当前位置: X-MOL 学术Int. J. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
New SAR target recognition based on YOLO and very deep multi-canonical correlation analysis
International Journal of Remote Sensing ( IF 3.0 ) Pub Date : 2021-08-04 , DOI: 10.1080/01431161.2021.1953719
Moussa Amrani 1 , Abdelatif Bey 1 , Abdenour Amamra 1
Affiliation  

ABSTRACT

Synthetic Aperture Radar (SAR) images are prone to be contaminated by noise, which makes it very difficult to perform target recognition in SAR images. Inspired by great success of very deep convolutional neural networks (CNNs), this paper proposes a robust feature extraction method for SAR image target classification by adaptively fusing effective features from different CNN layers. First, YOLOv4 network is fine-tuned to detect the targets from the respective MF SAR target images. Second, a very deep CNN is trained from scratch on the moving and stationary target acquisition and recognition (MSTAR) database by using small filters throughout the whole net to reduce the speckle noise. Besides, using small-size convolution filters decreases the number of parameters in each layer and, therefore, reduces computation cost as the CNN goes deeper. The resulting CNN model is capable of extracting very deep features from the target images without performing any noise filtering or pre-processing techniques. Third, our approach proposes to use the multi-canonical correlation analysis (MCCA) to adaptively learn CNN features from different layers such that the resulting representations are highly linearly correlated and therefore can achieve better classification accuracy even if a simple linear support vector machine is used. Experimental results on the MSTAR dataset demonstrate that the proposed method outperforms the state-of-the-art methods.



中文翻译:

基于YOLO和极深多典型相关分析的新型SAR目标识别

摘要

合成孔径雷达 (SAR) 图像容易受到噪声的污染,这使得在 SAR 图像中进行目标识别非常困难。受极深卷积神经网络 (CNN) 巨大成功的启发,本文通过自适应融合来自不同 CNN 层的有效特征,提出了一种用于 SAR 图像目标分类的鲁棒特征提取方法。首先,对 YOLOv4 网络进行微调以从各自的 MF SAR 目标图像中检测目标。其次,通过在整个网络中使用小滤波器来减少斑点噪声,在移动和静止目标采集和识别 (MSTAR) 数据库上从头开始训练非常深的 CNN。此外,使用小尺寸卷积滤波器减少了每一层的参数数量,因此随着 CNN 的深入,计算成本也降低了。由此产生的 CNN 模型能够从目标图像中提取非常深的特征,而无需执行任何噪声过滤或预处理技术。第三,我们的方法建议使用多规范相关分析 (MCCA) 来自适应地学习来自不同层的 CNN 特征,使得结果表示高度线性相关,因此即使使用简单的线性支持向量机也可以获得更好的分类精度. MSTAR 数据集上的实验结果表明,所提出的方法优于最先进的方法。我们的方法建议使用多规范相关分析 (MCCA) 来自适应地学习来自不同层的 CNN 特征,这样得到的表示是高度线性相关的,因此即使使用简单的线性支持向量机也可以获得更好的分类精度。MSTAR 数据集上的实验结果表明,所提出的方法优于最先进的方法。我们的方法建议使用多规范相关分析 (MCCA) 来自适应地学习来自不同层的 CNN 特征,这样得到的表示是高度线性相关的,因此即使使用简单的线性支持向量机也可以获得更好的分类精度。MSTAR 数据集上的实验结果表明,所提出的方法优于最先进的方法。

更新日期:2021-08-04
down
wechat
bug