Preview  

出　　处：《Journal of Geodesy and Geoinformation Science》2020年第2期I0002-I0002,共1页测绘学报（英文版）

摘　　要：A Remote Sensing Image Semantic Segmentation Method by Combining De formable Convolution with Conditional Random Fields Zongcheng ZUO1,Wen ZHANG2,Dongying ZHANG31.Schood of Aeronautics and Astronoutics,Shanghai Jiao Tong Uniberily。Shanghai 200240,China;2.School of Remole Sensing and Informarion Engineering,Wuhan Unieriy,Wushan 430079,China;3.Schood of Hydrppower and Information Eninering.Huashong Uninersity of Science and Technologr,Wuhan 430074,China.Abstract:Curently,deep convolutional neunal networks have made great progres in the field of semantie segmentation.Because of the fixed convolution kemel geometry,standard convolution neural networks have been limited in the ability to simulate geomnetric transformations.Therefore。a deformable convolution is introduced to enhance the adaptability of coovolutional neheorks to spatial transformation.

关 键 词：CONVOLUTION ring. progr 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]