基于熵权-可信度因子的舰船细粒度分类方法

doi:10.12305/j.issn.1001-506X.2025.11.06

摘要/Abstract

摘要：

针对多载荷协同完成舰船目标细粒度分类任务，考虑载荷访问周期不一致问题，提出一种基于熵权-可信度模型的舰船目标细粒度分类方法。在历史信息的支持下，依据信息熵权评估多个电子/成像探测载荷的不确定性，进而建立基于加权合成法则的可信度模型。该算法结合区域历史态势，解决探测窗口交错造成的推理中断问题，实现跨模态信息决策级融合。6类舰船目标细粒度分类任务中，所提方法的准确率达到91%，具有较好准确性和鲁棒性。

关键词: 信息融合, 细粒度分类, 电子探测, 成像探测

Abstract:

For the fine-grained ship target classification in multi-payload collaborative detection task, considering the various revisit time of payloads, a method based on entropy weight and credibility model for fine grained classification of ship targets is proposed. With the support of historical information, the uncertainty of multiple electronic/imaging detection payloads are evaluated through entropy weight.Then, a certainty factor model is established based on weighted synthesis rules. The proposed method solves the interruption of reasoning issues caused by intersection of detection windows via combininng regional historical situation, achieving decision-level cross-modal information fusion. In the fine-grained classification task involving six categories of ship targets, the accuracy of the proposed method achieves 91%, demonstrating satisfactory accuracy and robustness.

Key words: information fusion, fine-grained classification, eletronic detection, imaging detection

中图分类号:

TP 391

张小舟, 贾振俊, 郭晓云. 基于熵权-可信度因子的舰船细粒度分类方法[J]. 系统工程与电子技术, 2025, 47(11): 3568-3573.

Xiaozhou ZHANG, Zhenjun JIA, Xiaoyun GUO. Method for fine-grained ship classification based on entropy weight and certainty factor[J]. Systems Engineering and Electronics, 2025, 47(11): 3568-3573.

