基于深度学习的光电系统智能目标识别

doi:10.12382/bgxb.2022.A004

摘要/Abstract

摘要： 智能目标识别技术是光电系统多维立体侦察体系的重要支撑，是实现多角度、全方位目标定位、感知分析的基础。为满足复杂环境下光电系统中基于深度学习的目标识别需求，聚焦数据、算法和计算能力三大挑战，提出一种基于多源信息融合的智能化目标识别方法，对多个传感器融合得到的图像进行学习和训练，从而提高目标识别的能力。基于多维图像融合的目标识别技术，将多波段融合图像数据进行标注、训练学习，用来自动识别出图像中的多个目标。实验结果表明，所提算法能够实现对融合目标的精确识别与定位。

关键词: 光电系统, 智能目标识别, 深度学习, 多源数据, 图像融合, 视觉感知

Abstract: Intelligent target recognition technology is an important support of multi-dimensional and three-dimensional reconnaissance system of electro-optical system, which is the basis of multi-angle and omni-directional target positioning and perception analysis. Focusing on the three challenges of data，algorithm and computing power，an intelligent target recognition method based on multi-source information fusion is proposed to meet the needs of deep learning-based target recognition of electro-optical system in complex environment.The proposed method is to learn and train the images fused by multiple sensors so as to improve the ability to recognize targets.The target recognition technology based on multi-dimensional image fusion is used to label，train and learn the multi band fused image data，thus automatically identifying the multiple targets in the image. Experimental results show that the proposed method can be used to accurately identify and locate the fusion target.

Key words: electro-opticalsystem, intelligenttargetrecognition, deeplearning, multi-sourcedata, imagefusion, visualperception

中图分类号:

TP29

李良福，陈卫东，高强，许开銮，刘轩，何曦，钱钧. 基于深度学习的光电系统智能目标识别[J]. 兵工学报, 2022, 43(S1): 162-168.

LI Liangfu， CHEN Weidong， GAO Qiang， XU Kailuan， LIU Xuan， HE Xi， QIAN Jun. Deep Learning-based Intelligent Target Recognition Technology for Electro-optical System[J]. Acta Armamentarii, 2022, 43(S1): 162-168.

参考文献

［1］ LEE J S，PARK T H.Fast road detection by CNN-based camera-lidar fusion and spherical coordinate transformation［J］.IEEE Transactions on Intelligent Transportation Systems，2021，22(9):5802-5810.
［2］ CAVALIERE D，LOIA V，SAGGESE A，et al. Semantically enhanced UAVs to increase the aerial scene understanding［J］.IEEE Transactions on Systems，Man，and Cybernetics:Systems，2019，49(3): 555-567.
［3］王芳，王海晏，寇添，等.多维特征点空间的红外弱小目标检测方法［J］.应用光学，2021，41(6):1268-1276.
WANG F，WANG H Y，KOU T，et al.Multi-dimensional feature point space infrared dim target detection method［J］.Journal of Applied Optics，2021，41(6):1268-1276.(in Chinese)
［4］牛畅，尹奎英，黄银和.无人机对地目标自动检测与跟踪技术［J］.应用光学，2021，41(6):1153-1160.
NIU C，YIN K Y，HUANG Y H.Automatic target detecting and tracking technology based on UAV ground target images［J］.Journal of Applied Optics，2021，41(6): 1153-1160.(in Chinese)
［5］高文静，杨预立，邢强，等.基于目标运动的复眼式双目视觉测距法［J］.应用光学，2020，41(3):571-579.
GAO W J，YANG Y L，XING Q,et al Compound eye binocular vision ranging method based on target motion ［J］. Journal of Applied Optics，2020，41(3): 571-579.(in Chinese)
［6］杜鹏飞，李小勇，高雅丽.多模态视觉语言表征学习研究综述［J］.软件学报，2021，32(2):327-348.
DU P F，LI X Y，GAO Y L. Survey on multimodal visual language representation learning［J］.Journal of Software，2021，32(2):327-348.(in Chinese)
［7］ WANG Z C，DU L，ZHANG P， et al.Visual attention-based target detection and discrimination for high-resolution SAR images in complex scenes［J］.IEEE Transactions on Geoscience and Remote Sensing，2018，56(4):1855-1872.
［8］ CHEN L C，PAPANDREOU G，KOKKINOS I，et al. DeepLab:semantic image segmentation with deep convolutional nets， atrous convolution，and fully connected CRFs［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，40(4):834-848.
［9］ MADAWI K E，RASHED H.，SALLAB A E，et al. RGB and lidar
fusion based 3D semantic segmentation for autonomous driving［C］∥
Proceedings of IEEE Intelligent Transportation Systems Conference.Auckland，New Zealand:IEEE, 2019.
［10］ LIU J，GONG M G，QIN K，et al.A deep convolutional coupling network for change detection based on heterogeneous optical and radar images［J］.IEEE Transactions on Neural Networks and Learning Systems，2018，29(3):545-559.
［11］ MINAEIAN S，LIU J，SON Y J.Effective and efficient detection of moving targets from a UAV's camera［J］.IEEE Transactions on Intelligent Transportation Systems，2018，19(2):497-506.
［12］ AL-KAFF A, MARTN D, GARCA F，et al.Survey of computer vision algorithms and applications for unmanned aerial vehicles［J］. Expert Systems with Applications，2018，92:447-463.
［13］ XU D，DUAN Q，ZHENG J M, et al.Shading-based surface detail recovery under general unknown illumination［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，40(2):423-436.
［14］高昂，董志明，叶红兵，等.基于深度强化学习的巡飞弹突防控制决策［J］.兵工学报，2021，42(5):1101-1110.
GAO A，DONG Z M，YE H B, et al. Loitering munition penetration control decision based on deep reinforcement learning［J］.Acta Armamentarii，2021，42(5):1101-1110.(in Chinese)
［15］闫孟达，杨任农，左家亮，等.基于深度学习的空空导弹多类攻击区实时解算［J］.兵工学报，2020，41(12):2466-2477.
YAN M D，YANG R N，ZUO J L, et al.Real-time computing of air-to-air missile multiple capture zones based on deep learning［J］. Acta Armamentarii，2021，41(12):2466-2477.(in Chinese)

