中国专利数据库

专利名称:【中文】基于轻量化语义分割网络的遥感图像地物分类方法 【EN】Remote sensing image ground feature classification method based on lightweight semantic segmentation network

专利申请号201911300840.9
申请日2019.12.17
公开(公告)号CN111079649A
公开(公告)日2020.04.28
主分类号G06K9/00
分案原申请号
分类号G06K9/00 G06K9/44 G06K9/62
优先权
申请(专利权)人【中文】西安电子科技大学【EN】XIDIAN University
地址【中文】710071 陕西省西安市太白南路2号【EN】Xi'an City, Shaanxi province Taibai Road 710071 No. 2
发明(设计)人【中文】张向荣;王昕;焦李成;李辰;唐旭;周挥宇;陈璞花;古晶【EN】Zhang Xiangrong;Wang Xin;Jiao Licheng;Li Chen;Tang Xu;Zhou Huiyu;Chen Puhua;Gu Jing
国际申请
国际公布
进入国家阶段日期
专利代理机构【中文】陕西电子工业专利中心 61205【EN】Shaanxi Electronics Industry Patent Center
代理人【中文】王品华;黎汉华【EN】Wang Pinhua;Li Hanhua
专利类型发明专利
摘要【中文】本发明公开了一种基于轻量化语义分割网络的遥感图像地物分类方法,主要解决现有方法由于图像空间和通道特征信息利用不足且模型庞大,而导致的对遥感图像地物分类精度不高、训练速度较慢的问题。其方案为:在遥感图像地物分类数据集中获取训练样本和测试样本;构建引入可拓宽通道分解空洞卷积的轻量化遥感图像地物分类模型,设计关注地物边缘的整体损失函数;将训练样本输入到所构建的地物分类模型中训练,得到训练好的模型;将测试样本输入训练好的模型中,预测输出遥感图像中地物分类结果。本发明提升了特征的表达能力,减少了网络参数,提高了遥感图像地物分类的平均精度和训练速度,可用于获取一幅遥感图像的地物分布情况。 【EN】The invention discloses a remote sensing image ground feature classification method based on a lightweight semantic segmentation network, which mainly solves the problems of low precision and low training speed of remote sensing image ground feature classification caused by insufficient utilization of image space and channel characteristic information and huge model in the existing method. The scheme is as follows: acquiring a training sample and a test sample in a remote sensing image ground object classification data set; constructing a lightweight remote sensing image ground object classification model introducing the convolution of the widened channel decomposition cavity, and designing an integral loss function concerning the edge of the ground object; inputting the training sample into the constructed ground feature classification model for training to obtain a trained model; and inputting the test sample into the trained model, and predicting and outputting the ground feature classification result in the remote sensing image. The invention improves the expression capability of the characteristics, reduces the network parameters, improves the average precision and the training speed of the ground feature classification of the remote sensing image, and can be used for obtaining the ground feature distribution condition of one remote sensing image.
全文下载下载
©2021 Patent9.com All rights reserved.