图/表 6

图1

图2

表1

图3

表2

表3

参考文献 28

1	高保慧, 胡海, 钟志通, 等. 天基引导对海打击杀伤链构建方法[J]. 指挥与控制学报, 2024, 10 (2): 184- 196. doi: 10.3969/j.issn.2096-0204.2024.02.0184
	GAO B H, HU H, ZHONG Z T, et al. Kill chain construction in surface strikes under space-based guidance[J]. Journal of Command and Control, 2024, 10 (2): 184- 196. doi: 10.3969/j.issn.2096-0204.2024.02.0184
2	马力, 师鹏, 陈宇, 等. 天基信息支援体系离散事件仿真与效能评估[J]. 系统工程与电子技术, 2024, 46 (3): 906- 913.
	MA L, SHI P, CHEN Y, et al. Discrete event stimulation and effectiveness evaluation of space-basedinformation support system[J]. Systems Engineering and Electronics, 2024, 46 (3): 906- 913.
3	陈宇, 师鹏, 马力, 等. 天基信息支援体系建模与效能评估方法[J]. 系统工程与电子技术, 2024, 46 (10): 3407- 3415.
	CHEN Y, SHI P, MA L, et al. Modeling and effectiveness evaluation method of space-based information support system[J]. Systems Engineering and Electronics, 2024, 46 (10): 3407- 3415.
4	赵其昌, 吴一全, 苑玉彬. 光学遥感图像舰船目标检测与识别方法研究进展[J]. 航空学报, 2024, 45 (8): 51- 84.
	ZHAO Q C, WU Y Q, YUAN Y B. Progress of ship detection and recognition methods in optical remote sensing images[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45 (8): 51- 84.
5	SONG Y X, SONG F, JIN L, et al. An attention cut classification network for fine-grained ship classificationin remote sensing images[J]. Remote Sensing Letters, 2022, 13 (4): 418- 427. doi: 10.1080/2150704X.2022.2035464
6	XIONG W, XIONG Z Y, CUI Y Q. An explainable attention network for fine-grained ship classification using remote-sensing images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 151770- 151784.
7	CHEN J Q, CHEN K Y, CHEN H, et al. Contrastive learning for fine-grained ship classification in remotesensing images[J]. IEEE Trans. on Geoscience and Remote Sensing, 2022, 60, 4707916.
8	CHEN Y T, ZHANG Z L, CHEN Z K, et al. Fine-grained classification of optical remote sensing ship image based on deep convolution neural network[J]. Remote Sensing, 2022, 14 (18): 4566. doi: 10.3390/rs14184566
9	刘松涛, 赵帅, 汪慧阳. 雷达辐射源识别技术研究新进展[J]. 中国电子科学研究院学报, 2022, 17 (6): 523- 533. doi: 10.3969/j.issn.1673-5692.2022.06.002
	LIU S T, ZHAO S, WANG H Y. New development on the technology of radar emitter Identification[J]. Journal of China Academy of Electronics and Information Technology, 2022, 17 (6): 523- 533. doi: 10.3969/j.issn.1673-5692.2022.06.002
10	刘宇轩, 柳征, 刘海军, 等. 基于辐射源关联分析的舰船平台识别方法[J]. 电子信息对抗技术, 2009, 24 (3): 24- 28. doi: 10.3969/j.issn.1674-2230.2009.03.006
	LIU Y X, LIU Z, LIU H J, et al. A ship platform identification method based on association analysis of emitters[J]. Electronic Information Warfare Technology, 2009, 24 (3): 24- 28. doi: 10.3969/j.issn.1674-2230.2009.03.006
11	陈旗, 谢金辉. 基于两级证据合成的海上辐射源目标识别方法[J]. 电子信息对抗技术, 2017, 32 (1): 13- 17，26. doi: 10.3969/j.issn.1674-2230.2017.01.003
	CHEN Q, XIE J H. A method of emitter identification based on two-stage evidence combination[J]. Electronic Information Warfare Technology, 2017, 32 (1): 13- 17，26. doi: 10.3969/j.issn.1674-2230.2017.01.003
12	吴俊, 程咏梅, 曲圣杰, 等. 基于三级信息融合结构的多平台多雷达目标识别算法[J]. 西北工业大学学报, 2012, 30 (3): 367- 372. doi: 10.3969/j.issn.1000-2758.2012.03.011
	WU J, CHENG Y M, QU S J, et al. An effective multi-platform multi-radar target identification algorithm based on three level fusion hierarchical structure[J]. Journal of Northwestern Polytechnical University, 2012, 30 (3): 367- 372. doi: 10.3969/j.issn.1000-2758.2012.03.011
13	王壮, 樊昀, 王成, 等. 基于星载电子侦察与成像侦察的数据融合技术[J]. 电子学报, 2003, 31 (12): 2127- 2130.
	WANG Z, FAN Y, WANG C, et al. Data fusion based on spaceborne electronic and imaging reconnaissance information[J]. Acta Electronica Snica, 2003, 31 (12): 2127- 2130.
14	高敬, 黄高明, 甘泉, 等. 基于证据理论的雷达与通信侦察目标识别算法[J]. 航天电子对抗, 2012, 28 (2): 62- 64. doi: 10.3969/j.issn.1673-2421.2012.02.019
