基于多源信息融合的巡飞弹对地目标识别与毁伤评估

doi:10.16182/j.issn1004731x.joss.22-1130

系统仿真学报 ›› 2024, Vol. 36 ›› Issue (2): 511-521.doi: 10.16182/j.issn1004731x.joss.22-1130

基于多源信息融合的巡飞弹对地目标识别与毁伤评估

徐艺博¹(), 于清华¹(), 王炎娟², 郭策¹, 冯世如³, 卢惠民¹

^1.国防科技大学智能科学学院，湖南长沙 410073
^2.北京航天飞行控制中心，北京 100094
^3.深圳天富创科技有限公司，广东深圳 518000

收稿日期:2022-09-24 修回日期:2023-01-10 出版日期:2024-02-15 发布日期:2024-02-04
通讯作者: 于清华 E-mail:yiboxybxf@163.com;yuqinghua@nudt.edu.cn
第一作者简介:徐艺博(1997-)，男，博士生，研究方向为深度学习与人工智能可解释性。E-mail：yiboxybxf@163.com

Ground Target Recognition and Damage Assessment of Patrol Missiles Based on Multi-source Information Fusion

Xu Yibo¹(), Yu Qinghua¹(), Wang Yanjuan², Guo Ce¹, Feng Shiru³, Lu Huimin¹

^1.College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
^2.Beijing Aerospace Control Center, Beijing 100094, China
^3.Shenzhen TFC Technology co. , Ltd, Shenzhen 518000, China

Received:2022-09-24 Revised:2023-01-10 Online:2024-02-15 Published:2024-02-04
Contact: Yu Qinghua E-mail:yiboxybxf@163.com;yuqinghua@nudt.edu.cn

摘要/Abstract

摘要：

面向利用多枚巡飞弹对地面高防御移动目标进行打击的任务场景，提出一种基于多源信息融合的巡飞弹对地移动目标识别与毁伤评估方法。基于IoU判定实现红外图像与可见光图像的多源信息融合；提出一种基于YOLO-VGGNet的两阶段紧耦合的巡飞弹对地移动目标毁伤评估方法，利用卷积神经网络深度语义信息提取的优势，引入红外毁伤信息，实现对地面移动目标的在线实时毁伤评估。实验结果表明：基于多源信息融合的目标识别算法有效提升了巡飞弹对地面移动目标识别的有效性；基于YOLO-VGGNet的在线实时毁伤等级评估方法较传统基于图像变化检测与基于两阶段卷积神经网络的方法评估准确率分别提升19%和10.25%。

关键词: 多源信息融合, 毁伤评估, 卷积神经网络, YOLO-VGGNet, 在线实时评估

Abstract:

For the multiple patrol missiles to attack the high defense capacity targets, a mobile ground target detection and damage assessment method based on multi-source information fusion is proposed. The multi-source information fusion of infrared images and RGB images is carried out by using IoU determination. A novel two-stage tightly coupled damage assessment method based on YOLO-VGGNet of patrol missiles to mobile ground targets is proposed. This method can fully use the advantage of deep semantic information extraction of CNNs and introduce the infrared damaging information simultaneously to achieve the online and real-time damage assessment of mobile ground targets. The results of simulation experiments show that the target recognition algorithm based on multi-source information fusion significantly improves the detection of mobile ground targets of patrol missiles. Compared with the traditional image-change-detection-based method and the two-CNN learning-based method, the real-time and online damage level assessment method based on YOLO-VGGNet improves the accuracy by 19% and 10.3%, respectively.

Key words: multi-source information fusion, damage assessment, convolutional neural networks, YOLO-VGGNet, online real-time assessment

中图分类号:

TP242.6

徐艺博,于清华,王炎娟等 . 基于多源信息融合的巡飞弹对地目标识别与毁伤评估[J]. 系统仿真学报, 2024, 36(2): 511-521.

Xu Yibo,Yu Qinghua,Wang Yanjuan,et al . Ground Target Recognition and Damage Assessment of Patrol Missiles Based on Multi-source Information Fusion[J]. Journal of System Simulation, 2024, 36(2): 511-521.

