Advanced Search
中文
Volume 43 Issue 10
Oct.  2021
Turn off MathJax
Article Contents
Abstract
References
ZHONG Rui, YANG Li, DU Yongcheng. The Influence of Deep Transfer Learning Pre-training on Infrared Wake Image Recognition[J]. Infrared Technology , 2021, 43(10): 979-986.
Citation: ZHONG Rui, YANG Li, DU Yongcheng. The Influence of Deep Transfer Learning Pre-training on Infrared Wake Image Recognition[J]. Infrared Technology , 2021, 43(10): 979-986.
shu

The Influence of Deep Transfer Learning Pre-training on Infrared Wake Image Recognition

  • School of Power Engineering, Naval University of Engineering, Wuhan 430033, China

More Information
  • Received Date: March 07, 2020
  • Revised Date: April 26, 2020
    Graphical Abstract
    • Abstract
  • With lower underwater vehicle noise levels, the infrared imaging characteristics of underwater vehicle wake have become one of the main detectable sources. Using the infrared characteristics of underwater vehicle wakes to detect underwater vehicle traces has gradually developed into a popular detection method. Because of the low efficiency and inaccuracy of artificial wake characteristics identification, the adopted artificial intelligence deep learning method can be greatly improved. In this study, the infrared feature recognition of underwater vehicle wake is the primary focus. A sample set of mixed classes was made by image classification. The training effect of different pre-training networks was compared using migration learning. The influence of the internal parameters of the pre-training networks on the training effect of the wake was discussed. Finally, in the small sample set of 45 two kinds of wake, the recognition accuracy of the network after pre-training increased by 21.43%, the false detection rate decreased by 2.14%, and the positioning accuracy of the image with infrared characteristics was 18.18% higher than that of the visible image. This pre-training test has a certain application potential for future research on wake detection combined with convolution neural network recognition.
    • FullText(HTML)
    • References (13)
  • [1]
    王雨农. 基于视觉注意机制的神经网络模型研究及应用[D]. 合肥: 中国科学技术大学, 2017.

    WANG Yunong. Research on Visual Attention Based Neural Network Model and its Application[D]. Hefei: University of Science and Technology of China, 2017.
    [2]
    Rumelhart D, Mcclelland J. Learning internal representations by error propagation[M]//Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Massachusetts: MIT Press, 1986: 318-362.
    [3]
    尹勰, 闫磊. 基于深度卷积神经网络的图像目标检测[J]. 工业控制计算机, 2017, 30(4): 96-97. https://www.cnki.com.cn/Article/CJFDTOTAL-GYKJ201704040.htm

    YIN Xie, YAN Lei. Image target detection based on deep convolutional neural network [J]. Industrial Control Computer, 2017, 30(4): 96-97. https://www.cnki.com.cn/Article/CJFDTOTAL-GYKJ201704040.htm
    [4]
    Razavian A S, Azizpour H, Sullivan J, et al. CNN features off-the-shelf: an astounding baseline for recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014: 512-519.
    [5]
    Zeiler M D, Fergus R. Visualizing and Understanding Convolutional Networks[M]//Computer Vision-ECCV, Springer International Publishing, 2014.
    [6]
    胡炎, 单子力, 高峰. 基于Faster-RCNN和多分辨率SAR的海上舰船目标检测[J]. 无线电工程, 2018, 48(2): 96-100. https://www.cnki.com.cn/Article/CJFDTOTAL-WXDG201802005.htm

    HU Yan, SHAN Zili, GAO Feng. Ship target detection based on faster-RCNN and multi-resolution SAR[J]. Radio Engineering, 2018, 48(2): 96-100. https://www.cnki.com.cn/Article/CJFDTOTAL-WXDG201802005.htm
    [7]
    李新. 基于红外热像技术连铸板坯裂纹预报方法研究[D]. 唐山: 华北理工大学, 2015.

    LI Xin. Research on Crack Prediction Method of Continuous Casting Slab Based on Infrared Thermography[D]. Tangshan : North China University of Technology, 2015.
    [8]
    张健, 杨立, 袁江涛. 水下航行器热尾流试验研究[J]. 实验流体力学, 2008, 22(3): 9-15. https://www.cnki.com.cn/Article/CJFDTOTAL-LTLC200803002.htm

    ZHANG Jian, YANG Li, YUAN Jiangtao. Experimental study on thermal wake of underwater vehicles[J]. Experimental Fluid Mechanics, 2008, 22(3): 9-15. https://www.cnki.com.cn/Article/CJFDTOTAL-LTLC200803002.htm
    [9]
    贺林. 水喷淋消声器设计与实验研究[D]. 哈尔滨: 哈尔滨工程大学, 2006.

    HE Lin. Design and Experimental Study of Water Spray Muffler[D]. Harbin : Harbin Engineering University, 2006.
    [10]
    伍伟明. 基于Faster R-CNN的目标检测算法的研究[D]. 广州: 华南理工大学, 2018.

    WU Weiming. Research on Target Detection Algorithm Based on Faster R-CNN[D]. Guangzhou : South China University of Technology, 2018.
    [11]
    刘万军, 梁雪剑, 曲海成. 自适应增强卷积神经网络图像识别[J]. 中国图象图形学报, 2019, 22(12): 1723-1736. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201712008.htm

    LIU Wanjun, LIANG Xuejian, QU Haicheng. Adaptive enhanced convolutional neural network image recognition[J]. Chinese Journal of Image Graphics, 2019, 22(12): 1723-1736. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201712008.htm
    [12]
    Lecun Y, Boser B, Denker J, et al. Back propagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551. DOI: 10.1162/neco.1989.1.4.541
    [13]
    王红霞, 周家奇, 辜承昊, 等. 用于图像分类的卷积神经网络中激活函数的设计[J]. 浙江大学学报: 工学版, 2019, 53(7): 1363-1373. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC201907016.htm

    WANG Hongxia, ZHOU Jiaqi, GU Chenghao, et al. Design of activation functions in convolutional neural networks for image classification[J]. Journal of Zhejiang University: Engineering Edition, 2019, 53(7): 1363-1373. https://www.cnki.com.cn/Article/CJFDTOTAL-ZDZC201907016.htm
    • Related Articles

Catalog

    Get Citation
    PDF
    XML
    Article views PDF downloads Cited by()
    Related

    Copyright © 《Infrared Technology》Editorial Office滇ICP备12000354号-3

    Supported by: Beijing Renhe Information Technology Co., Ltd.  Baidu Analytics

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return