复杂环境下多传感器目标识别的数据融合方法

doi:10.19665/j.issn1001-2400.2020.04.005

摘要/Abstract

摘要：

针对复杂战场环境下目标信息不确定性造成目标识别困难和误判,导致目标识别结果准确率低的问题, 提出了一种基于离散因子多传感器目标识别的数据融合方法。通过多时段、多区域获取的多个传感器输出的数据,给出目标特性相应的传感器的离散因子;依据离散因子给出多传感器目标识别的当前权重,建立多传感器目标识别的相对一致性和相对加权一致性等函数;结合多传感器目标识别的当前权重以及相关的一致性函数,构建了多传感器目标识别的数据融合支持度计算模型。试验结果表明:在复杂环境下,与提前给定传感器权重目标识别的数据融合方法比较,基于离散因子多传感器目标识别的数据融合方法的目标识别结果更加准确,符合实际。说明这种方法更加可靠,并具有一定的抗干扰能力。

关键词: 多传感器, 离散因子, 当前权重, 一致性, 数据融合

Abstract:

In the complex battlefield environment, the uncertainty of target information causes the target recognition difficulty and misjudgment, which brings about the problem of a low accuracy of target recognition results. This paper proposes a data fusion method for multi-sensor target recognition based on the discrete factor, which can give rise to the output data of the multi-sensor at the multi-period and multi-regions detection, and bring about the discrete factor of obtaining target characteristic corresponding sensors. It can provide the current weight of multi-sensor target recognition according to the discrete factor, establish the relative consistency and the relative weighted consistency function of multi-sensor target recognition, combine the current weight of multi-sensor target recognition and the related consistency function, and construct the data fusion result support calculation model of multi-sensor target recognition. Experimental results show that when the environment is complex, the data fusion method for multi-sensor target recognition based on the discrete factor has more accurate target recognition results, which conforms to the reality in comparison with the data fusion method for target recognition with a given sensor weight in advance. It is shown that the method proposed in this paper is more reliable and has a certain anti-interference ability.

Key words: multi-sensor, discrete factor, current weight, consistency, data fusion

中图分类号:

TP305

卢莉萍,张晓倩. 复杂环境下多传感器目标识别的数据融合方法[J]. 西安电子科技大学学报, 2020, 47(4): 31-38.

LU Liping,ZHANG Xiaoqian. Datafusion method of multi-sensor target recognition in complex environment[J]. Journal of Xidian University, 2020, 47(4): 31-38.

