基于双向门控尺度特征融合的遥感场景分类  

Remote sensing scene classification based on bidirectional gated scale feature fusion

作　　者：宋中山[1,2] 梁家锐 郑禄[1,2] 刘振宇 帖军[1,2] SONG Zhongshan;LIANG Jiarui;ZHENG Lu;LIU Zhenyu;TIE Jun(College of Computer Science,South-Central University for Nationalities,Wuhan Hubei 430074,China;Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises(South-Central University for Nationalities),Wuhan Hubei 430074,China;College of Resources and Environmental Science,South-Central University for Nationalities,Wuhan Hubei 430074,China)

机构地区：[1]中南民族大学计算机科学学院,武汉430074 [2]湖北省制造企业智能管理工程技术研究中心(中南民族大学),武汉430074 [3]中南民族大学资源与环境学院,武汉430074

出　　处：《计算机应用》2021年第9期2726-2735,共10页journal of Computer Applications

基　　金：湖北省技术创新专项(重大项目)(2019ABA101);武汉市科技计划应用基础前沿项目(2020020601012267);中南民族大学研究生学术创新基金资助项目(3212020sycxjj130)。

摘　　要：针对遥感影像数据集的图像在形状、纹理和颜色上存在较大差别,以及因拍摄高度和角度不同存在的尺度差异导致遥感场景分类精度不高的问题,提出利用主动旋转聚合来融合不同尺度的特征,并通过双向门控提高底层特征与顶层特征互补性的特征融合补偿卷积神经网络(FAC-CNN)。该网络利用图像金字塔为原始图像生成不同尺度图像后将其输入到分支网络中来提取多尺度特征,并提出主动旋转聚合的方式来融合不同尺度的特征,使融合后的特征具有方向信息,从而提高模型对不同尺度输入以及不同旋转输入的泛化能力,实现模型分类精度的提升。FAC-CNN比基于VGGNet的注意循环卷积网络(ARCNet-VGGNet)和门控双向网络(GBNet)在西北工业大学遥感场景图像分类数据集(NWPU-RESISC)上准确率分别提升了2.05个百分点与2.69个百分点,在航空影像数据集(AID)上准确率分别提升了3.24个百分点与0.86个百分点。实验结果表明,FAC-CNN能有效解决遥感影像数据集存在的问题,提高遥感场景分类的精度。There are large differences in shape,texture and color of images in remote sensing image datasets,and the classification accuracy of remote sensing scenes is low due to the scale differences cased by different shooting heights and angles.Therefore,a Feature Aggregation Compensation Convolution Neural Network(FAC-CNN)was proposed,which used active rotation aggregation to fuse features of different scales and improved the complementarity between bottom features and top features through bidirectional gated method.In the network,the image pyramid was used to generate images of different scales and input them into the branch network to extract multi-scale features,and the active rotation aggregation method was proposed to fuse features of different scales,so that the fused features have directional information,which improved the generalization ability of the model to different scale inputs and different rotation inputs,and improved the classification accuracy of the model.On NorthWestern Polytechnical University REmote Sensing Image Scene Classification(NWPU-RESISC)dataset,the accuracy of FAC-CNN was increased by 2.05 percentage points and 2.69 percentage points respectively compared to those of Attention Recurrent Convolutional Network based on VGGNet(ARCNet-VGGNet)and Gated Bidirectional Network(GBNet);and on Aerial Image Dataset(AID),the accuracy of FAC-CNN was increased by 3.24 percentage points and 0.86 percentage points respectively compared to those of the two comparison networks.Experimental results show that FAC-CNN can effectively solve the problems in remote sensing image datasets and improve the accuracy of remote sensing scene classification.

关 键 词：遥感图像 场景分类 双向门控方法 卷积神经网络 主动旋转聚合 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]