Ship recognition based on multi-band deep neural network

Feng LIU; Tong-sheng SHEN; Xin-xing MA; Jian ZHANG

doi:10.3788/OPE.20172511.2939

您当前的位置：

首页 >

文章列表页 >

Ship recognition based on multi-band deep neural network

Information Sciences | 更新时间：2020-07-07

- Ship recognition based on multi-band deep neural network
- Optics and Precision Engineering Vol. 25, Issue 11, Pages: 2939-2946(2017)
- 作者机构：
  
  1.海军航空工程学院控制工程系, 山东烟台 264001
  2.中国国防科技信息中心, 北京 100142
  3.91206部队, 山东青岛 266108
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20172511.2939
  CLC： TP391.4
- Received：11 April 2017，
  
  Accepted：30 June 2017，
  
  Published：25 November 2017
- 稿件说明：
移动端阅览
Feng LIU, Tong-sheng SHEN, Xin-xing MA, et al. Ship recognition based on multi-band deep neural network[J]. Optics and precision engineering, 2017, 25(11): 2939-2946.
DOI：

Feng LIU, Tong-sheng SHEN, Xin-xing MA, et al. Ship recognition based on multi-band deep neural network[J]. Optics and precision engineering, 2017, 25(11): 2939-2946. DOI： 10.3788/OPE.20172511.2939.

摘要

考虑多波段图像的融合识别可以扩展识别系统的应用范围，本文探索并设计了一种基于卷积神经网络的融合识别方法。该方法以AlexNet网络模型为基础，同时对可见光、中波红外和长波红外三波段图像进行特征提取；然后，利用互信息的方法对串联的三波段特征向量进行特征选择，依据重要性排序的方式选定固定长度的特征向量；最后，依据特征提取层级的不同，分别以早期融合、中期融合和后期融合3种融合方式来验证算法的有效性。采用自建的三波段舰船图像数据库进行了模型的训练和测试，共包含6类目标，5 000余张图像。实验结果显示，采用的3种融合识别方法中，中间层融合的识别准确率最高，达到84.5%，比早期融合和后期融合分别高5%和7%左右。另外，在本文的应用场景下，无论何种融合方式，其融合识别的准确率均明显高于其他单波段识别的准确率。

Abstract

The fusion recognition of multi-band images can extend the application range of recognition systems. A fusion method based on convolutional neural networks (CNN) was explored and designed in this paper. Based on the AlexNet network model

it was extracted that the ship target features of three wave band images concurrently in visible light

Middle Wave Infrared (MWIR) and Long Wave Infrared (LWIR) bands. Then

it performed the feature selection for concatenated three-band eigenvectors by using the mutual information method and determines the dimensions of fusion eigenvectors according to sorting the importance of concatenated feature eigenvectors. Finally

three fusion methods named as Early fusion

Middle fusion and Late fusion were used to verify respectively the effectiveness of the proposed algorithm according to the features extracted from different levels. An available ship target dataset in three bands containing 6 categories of targets and more than 5 000 images was established for our experimental verification. The results show that the recognition rate from Middle fusion reaches 84.5%. Compared with Early Fusion and Late Fusion

it increases by 8% and 12%. Moreover

the recognition rates of all three fusion methods have been improve significantly as compared to that of the single band recognitions at the same application scene.

关键词

Keywords

references

WAGNER J, FISCHER V, HERMAN M, et al .. Multispectral pedestrian detection using deep fusion convolutional neural networks[C]. 24 th European Symposium on Artificial Neural Networks , Computational Intelligence and Machine Learning ( ESANN ), 2016:509-514.

NGIAM J, KHOSLA A, KIM M, et al .. Multimodal deep learning[C]. Proceedings of the 28 th international conference on machine learning ( ICML -11), 2011:689-696.

SRIVASTAVA N, SALAKHUTDINOV R R. Multimodal learning with deep boltzmann machines[C]. Proceedings of the 25 th International Conference on Neural Information Processing Systems , NIPS , 2012:2222-2230.

