Non-locally Enhanced Feature Fusion Network for Aircraft Recognition in Remote Sensing Images
Non-locally Enhanced Feature Fusion Network for Aircraft Recognition in Remote Sensing Images
复制标题
用于遥感图像中飞机识别的非局部增强特征融合网络
DOI：
10.3390/rs12040681
复制
发表时间：
2020-02
期刊：
影响因子：
5
通讯作者：
Wang Kang
中科院分区：
文献类型：
--
作者：
Xiong Yunsheng;Niu Xin;Dou Yong;Qie Hang;Wang Kang
飞机识别具有很大的应用价值，但遥感图像中的飞机存在分辨率低、对比度差、清晰度差、垂直视角下缺乏细节等问题，这给飞机识别带来了很大的困难。特别是在飞机种类繁多、飞机之间差异细微的情况下，对飞机的细粒度识别更具挑战性。本文提出了一种非局部增强特征融合网络(NLFFNet)，并试图充分利用飞机可识别部件的特征。首先，针对飞机图像的远距离自相关性，采用非局部增强操作，引导网络更加关注区分区域，增强有利于分类的特征。其次，提出了一种零件级特征融合机制(PFF)，该机制在共享特征图上裁剪飞机的5个零件，然后通过零件全连接层(PFC)提取零件内部的细微特征，并通过组合全连接层(CFC)将这些零件的特征融合在一起。此外，通过采用改进的损失函数，可以在提高损失函数中硬例子的权重的同时，降低过难例子的权重，提高了网络的整体识别能力。数据集包括47类飞机，包括多架外观略有差异的同族飞机，在测试数据集上可以达到89.12%的准确率，证明了该方法的有效性。
Aircraft recognition has great application value, but aircraft in remote sensing images have some problems such as low resolution, poor contrasts, poor sharpness, and lack of details caused by the vertical view, which make the aircraft recognition very difficult. Especially when there are many kinds of aircraft and the differences between aircraft are subtle, the fine-grained recognition of aircraft is more challenging. In this paper, we propose a non-locally enhanced feature fusion network(NLFFNet) and attempt to make full use of the features from discriminative parts of aircraft. First, according to the long-distance self-correlation in aircraft images, we adopt non-locally enhanced operation and guide the network to pay more attention to the discriminating areas and enhance the features beneficial to classification. Second, we propose a part-level feature fusion mechanism(PFF), which crops 5 parts of the aircraft on the shared feature maps, then extracts the subtle features inside the parts through the part full connection layer(PFC) and fuses the features of these parts together through the combined full connection layer(CFC). In addition, by adopting the improved loss function, we can enhance the weight of hard examples in the loss function meanwhile reducing the weight of excessively hard examples, which improves the overall recognition ability of the network. The dataset includes 47 categories of aircraft, including many aircraft of the same family with slight differences in appearance, and our method can achieve 89.12% accuracy on the test dataset, which proves the effectiveness of our method.
登录
查看更多内容
DOI：
10.1109/jstars.2013.2280063
发表时间：
2014-06
影响因子：
5.5
作者：
Yanfei Zhong;Ruyi Feng;Liangpei Zhang
通讯作者：
Yanfei Zhong;Ruyi Feng;Liangpei Zhang
DOI：
10.1109/iccsee.2012.330
发表时间：
2012-03
期刊：
2012 International Conference on Computer Science and Electronics Engineering
影响因子：
--
作者：
Wu Henan;Ling Dejun;W. Hongwei;Liu Ying;Sun Xiaorui
通讯作者：
Wu Henan;Ling Dejun;W. Hongwei;Liu Ying;Sun Xiaorui
基于深度卷积神经网络分割的飞机类型识别
影响因子：
4.8
作者：
Jiawei Zuo;Guangluan Xu;Kun Fu;Xian Sun;Hao Sun
通讯作者：
Hao Sun
DOI：
--
发表时间：
2002
期刊：
2020 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices (ASEMD)
影响因子：
--
作者：
Gabriella Csurka;C. Dance;Lixin Fan;J. Willamowski;Cédric Bray
通讯作者：
Gabriella Csurka;C. Dance;Lixin Fan;J. Willamowski;Cédric Bray
DOI：
--
发表时间：
2011-07
期刊：
--
影响因子：
--
作者：
C. Wah;Steve Branson;P. Welinder;P. Perona;Serge J. Belongie
通讯作者：
C. Wah;Steve Branson;P. Welinder;P. Perona;Serge J. Belongie