	GAO J, HUANG G M, GAN Q, et al. Target identification algorithm of radar and communication reconnaissance based on evidence theory[J]. Aerospace Electronic Warfare, 2012, 28 (2): 62- 64. doi: 10.3969/j.issn.1673-2421.2012.02.019
15	王万良. 人工智能导论[M]. 5版. 北京: 高等教育出版社, 2020.
	WANG W L. Introduction to artificial intelligence. [M] 5th ed. Beijing: Highher Education Press, 2020.
16	SHORTLIFFE E H, BUCHNAN B G. A model of inexact reasoning in medicine[J]. Mathematical Biosciences, 1987, 23 (3/4): 351- 379.
17	YU V L, BUCHNAN B G, SHORTLIFFE E H, et al. Evaluating the performance of a computer-based consultant[J]. Computer Programs in Biomedicine, 1979, 9 (1): 95- 102. doi: 10.1016/0010-468X(79)90022-9
18	李晓菲, 缪建明, 沈丙振. 基于改进方差最大化的主客观组合赋权方法[J]. 火力与指挥控制, 2022, 47 (3): 124- 128. doi: 10.3969/j.issn.1002-0640.2022.03.021
	LI X F, MIAO J M, SHEN B Z. Research on subjective and objective combination weighting method based on improved variance maximization[J]. Fire Control & Command Control, 2022, 47 (3): 124- 128. doi: 10.3969/j.issn.1002-0640.2022.03.021
19	田宝玉. 信息论基础[M]. 2版. 北京: 人民邮电出版社, 2020.
	TIAN B Y. Elemennts of information theory [M]. 2nd ed. Beijing: Post and Telecom Press, 2020.
20	张甜, 阎红灿. 基于熵权法的多属性决策算法优化及应用[J]. 华北理工大学学报(自然科学版), 2022, 44(1): 82−88.
	ZHANG T, YAN H C. Optimization and application of multi-attribute decision algorithm based on entropy weight method[J]. Journal of North China University of Science and Technology (Natural Science Edition), 2022, 44(1): 82−88.
21	YANG G F, REN M, HAO X M. Multi-criteria decision-making problem based on the novel probabilistic hesitant fuzzy entropy and Todim method[J]. Alexandria Engineering Journal, 2023, 68, 437- 451. doi: 10.1016/j.aej.2023.01.014
22	岳喜超, 王勇, 陈乐, 等. 结合主成分分析与熵权的关键变量筛选算法[J]. 中国电子科学研究院学报, 2023, 18 (7): 671- 679. doi: 10.3969/j.issn.1673-5692.2023.07.011
	YUE X C, WANG Y, CHEN L, et al. Key variable screening algorithm combing principal component and entropy weight[J]. Journal of CAEIT, 2023, 18 (7): 671- 679. doi: 10.3969/j.issn.1673-5692.2023.07.011
23	钱丽丽, 刘思峰, 谢乃明. 基于熵权和区间灰数信息的灰色聚类模型[J]. 系统工程与电子技术, 2016, 38 (2): 352- 356. doi: 10.3969/j.issn.1001-506X.2016.02.17
	QIAN L L, LIU S F, XIE N M. Grey clustering model based on entropy-weight and grey numbers[J]. Systems Engineering and Electronics, 2016, 38 (2): 352- 356. doi: 10.3969/j.issn.1001-506X.2016.02.17
24	李占山, 杨云凯, 张家晨. 基于熵权法的过滤式特征选择算法[J]. 东北大学学报（自然科学版）, 2022, 43 (7): 921- 929.
	LI Z S, YANG Y K, ZHANG J C. Filtering feature selection algorithm based on entropy weight method[J]. Journal of Northeastern University （Natural Science）, 2022, 43 (7): 921- 929.
25	李恒璐, 陈伯孝. 丁一, 等. 基于信息熵权的最近邻域数据关联算法[J]. 系统工程与电子技术, 2020, 42 (4): 806- 812. doi: 10.3969/j.issn.1001-506X.2020.04.10
	LI H L, CHEN B X, DING Y, et al. Nearest neighbor data association algorithm based on information entropy weight[J]. Systems Engineering and Electronics, 2020, 42 (4): 806- 812. doi: 10.3969/j.issn.1001-506X.2020.04.10
26	XU W H, CAI K, WANG D D. A novel information fusion method using improved entropy measure in multi-source incomplete interval-valued datasets[J]. International Journal of Approximate Reasoning, 2024, 164, 109081. doi: 10.1016/j.ijar.2023.109081
27	陈中起, 周中良, 于雷, 等. 基于改进信息熵的空地多目标共计优先权决策[J]. 系统工程与电子技术, 2011, 33 (2): 329- 333. doi: 10.3969/j.issn.1001-506X.2011.02.20
	CHEN Z Q, ZHOU Z L, YU L, et al. Priority decision of air-to-surface multi-target attack based on improved entropy[J]. Systems Engineering and Electronics, 2011, 33 (2): 329- 333. doi: 10.3969/j.issn.1001-506X.2011.02.20
28	任永梅, 杨杰, 郭志强, 等. 基于多尺度卷积神经网络的自适应熵加权决策融合船舶图像分类方法[J]. 电子与信息学报, 2021, 43 (5): 1424- 1431. doi: 10.11999/JEIT200102
	REN Y M, YANG J, GUO Z Q, et al. Self-adaptive entropy weighted decision fusion method for ship image classification based on multi-scale convolutional neural network[J]. Journal of Electronics & Information Technology, 2021, 43 (5): 1424- 1431. doi: 10.11999/JEIT200102

