ABSTRACT
Due to the particularity of ginseng cultivation, the soil fertility of cultivated ginseng is seriously depleted, so that the cultivated ginseng land can not be reused in the short term, and the land area available for cultivating ginseng becomes less and less with the growth of ginseng cultivation time. Therefore, in order to effectively manage ginseng cultivation, and achieve the sustainable use of ginseng land, it is necessary to obtain accurate information on the distribution of ginseng planting space. In this study, the object-oriented classification method based on rule set was used to extract ginseng planting area based on the ZY-3 satellite data in Fusong county, Jilin province. Firstly, multi-scale segmentation of ZY-3 remote sensing image in the study area was made, and the optimal segmentation scale was determined on the basis of multi-scale segmentation results. Secondly, a spectral curve according to the different feature type samples was generated. The similarities and differences between ginseng plot and other types of surface features were analyzed, and a rule set based on the results of spectral analysis was established to achieve the final extraction. The results show that the object-oriented classification method based on rule set can effectively extract the ginseng planting plots in the study area, and solve the problem that the extraction result is broken compared with the traditional pixel-based classification method.