〈Original Papers〉Image classification techniques in mapping urban landscape : A case study of Tsukuba city using AVNIR-2 sensor data

Although several techniques to extract the land uses from remotely sensed data have been evolving, mapping urban landscape with enough accuracy is not completely achieved. This paper aims to evaluate image classification methods for mapping the urban landscape of a fast growing city in the Tokyo metropolitan fringe using Advanced Land Observing Satellite (ALOS) data. Three image classification methods: unsupervised, supervised and fuzzy supervised were evaluated. An AVNIR-2 sensor image of ALOS satellite covering Tsukuba city was used for the study. Field survey data including high resolution satellite image and aerial photographs were used for scheming land use types, selecting training samples and assessing accuracies of the classification results. Seven types of land uses: forested land; lawn/ grass; paddy field; dry farmland/exposed field; facility/ industry; residence/parking/road/upland bare field and water were extracted using the methods. Error matrix and Kappa index were computed to measure the map accuracy. The fuzzy supervised method improved the mapping results showing highest overall accuracy of 87.7% as compared to supervised and unsupervised methods. The fuzzy method effectively dealt with the mixed pixels that appeared in the residential area. The study also revealed that the image classification method greatly influences the spatial statistics of land use types.