KARPATHY A, TODERICI G, SHETTY S, et al .. Large-scale video classification with convolutional neural networks[C]. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition , 2014:1725-1732.

WANG LW, LI Y, LAZEBNIK S. Learning deep structure-preserving image-text embeddings[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2016:5005-5013.

SOCHER R, HUVAL B, BATH B, et al .. Convolutional-recursive deep learning for 3d object classification[C]. Proceedings of the 25th International Conference on Neural Information Processing Systems , 2012:656-664.

SIMONYAN K, ZISSERMAN A. Two-stream convolutional networks for action recognition in videos[C]. Proceedings of the 27 th International Conference on Neural Information Processing Systems , MIT Press , 2014:568-576.

GUNDOGDU E, SOLMAZ B, YVCESOY V, et al .. MARVEL:A large-scale image dataset for maritime vessels[C]. Asian Conference on Computer Vision , Springer , 2016:165-180.

BOUSETOUANE F, MORRIS B. Fast CNN surveillance pipeline for fine-grained vessel classification and detection in maritime scenarios[C]. 201613 th IEEE International Conference on Advanced Video and Signal Based Surveillance ( AVSS ), 2016:242-248.

REN S Q, HE K M, GIRSHICK R, et al .. Faster R-CNN:Towards real-time object detection with region proposal networks[C]. AIPS Proceedings of the 28 th International Conference on Neural Information Processing Systems , 2015:91-99.

ZHANG M M, CHOI J, DANⅡLIAIS K, et al .. Vais:A dataset for recognizing maritime imagery in the visible and infrared spectrums[C]. IEEE Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops , 2015:10-16.

周飞燕, 金林鹏, 董军.卷积神经网络研究综述[J].计算机学报, 2017, 40(6):1229-1251.

ZHOU F Y, JIN L P, DONG J. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40(6):1229-1251.(in Chinese)

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 60(6):84-90.

NAIR V, HINTON G E. Rectified linear units improve restricted boltzmann machines[C] Proceedings of the 27 th International Conference on Machine Learning ( ICML -10), Omnipress, 2010:807-814.

ZHANG Y, WU J X, CAI J F. Compact representation for image classification:To choose or to compress?[C] Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2014:907-914.

YE P, KUMAR J, DOERMANN D. Beyond human opinion scores:blind image quality assessment based on synthetic scores[C] IEEE Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2014:4241-4248.

XUE W F, ZHANG L, MOU X Q, et al.. Gradient magnitude similarity deviation:a highly efficient perceptual image quality index[J]. IEEE Transactions on Image Processing, 2014, 23(2):684-695.

SHEIKH H R, BOVIK A C, DE VECIANA G. An information fidelity criterion for image quality assessment using natural scene statistics[J]. IEEE Transactions on image Processing, 2005, 14(12):2117-2128.

ZHANG L, ZHANG L, MOU X, et al.. FSIM:a feature similarity index for image quality assessment[J]. IEEE transactions on Image Processing, 2011, 20(8):2378-2386.

WANG Z, BOVIK A C, SHEIKH H R, et al.. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.

Views

461

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A method for dense occlusion target recognition of service robots based on improved YOLOv7

Saliency maps for point cloud recognition models

Super-resolution reconstruction of micro-scanning images

Path planning strategy of amphibious spherical robot

SAR ATR based on disentangled representation learning generative adversarial networks and support vector machine

Related Author

CHEN Renxiang

QIU Tianran

YANG Lixia

YU Tenwei

JIA Fei

CHEN Cai

LIANG Ao

ZHANG Hao

Related Institution

Chongqing Intelligent Robot Research Institute， Chongqing 4000714

School of Business Administration， Chongqing University of Science and Technology

Chongqing Engineering Laboratory of Traffic Engineering Application Robot， Chongqing Jiaotong University

University of Chinese Academy of Sciences

Institutes for Robotics and Intelligent Manufacturing， Chinese Academy of Sciences

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