首页 > 论文 > 激光与光电子学进展 > 56卷 > 23期(pp:231006--1)

飞机目标分类的深度卷积神经网络设计优化

Design and Optimization of Deep Convolutional Neural Network for Aircraft Target Classification

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对使用传统方法和神经网络对飞机目标分类时遇到的准确率低、分类种类少等问题,研究了深度卷积神经网络(DCNN)在飞机目标分类中的可行性。为了匹配模型容量、避免过拟合、提高分类性能等,设计了9层DCNN模型,并使用随机梯度下降优化器进行优化。在数据集中选用6类具有代表性的飞机类型进行实验,提出两种正则化级联方式以防止过拟合并加快模型收敛,最终实现了99.1%的飞机分类准确率,由此说明该DCNN模型在飞机目标分类中的有效性。通过归一化混淆矩阵分析分类结果,给出了每类飞机自分类的准确率。此外,设计了一组对比实验,用经典的AlexNet在同一数据集上进行测试,结果表明,所设计的DCNN的准确率高于AlexNet分类算法95.5%。该模型有效地解决了飞机目标分类精度低的问题,在军事和民航飞机目标的分类研究中具有一定的参考价值和应用前景。

Abstract

Aiming at the problems of low classification accuracy and less classification types in the classification for aircraft targets by using conventional methods and neural networks, the feasibility of deep convolutional neural network (DCNN) models is studied. To match model capacity, avoid overfitting, and improve classification performance, a nine-layer DCNN model is designed and optimized with stochastic gradient descent optimizer. Six representative types of aircrafts are selected in the dataset, and two regularization cascade methods are proposed to prevent overfitting and speed up the model convergence. Finally, an aircraft classification accuracy of 99.1% is achieved, which demonstrates the effectiveness of the DCNN model in aircraft target classification. By analyzing the classification results of the normalized confusion matrix, the accuracy of the self-classification of each type of aircraft is given. In addition, a group of comparative experiments are designed to test the same dataset with the classic AlexNet. The results show that the proposed DCNN model is superior to the AlexNet classification algorithm with an accuracy improvement of 95.5%. This model effectively solves the problem of low accuracy in aircraft target classification at present and proves that the DCNN model has certain reference values and application prospects in the classification research of military and civil aviation aircraft targets.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.231006

所属栏目:图像处理

基金项目:光电信息控制和安全技术重点实验室基金;

收稿日期:2019-05-15

修改稿日期:2019-06-03

网络出版日期:2019-12-01

作者单位    点击查看

马俊成:河北工业大学电子信息工程学院, 天津 300401
赵红东:河北工业大学电子信息工程学院, 天津 300401
杨东旭:河北工业大学电子信息工程学院, 天津 300401
康晴:河北工业大学电子信息工程学院, 天津 300401

联系人作者:赵红东(zhaohd@hebut.edu.cn)

备注:光电信息控制和安全技术重点实验室基金;

【1】Chen Y, Fan R S, Wang J X, et al. Cloud detection of ZY-3 satellite remote sensing images based on deep learning [J]. Acta Optica Sinica. 2018, 38(1): 0128005.
陈洋, 范荣双, 王竞雪, 等. 基于深度学习的资源三号卫星遥感影像云检测方法 [J]. 光学学报. 2018, 38(1): 0128005.

【2】Yan M, Zhao H D, Li Y H, et al. Multi-classification and recognition of hyperspectral remote sensing objects based on convolutional neural network [J]. Laser & Optoelectronics Progress. 2019, 56(2): 021702.
闫苗, 赵红东, 李宇海, 等. 基于卷积神经网络的高光谱遥感地物多分类识别 [J]. 激光与光电子学进展. 2019, 56(2): 021702.

【3】He S L, Xu J H, Zhang S Y. Land use classification of object-oriented multi-scale by UAV image [J]. Remote Sensing for Land & Resources. 2013, 25(2): 107-112.
何少林, 徐京华, 张帅毅. 面向对象的多尺度无人机影像土地利用信息提取 [J]. 国土资源遥感. 2013, 25(2): 107-112.

