李尚生,
李相平,
但波,
王旭坤
海军航空大学 烟台 264001
详细信息
作者简介:付哲泉:男,1992年生,博士生,研究方向为精确制导技术及其智能化
李尚生:男,1965年生,教授,研究方向为导弹制导技术
李相平:男,1963年生,教授,研究方向为精确制导和目标探测技术
但波:男,1985年生,讲师,研究方向为目标识别与选择技术
王旭坤:男,1995年生,硕士生,研究方向为雷达目标识别技术
通讯作者:付哲泉 fuzq2413@163.com
中图分类号:TN957.51计量
文章访问数:4188
HTML全文浏览量:920
PDF下载量:83
被引次数:0
出版历程
收稿日期:2019-11-14
修回日期:2020-04-16
网络出版日期:2020-04-25
刊出日期:2020-12-08
Ship Target Recognition Based on Highly Efficient Scalable Improved Residual Structure Neural Network
Zhequan FU,,Shangsheng LI,
Xiangping LI,
Bo DAN,
Xukun WANG
Naval Aviation University, Yantai 264001, China
摘要
摘要:神经网络的深度在一定范围内与识别效果成正相关,为解决超出范围后网络层数增加识别准确率却下降的模型饱和问题,该文提出一种具有高效的微块内部结构和残差网络结构的神经网络模型,用于对舰船目标基于高分辨距离像的分类识别。该方法利用具有小尺度卷积核的卷积模块提取目标的稳定可分特征,同时利用联合损失函数约束目标特征的类内距离提高识别能力。仿真结果表明,该模型相比于其他常见网络结构,在模型参数更少的情况下,识别效果更好,同时具有较强的噪声鲁棒性。
关键词:目标识别/
高分辨距离像/
神经网络/
残差结构
Abstract:The depth of neural network is positively correlated with the recognition effect in a certain range. In order to solve the problem that model recognition accuracy decreases when the number of network layers increases after exceeding the range. A neural network model with efficient micro internal blocks structure and residual network structure is proposed, which is used for recognition of ship targets based on High Range Resolution Profile (HRRP) data. In this method, the convolution module with a small scale convolution kernel is used to extract automatically the stable and separable features of target. And the intra-class distance of the target is constrained by the joint loss function to improve the recognition ability. Simulation results show that compared with other common network structures, this model has better recognition performance and stronger noise robustness with fewer model parameters.
Key words:Target recognition/
High Range Resolution Profile (HRRP)/
Neural Network (NN)/
Residual Structure
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=1347634f-6f97-4b11-9a38-984505fddb3c