基于深度学习的自然资源调查监测图斑辅助辨识方法OA

The image data collected by the Natural Resource Survey and Monitoring Institute suffers from incomplete labeling,where many images are assigned only limited tags,making it difficult to fully learn accurate mapping relationship between images and natural resource categories.This results in poor auxilia-ry identification performance for monitoring patches.In this paper,a deep learning-based method for auxiliary identification of natural resource survey and monitoring patches has been put forward.By map-ping from spatial domain of monitoring images to the label space of natural resources,the method en-hances the annotation of natural resource survey and monitoring image data and prevents overfitting.Based on constructing a deep learning model and incorporating a self-attention mechanism for patch classifica-tion and localization,the mapping relationship between images and natural resource categories has been an-alyzed.It divides the target loss function values,constructs a patch auxiliary identification formula,and a-chieves auxiliary identification of patches.As showed by experimental results,the identified patch points 1,2,3,and 4 correspond to coordinates(0,-30),(60,-12),(60,-55),and(40,-30)respectively.It is consistent with actual location.The minimum time consumption is 15 seconds with strong identification capability.