图/表 11

图1

图2

图3

图4

图5

图6

表1

图7

图8

表2

图9

参考文献 23

1	吴森堂. 导弹自主编队协同制导控制技术[M]. 北京: 国防工业出版社, 2015.
	Wu Sentang. Cooperative Guidance & Control of Missiles Autonomous Formation[M]. Beijing: National Defense Industry Press, 2015.
2	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 Ang, Dong Zhiming, Ye Hongbing, et al. Loitering Munition Penetration Control Decision Based on Deep Reinforcement Learning[J]. Acta Armamentarii, 2021, 42(5): 1101-1110.
3	程进, 罗世彬, 宋闯, 等. 弹群协同与自主决策[M]. 北京: 科学出版社, 2020.
	Cheng Jin, Luo Shibin, Song Chuang, et al. Missile-group Coordination and Autonomous Decision-making[M]. Beijing: Science Press, 2020.
4	曲婉嘉, 徐忠林, 张柏林, 等. 基于贝叶斯网络云模型的目标毁伤评估方法[J]. 兵工学报, 2016, 37(11): 2075-2084.
	Qu Wanjia, Xu Zhonglin, Zhang Bolin, et al. Battle Damage Assessment Method Based on BN-cloud Model[J]. Acta Armamentarii, 2016, 37(11): 2075-2084.
5	Mujica L E, Rodellar J, Fernández A, et al. Q-statistic and T2-statistic PCA-based Measures for Damage Assessment in Structures[J]. Structural Health Monitoring, 2011, 10(5): 539-553.
6	杨青青, 樊桂花. 基于改进模糊综合评判法的建筑物毁伤效果评估[J]. 系统工程与电子技术, 2018, 40(9): 2026-2031.
	Yang Qingqing, Fan Guihua. Battle Damage Assessment of Buildings Based on Improved Fuzzy Comprehensive Evaluation Method[J]. Systems Engineering and Electronics, 2018, 40(9): 2026-2031.
7	田福平, 汶博, 郑鹏鹏. 基于贝叶斯网络的作战目标评估[J]. 火力与指挥控制, 2017, 42(2): 79-82.
	Tian Fuping, Wen Bo, Zheng Pengpeng. Warfare Targets Assessment Based on Bayesian Network[J]. Fire Control & Command Control, 2017, 42(2): 79-82.
8	马晓明, 丁平, 晏卫东. 基于贝叶斯网络的舰船目标毁伤评估[J]. 兵工自动化, 2016, 35(6): 72-75.
	Ma Xiaoming, Ding Ping, Yan Weidong. Warship-damage Assessment Based on Bayesian Networks[J]. Ordnance Industry Automation, 2016, 35(6): 72-75.
9	杨凯达. 加入毁伤时间流的目标毁伤效果评估方法[J]. 舰船电子工程, 2022, 42(4): 129-134, 170.
	Yang Kaida. Method of Battle Damage Assessment with Damage Time Stream[J]. Ship Electronic Engineering, 2022, 42(4): 129-134, 170.
10	Kuncheva L I, Faithfull W J. PCA Feature Extraction for Change Detection in Multidimensional Unlabeled Data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(1): 69-80.
11	Li Qiang, Gong Lixia, Zhang Jingfa. A Correlation Change Detection Method Integrating PCA and Multi- texture Features of SAR Image for Building Damage Detection[J]. European Journal of Remote Sensing, 2019, 52(1): 435-447.
12	Wu Chen, Chen Hong ruiuan, Du Bo, et al. Unsupervised Change Detection in Multitemporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network[J]. IEEE Transactions on Cybernetics, 2022, 52(11): 12084-12098.
13	Yousif Osama, Ban Yifang. Improving Urban Change Detection from Multitemporal SAR Images Using PCA-NLM[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(4): 2032-2041.
14	涂震飚, 林涛. 基于下视图像的打击效果评估系统研究[J]. 战术导弹技术, 2012(5): 6-9.
	Tu Zhenbiao, Lin Tao. Research on Battle Damage Assessment System Based on Downward-looking Scene Image[J]. Tactical Missile Technology, 2012(5): 6-9.
15	Anastasopoulos I, Anastasopoulos P C, Agalianos A, et al. Simple Method for Real-time Seismic Damage Assessment of Bridges[J]. Soil Dynamics and Earthquake Engineering, 2015, 78: 201-212.
16	He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep Residual Learning for Image Recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2016: 770-778.
17	余丽山, 李彦彬, 赵永龙, 等. 基于BP神经网络的飞机抗毁伤能力评估[J]. 弹箭与制导学报, 2018, 38(1): 23-26.
	Yu Lishan, Li Yanbin, Zhao Yonglong, et al. Assessment of Aircraft Anti Damage Capability Based on BP Neural Network[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2018, 38(1): 23-26.
18	张宗腾, 张琳, 谢春燕, 等. 基于改进GA-BP神经网络的目标毁伤效果评估[J]. 火力与指挥控制, 2021, 46(11): 43-48.
	Zhang Zongteng, Zhang Lin, Xie Chunyan, et al. Battle Damage Effect Assessment Based on Improved GA-BP Neural Network[J]. Fire Control & Command Control, 2021, 46(11): 43-48.
19	Shen Yu, Zhu Sijie, Yang Taojianan, et al. BDANet: Multiscale Convolutional Neural Network with Cross-directional Attention for Building Damage Assessment from Satellite Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-14.
20	Sarath P, Soorya M, Shaik Abdul Rahman A, et al. Assessing Car Damage Using Mask R-CNN[J]. International Journal of Engineering and Advanced Technology, 2020, 9(3): 2287-2290.
21	Alqahtani H, Ray A. Neural Network-based Automated Assessment of Fatigue Damage in Mechanical Structures[J]. Machines, 2020, 8(4): 85.
22	Xu Jinglin, Zeng Feng, Liu Wen, et al. Damage Detection and Level Classification of Roof Damage after Typhoon Faxai Based on Aerial Photos and Deep Learning[J]. Applied Sciences, 2022, 12(10): 4912.
23	Tang Shimin, Chen Zhiqiang. Understanding Natural Disaster Scenes from Mobile Images Using Deep Learning[J]. Applied Sciences, 2021, 11(9): 3952.