【4】Zhang J, Zhao H D, Li Y H, et al. Classifier for recognition of fine-grained vehicle models under complex background [J]. Laser & Optoelectronics Progress. 2019, 56(4): 041501.
张洁, 赵红东, 李宇海, 等. 复杂背景下车型识别分类器 [J]. 激光与光电子学进展. 2019, 56(4): 041501.

【5】Li J N, Zhang B H. Face recognition by feature matching fusion combined with improved convolutional neural network [J]. Laser & Optoelectronics Progress. 2018, 55(10): 101504.
李佳妮, 张宝华. 特征匹配融合结合改进卷积神经网络的人脸识别 [J]. 激光与光电子学进展. 2018, 55(10): 101504.

【6】Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors [J]. Nature. 1986, 323(6088): 533-536.

【7】Zhan G K, Xia Z L. Plane image recognition based on support vector machine [J]. Modern Electronics Technique. 2007, 30(21): 127-129.
战国科, 夏哲雷. 基于支持向量机的飞机图像识别算法 [J]. 现代电子技术. 2007, 30(21): 127-129.

【8】Tian R J, Yang F. Features extraction and selection of air target recognitions [J]. Ordnance Industry Automation. 2014, 33(3): 80-83.
田瑞娟, 杨帆. 基于空中目标识别的特征提取与选择 [J]. 兵工自动化. 2014, 33(3): 80-83.

【9】Yao H Q. Jiang Y L. Based on the genetic algorithm to optimize the BP neural network in the degree of concrete creep prediction model. Applied Mechanics, Materials[J]. 2014, 584/585/586: 1346-1350.

【10】Tang X P, Yang X G, Liu Y F, et al. Aircraft recognition based on deep convolutional neural network [J]. Electronics Optics & Control. 2018, 25(5): 68-72.
唐小佩, 杨小冈, 刘云峰, 等. 基于深度卷积神经网络的飞机识别研究 [J]. 电光与控制. 2018, 25(5): 68-72.

【11】LeCun Y, Bottou L, Bengio Y, et al. . Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE. 1998, 86(11): 2278-2324.

【12】Ouyang R Q, Yong Y, Wang B X. Application of convolution neural network in aircraft type recognition [J]. Ordnance Industry Automation. 2017, 36(12): 71-75.
欧阳瑞麒, 雍杨, 王兵学. 卷积神经网络在飞机类型识别中的应用 [J]. 兵工自动化. 2017, 36(12): 71-75.

【13】Yuan L S, Lou M Y, Liu Y Q, et al. Palm vein classification based on deep neural network and random forest [J]. Laser & Optoelectronics Progress. 2019, 56(10): 101010.
袁丽莎, 娄梦莹, 刘娅琴, 等. 结合深度神经网络和随机森林的手掌静脉分类 [J]. 激光与光电子学进展. 2019, 56(10): 101010.

【14】LeCun Y, Bengio Y, Hinton G. Deep learning [J]. Nature. 2015, 521(7553): 436-444.

【15】Schmidhuber J. Deep learning in neural networks: an overview [J]. Neural Networks. 2015, 61: 85-117.

【16】Zheng Z Y, Gu S Y. TensorFlow: Google deep learning framework in action[M]. Beijing: Publishing House of Electronics Industry, 2017.
郑泽宇, 顾思宇. TensorFlow: 实战Google深度学习框架[M]. 北京: 电子工业出版社, 2017.

【17】Liu Q, Tang X L, Zhang N. Structure optimized convolutional neural network based on unsupervised pre-training [J]. Advanced Engineering Sciences. 2017, 49(s2): 210-215.
刘庆, 唐贤伦, 张娜. 基于非监督预训练的结构优化卷积神经网络 [J]. 工程科学与技术. 2017, 49(s2): 210-215.

引用该论文

Ma Juncheng,Zhao Hongdong,Yang Dongxu,Kang Qing. Design and Optimization of Deep Convolutional Neural Network for Aircraft Target Classification[J]. Laser & Optoelectronics Progress, 2019, 56(23): 231006

马俊成,赵红东,杨东旭,康晴. 飞机目标分类的深度卷积神经网络设计优化[J]. 激光与光电子学进展, 2019, 56(23): 231006

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF