超尺度自导注意力网络的遥感船舶识别  

Remote Sensing Ship Recognition Based on Hyper-Scale Self-Guided Attention Networks

作　　者：陈会伟[1] 刘树美 刘培学[1] 公茂法 CHEN Huiwei;LIU Shumei;LIU Peixue;GONG Maofa(Institute of Intelligent Manufacturing,Qingdao Huanghai University,Qingdao,Shandong 266427,China;College of Electrical Engineering and Automation,Shandong University of Science and Technology,Qingdao,Shandong 266427,China)

机构地区：[1]青岛黄海学院智能制造学院,山东青岛266427 [2]山东科技大学电气与自动化工程学院,山东青岛266427

出　　处：《计算机工程》2021年第10期314-320,共7页Computer Engineering

基　　金：山东省重点研发计划(2017GGX20100,2019GGX105001);山东省高等学校科技计划项目(J18KB163);青岛黄海学院重点项目(2019KJ01,2019KJ02)。

摘　　要：传统多尺度卷积神经网络因接收域有限,难以对超尺度变化的空间目标进行建模。提出一种遥感船舶的超尺度自导注意力网络(HSSGAN)识别框架,通过组连接的轻量级超尺度子空间模块捕获船舶的超尺度特征和尺度不变性,使用自导注意力网络逐步细化超尺度特征图,并在超尺度局部和全局语义之间建立长期依赖关系以增强类之间特征图的差异性。同时,通过忽略不相关信息及聚合相关特征以增强目标船舶的识别性。实验结果表明,与TP-FCN、CF-SDN和HSF-Net方法相比,HSSGAN方法具有更好的识别效果,F1-Score值为0.96678。Due to the limited reception domain,the existing multi-scale Convolutional Neural Networks(CNN)often fail to model space targets with super-scale variation.In order to solve this problem,a Hyper-Scale Self-Guided Attention Networks(HSSGAN)recognition framework for remote sensing ships is proposed.The framework employs a lightweight super-scale subspace module connected by groups to capture the super-scale feature and scale invariance of the ship.Then the super-scale feature map is refined gradually by using the self-guided attention,and a long-term dependency relationship is established between the super-scale local and global semantics adaptively to enhance the difference of the feature maps between classes.In addition,irrelevant information is ignored while relevant features are aggregated,so the identifiability of the target ship can be enhanced.The experimental results show that the HSSGAN method exhibits improved recognition performance with the F1 value reaching 0.96678.

关 键 词：目标识别 遥感图像 卷积神经网络 超尺度特征 子空间模块 组连接 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]