等级	YOLO-VGGNet	PCA-k-means	Mask-RCNN	真值
准确率	84.50	65.50	74.25
正常	86	62	82	100
轻度	79	55	63	100
中度	81	59	68	100
重度	92	86	84	100

[1]	陈静, 张昭冲, 王琳凯, 安脉, 王伟. 基于卷积长短时记忆网络的短时公交客流量预测[J]. 系统仿真学报, 2024, 36(2): 476-486.
[2]	张凯, 卢海鹏, 韩莹, 张龄允, 丁昱杰. 融合变分模态分解的时空卷积短时车速预测[J]. 系统仿真学报, 2023, 35(8): 1651-1660.
[3]	蔡兴泉, 李治均, 奚梦瑶, 孙海燕. 基于神经网络的手绘服饰图纹上色及风格迁移[J]. 系统仿真学报, 2023, 35(3): 604-615.
[4]	杨丰玮, 陈鹏, 郗凯, 蒲华林, 刘雪垠. 融合空间信息的运动想象脑电在线分类方法[J]. 系统仿真学报, 2023, 35(2): 254-267.
[5]	张立峰, 王会忍. 基于卷积神经网络及有限元仿真的电容层析成像图像重建[J]. 系统仿真学报, 2022, 34(4): 712-718.
[6]	敖邦乾, 杨莎, 令狐金卿, 叶振环. 基于级联神经网络疲劳驾驶检测系统设计[J]. 系统仿真学报, 2022, 34(2): 323-333.
[7]	王亚茹, 杨凯, 翟永杰, 郭聪彬, 赵文清, 苏杰. 基于人工图像数据扩充的输电线路绝缘子识别[J]. 系统仿真学报, 2022, 34(11): 2337-2347.
[8]	徐佳乐, 张海东, 赵东海, 倪晚成. 基于卷积神经网络的陆战兵棋战术机动策略学习[J]. 系统仿真学报, 2022, 34(10): 2181-2193.
[9]	郭业才, 王庆伟. 基于截断迁移与并行残差网络的调制识别算法[J]. 系统仿真学报, 2022, 34(09): 2009-2018.
[10]	赵瑛, 陆耀, 张健, 梁启弟, 龙炜. 基于深度神经网络的多视角人体动作识别[J]. 系统仿真学报, 2021, 33(5): 1019-1030.
[11]	仝卫国, 庞雪纯, 朱赓宏. 基于卷积神经网络的气液两相流流型识别方法[J]. 系统仿真学报, 2021, 33(4): 883-891.
[12]	马榕, 陈秋瑞, 张晗, 梅铮, 王锐, 魏伟. 基于单目深度估计的低功耗视觉里程计[J]. 系统仿真学报, 2021, 33(12): 3001-3011.
[13]	黄欣, 方钰, 顾梦丹. 基于卷积神经网络的X线胸片疾病分类研究[J]. 系统仿真学报, 2020, 32(6): 1188-1194.
[14]	樊名鲁, 王艳, 纪志成. 基于特征生成的轴承不均衡数据故障诊断[J]. 系统仿真学报, 2020, 32(12): 2438-2448.
[15]	王红军, 黎邹邹, 邹湘军. 基于Adaboost与CNN的木材表面缺陷检测[J]. 系统仿真学报, 2019, 31(8): 1636-1645.

基于多源信息融合的巡飞弹对地目标识别与毁伤评估

Ground Target Recognition and Damage Assessment of Patrol Missiles Based on Multi-source Information Fusion

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 23

相关文章 15

编辑推荐

Metrics

本文评价

弹序	可见光识别目标	红外识别目标	融合后目标	真值
1	38	33	32	30
1	38	12	32	30
2	35	32	30	25
2	35	15	30	25
3	40	35	29	26
3	40	12	29	26
4	35	35	28	28
4	35	9	28	28
5	33	35	27	32
5	33	9	27	32

弹序	可见光识别目标	红外识别目标	融合后目标	真值
1	38	33	32	30
1	38	12	32	30
2	35	32	30	25
2	35	15	30	25
3	40	35	29	26
3	40	12	29	26
4	35	35	28	28
4	35	9	28	28
5	33	35	27	32
5	33	9	27	32

弹序	可见光识别目标	红外识别目标	融合后目标	真值
1	38	33	32	30
1	38	12	32	30
2	35	32	30	25
2	35	15	30	25
3	40	35	29	26
3	40	12	29	26
4	35	35	28	28
4	35	9	28	28
5	33	35	27	32
5	33	9	27	32