Spectral Characteristic Analysis and Remote Sensing Classification of Coastal Aquaculture Areas Based on GF-1 Data

Abstract

Zhu, H.; Li, K.; Wang, L.; Chu, J.; Gao, N., and Chen, Y., 2019. Spectral characteristic analysis and remote sensing classification of coastal aquaculture areas based on GF-1 data. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp. 49-57. Coconut Creek (Florida), ISSN 0749-0208.In this research, the offshore area of Bohai Sea, which is located at Yantai City in Shandong Province, was selected as the experimental region and the GF-1 data was used as experimental data. First, the spectral characteristics of different target objects in the study area were investigated using the sample point analysis method. The corresponding spectral discriminant function was also constructed. Second, the object-oriented multi-scale segmentation method was employed to perform the object segmentation of GF-1 image. Finally, the image segmentation results were classified through the constructed discriminant function of the spectral characteristics of target objects. The remote sensing classification results of coastal aquaculture areas were also obtained. The overall accuracy of such classification results was 91.6 %. Compared with traditional classification methods, classification accuracy improved greatly and the classified aquaculture types increased.