[1]	田大明, 苗圃. 融合模型求解与深度学习的可见光通信非线性均衡器[J]. 兵工学报, 2024, 45(2): 466-473.
[2]	张堃, 杜睿怡, 时昊天, 华帅. 基于Mogrifier-BiGRU的飞行器轨迹预测[J]. 兵工学报, 2024, 45(2): 373-384.
[3]	杨家铭, 潘悦, 王强, 曹怀刚, 高荪培. 水下弱目标跟踪的深度学习方法研究[J]. 兵工学报, 2024, 45(2): 385-394.
[4]	秦昊林, 许廷发, 李佳男. 基于超像素注意力和孪生结构的半监督高光谱显著性目标检测[J]. 兵工学报, 2023, 44(9): 2639-2649.
[5]	彭沛然, 任术波, 李佳男, 周鸿伟, 许廷发. 基于光照感知的多光谱融合行人检测方法[J]. 兵工学报, 2023, 44(9): 2622-2630.
[6]	周宇, 曹荣刚, 栗苹, 马啸. 一种用于外场试验图像的引信炸点检测方法[J]. 兵工学报, 2023, 44(8): 2453-2464.
[7]	张良安, 陈洋, 谢胜龙, 刘同鑫. 基于机器视觉与深度学习的飞机防护栅裂纹检测系统[J]. 兵工学报, 2023, 44(2): 507-516.
[8]	王洋, 冯永新, 宋碧雪, 田秉禾. DP-DRCnet卷积神经网络信号调制识别算法[J]. 兵工学报, 2023, 44(2): 545-555.
[9]	郑志伟, 管雪元, 傅健, 马训穷, 尹上. 基于卷积神经网络与长短期记忆神经网络的弹丸轨迹预测[J]. 兵工学报, 2023, 44(10): 2975-2983.
[10]	王强, 吴乐天, 李红, 王勇, 王欢, 杨万扣. 基于双支网络协作的红外弱小目标检测[J]. 兵工学报, 2023, 44(10): 3165-3176.
[11]	王亮，陈建华，李烨. 一种基于深度学习的无人艇海上目标识别技术[J]. 兵工学报, 2022, 43(S2): 13-19.
[12]	王晓琦，赵旸，张键，王硕. 基于深度学习的船体三维模型自动生成方法[J]. 兵工学报, 2022, 43(S2): 115-119.
[13]	张通彤, 姜湖海, 岳巍, 司晨, 袁满. 基于径向基函数神经网络的光电系统自适应控制[J]. 兵工学报, 2022, 43(3): 556-564.
[14]	李锦青，刘泽飞，满振龙. 基于生成对抗网络的密钥生成方法及其在微光图像加密中的应用[J]. 兵工学报, 2022, 43(2): 337-344.
[15]	唐伟，贾方秀，王晓鸣. 基于双边滤波的可见光与红外图像自适应融合[J]. 兵工学报, 2022, 43(11): 2836-2845.