Deep Interactive Segmentation Model with Dual Attention for Land Cover Intelligent Marking
In order to solve the problems of poor quality and low efficiency of current manual marking,this paper proposes a deep interactive segmentation model with dual attention for land cover intelligent marking. Firstly,the disk coding meth-od is used to simulate the user's point click interaction infor-mation,and the HRNet_18s network is used to extract the se-mantic information of the ground objects. Then,channel at-tention and spatial attention are introduced to strengthen the feature information of local important objects and suppress the feature information of interference background. Finally,the features are input into the OCRNet to further refine,and the segmentation results are obtained. In order to verify the effec-tiveness of this method,comparative experiments were con-ducted on two public datasets. The experimental results show that this method can effectively reduce the number of user in-teractions on the same segmentation accuracy,which is help-ful to improve the efficiency of intelligent land cover marking.
deep interactive segmentation modelmarkingland cover updatingspatial attentionchannel attention
NETL
NSTL
万方数据
