamics of Human-Influenced Systems Research Unit (EDYSAN, FRE 3498 CNRS), University of Picardy Jules Verne, 1 rue des Louvels, FR-80037 Amiens Cedex 1, France;School of Engineering and Applied Science, Aston University, Birmingham, B4 7ET, UK;School of Geography, University of Nottingham, Nottingham, NG7 2RD, UK;

关键词: classification;    training;    error;    accuracy;    remote sensing;    land cover;   

DOI  :  10.3390/ijgi5110199

来源: DOAJ

【 摘 要 】

The accuracy of a map is dependent on the reference dataset used in its construction. Classification analyses used in thematic mapping can, for example, be sensitive to a range of sampling and data quality concerns. With particular focus on the latter, the effects of reference data quality on land cover classifications from airborne thematic mapper data are explored. Variations in sampling intensity and effort are highlighted in a dataset that is widely used in mapping and modelling studies; these may need accounting for in analyses. The quality of the labelling in the reference dataset was also a key variable influencing mapping accuracy. Accuracy varied with the amount and nature of mislabelled training cases with the nature of the effects varying between classifiers. The largest impacts on accuracy occurred when mislabelling involved confusion between similar classes. Accuracy was also typically negatively related to the magnitude of mislabelled cases and the support vector machine (SVM), which has been claimed to be relatively insensitive to training data error, was the most sensitive of the set of classifiers investigated, with overall classification accuracy declining by 8% (significant at 95% level of confidence) with the use of a training set containing 20% mislabelled cases.

【 授权许可】

Unknown