类别	$ P1 $	$ P2 $	$ P3 $	$ P4 $	$ P5 $	$ P6 $
长宽比	8.00	7.50	6.00	7.00	6.50	7.00

指标	电侦卫星单一信源	成像卫星单一信源	本文方法	证据合成理论	Bayes理论
准确率	0.580 0	0.760 0	0.910 0	0.750 0	0.830 0
精确率	0.228 9	0.659 7	0.839 2	0.519 9	0.621 7
召回率	0.201 1	0.620 9	0.834 3	0.490 3	0.596 9
F1值	0.214 1	0.639 7	0.836 8	0.504 7	0.608 4

指标	VAR	MAD	RMS	IQR
准确率	0.001 4	0.029 4	0.851 3	0.050 0
精确率	0.005 5	0.060 0	0.740 9	0.104 4
召回率	0.006 0	0.062 6	0.728 0	0.106 8
F1值	0.005 7	0.061 3	0.734 4	0.107 0

[1]	李响, 曾顶, 殷君君, 国贤玉, 杨健. 基于梯度融合的极化SAR图像引导滤波[J]. 系统工程与电子技术, 2025, 47(9): 2890-2904.
[2]	韩子硕, 范喜全, 付强, 马传焱, 张冬冬. 面向无人机视角的多源信息融合目标检测[J]. 系统工程与电子技术, 2025, 47(1): 52-61.
[3]	任文娟, 杨战鹏, 许光銮, 付琨. 海上动目标身份置信度融合计算模型[J]. 系统工程与电子技术, 2023, 45(4): 1082-1089.
[4]	张晔, 侯毅, 欧阳克威, 周石琳. 单变量序列数据分类方法综述[J]. 系统工程与电子技术, 2023, 45(2): 313-335.
[5]	杨璐宁, 刘正华, 温暖. 面向多元未知环境的基于深度高斯过程组合导航轨迹预测方法[J]. 系统工程与电子技术, 2023, 45(11): 3632-3639.
[6]	黄林, 龚立, 姜伟, 王康勃. 基于多源信息融合与HMM的剩余寿命预测[J]. 系统工程与电子技术, 2022, 44(5): 1747-1756.
[7]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.
[8]	张瑜, 吴凯, 郭杰, 葛志闪, 张宝超. 基于数据质量评估的自适应序贯航迹关联算法[J]. 系统工程与电子技术, 2022, 44(11): 3477-3485.
[9]	关欣, 于昊天, 衣晓. 证据独立性及其对目标识别的影响研究[J]. 系统工程与电子技术, 2022, 44(1): 192-198.
[10]	赵岩, 吴建峰, 高育鹏. 基于多智能体导航的高超飞行器信息融合方法[J]. 系统工程与电子技术, 2020, 42(2): 405-413.
[11]	李佳炜, 江晶, 刘重阳, 吴卫华. 多星载光学传感器系统误差极大似然配准算法[J]. 系统工程与电子技术, 2020, 42(1): 1-9.
[12]	邵松世, 刘海涛, 张志华. 融合多源先验信息的舰船备件可靠性评估[J]. 系统工程与电子技术, 2019, 41(12): 2905-2910.
[13]	杨乐昌, 郭艳玲. 基于贝叶斯混合概率分布融合的系统可靠性分析与预测方法[J]. 系统工程与电子技术, 2018, 40(7): 1660-1668.
[14]	常天庆, 王全东, 郝娜, 孙皓泽, 孔德鹏. 基于信息融合的目标管理与被动定位方法[J]. 系统工程与电子技术, 2017, 39(9): 1921-1935.
[15]	唐续, 吴骐, 李明晏, 黄大羽. 天波超视距雷达的多路径融合多目标跟踪算法[J]. 系统工程与电子技术, 2017, 39(7): 1493-1499.