Urban mapping, accuracy, & image classification: A comparison of multiple approaches in Tsukuba City, Japan

概要

論文の詳細を見る
The rapid growth of urban space and its environmental challenges require precisemapping techniques to represent complex earth surface features more accurately. In thisstudy, we examined four mapping approaches (unsupervised, supervised, fuzzy supervisedand GIS post-processing) using Advanced Land Observing Satellite images to predict urbanland use and land cover of Tsukuba city in Japan. Intensive fieldwork was conducted tocollect ground truth data. A random stratified sampling method was chosen to generategeographic reference data for each map to assess the accuracy. The accuracies of the mapswere measured, producing error matrices and Kappa indices. The GIS post-processingapproach proposed in this research improved the mapping results, showing the highestoverall accuracy of 89.33% as compared to other approaches. The fuzzy supervisedapproach yielded a better accuracy (87.67%) than the supervised and unsupervisedapproaches. The fuzzy supervised approach effectively dealt with the heterogeneoussurface features in residential areas. This paper presents the strengths of the mappingapproaches and the potentials of the sensor for mapping urban areas, which may helpurban planners monitor and interpret complex urban characteristics.