图/表 4

表1

表2

表3

表4

参考文献 14

[1]	AKKARAT B, PONGSATHORN C, SANTANA B, et al. Simple Estimation of Late-time Response for Radar Target Identification[J]. Radio Science, 2017,52(6):743-756. doi: 10.1002/rds.v52.6
[2]	LEE S J, JEONG S J, YANG, E J, et al. Target Identification Using Bistatic High-resolution Range Profiles[J]. IET Radar, Sonar and Navigation, 2017,11(3):498-504. doi: 10.1049/iet-rsn.2016.0316
[3]	FABIAN R, MOHAMMADREZA S, JONATHAN B, et al. Ghost Target Identification by Analysis of the Doppler Distribution in Automotive Scenarios[C]// Proceedings of the 2017 International Radar Symposium. Washington: IEEE Computer Society, 2017: 8008128.
[4]	JIANG L, YAN L P, XIA Y Q, et al. Asynchronous Multirate Multisensor Data Fusion over Unreliable Measurements with Correlated Noise[J]. IEEE Transactions on Aerospace and Electronic Systems, 2017,53(5):2427-2437. doi: 10.1109/TAES.2017.2697598
[5]	YAN J K, LIU H W, PU W Q, et al. Benefit Analysis of Data Fusion for Target Tracking in Multiple Radar System[J]. IEEE Sensors Journal, 2016,16(16):6359-6366. doi: 10.1109/JSEN.2016.2581824
[6]	XIONG J, LI F M, LIU J. Fusion of Different Height Pyroelectric Infrared Sensors for Person Identification[J]. IEEE Sensors Journal, 2016,16(2):436-446. doi: 10.1109/JSEN.2015.2454000
[7]	苏伟, 李维民, 赵永. BP和D-S 结合的多传感器协同目标识别推理机制[J]. 空军工程大学学报(自然科学版), 2014,15(32):29-32.
	SU Wei, LI Weimin, ZHAO Yong. A Study of Reasoning Mechanism on Multiple Sensors Cooperation with Target Identification Based on BP Neural Network and D-S Evidence Theory[J]. Journal of Air Force Engineering University: Natural Science Edition, 2014,15(32):29-32.
[8]	冯立杰, 樊瑶. 基于D-S 证据理论的多传感器多特征目标识别[J]. 科技导报, 2014,32(15):32-36. doi: 10.3981/j.issn.1000-7857.2014.15.003
	FENG Lijie, FAN Yao. Target Identification Using Multiple Sensors Based on D-S Evidence Theory Characteristics[J]. Science & Technology Review, 2014,32(15):32-36. doi: 10.3981/j.issn.1000-7857.2014.15.003
[9]	张雅媛, 孙力帆, 郑国强. 基于改进Jousselme证据距离的多传感器决策融合方法[J]. 仪表技术与传感器, 2019, (7):82-87.
	ZHANG Yayuan, SUN Lifan, ZHENG Guoqiang. Approach to Multi Sensor Decision Fusion Based on Improved Jousselme Evidence Distance[J]. Instrument Technique and Sensor, 2019, (7):82-87.
[10]	HAO H J, WANG M L, TANG Y W, et al. Research on Data Fusion of Multi-sensors Based on Fuzzy Preference Relations[J]. Neural Computing and Applications, 2019,31(1):337-346.
[11]	常昕, 陈晓冬, 张佳琛, 等. 基于激光雷达和相机信息融合的目标检测及跟踪[J]. 光电工程, 2019,46(7):180420.
	CHANG Xin, CHEN Xiaodong, ZHANG Jiachen, et al. An Object Detection and Tracking Algorithm Based on LiDAR and Camera Information Fusion[J]. Opto-electronic Engineering, 2019,46(7):180420.
[12]	张梦骏, 郑益凯, 朱恺, 等. 基于自适应目标融合技术的指挥控制系统研究[J]. 无线电工程, 2019,49(8):683-688.
	ZHANGMengjun, ZHENG Yikai, ZHU Kai, et al. Research on Command and Control System Based on Self-adaptive Target Fusion Technology[J]. Radio Engineering, 2019,49(8):683-688.
[13]	田明明, 叶继华, 王仕民, 等. 一种复杂环境下多传感器数据融合方法[J]. 山东大学学报(工学版), 2019,49(3):32-38.
	TIAN Mingming, YE Jihua, WANG Shimin, et al. A Method of Multi-sensor Data Fusion under the Complicated Environment[J]. Journal of Shandong University: Engineering Science, 2019,49(3):32-38.
[14]	周尧, 姜礼平, 刘杨. 复杂环境下基于支持度的多传感器数据融合算法[J]. 火力与指挥控制, 2014,39(3):12-14,19.
	ZHOU Yao, JIANG Liping, LIU Yang. Data Fusion Algorithm Based on Support Degree Under Interferential Environment[J]. Fire Control and Command Control, 2014,39(3):12-14,19.

传感器编号	目标1		目标2		目标3
传感器编号	标准差	均值	标准差	均值	标准差	均值
1	50.0	246.0	68.0	372.0	23.0	289.0	318.0
2	2.3	38.4	7.9	45.1	0.7	29.2	36.2
3	1.1	1.8	0.6	2.6	0.7	2.9	3.4
4	2.5	3.6	0.7	5.8	0.8	6.2	6.5

传感器编号	目标1	目标2	目标3
1	0.28	0.59	0.37
2	0.52	0.43	0.00
3	0.27	0.33	0.64
4	0.42	0.50	0.81

传感器编号	目标1		目标2		目标3		目标4		目标5		测量值
传感器编号	标准差	均值	标准差	均值	标准差	均值	标准差	均值	标准差	均值	测量值
1	64.0	281.0	45.0	409.0	26.0	395.0	37.0	213.0	123.0	146.0	372.0
2	1.9	37.87	8.4	45.34	3.5	29.18	8.1	25.56	10.7	16.52	35.9
3	0.7	3.8	0.9	4.2	1.2	2.3	1.1	4.5	0.4	3.9	3.2
4	2.1	3.56	0.6	5.83	0.2	6.18	2.6	2.1	3.7	1.1	6.3

传感器编号	目标1	目标2	目标3	目标4	目标5
1	0.28	0.58	0.55	0.00	0.08
2	0.48	0.43	0.04	0.36	0.09
3	0.57	0.44	0.62	0.40	0.12
4	0.34	0.60	0.70	0.19	0.29

[1]	李佳炜,江晶,吴卫华,郑玉军. 应用统计线性回归的系统误差最大似然配准[J]. 西安电子科技大学学报, 2021, 48(4): 73-82.
[2]	葛川;刘琚;元辉;肖依凡;李凤荣;. 一种深度图的时域下采样编码及重建方法[J]. 西安电子科技大学学报, 2016, 43(4): 160-165+171.
[3]	雍霄驹;方洋旺;高翔;杨鹏飞. 自适应变长滑窗曲线拟合时间配准算法[J]. J4, 2014, 41(3): 209-213.
[4]	权义宁;姜振;黄晓冬;李伟峰. 一种新的数据融合航迹关联算法[J]. J4, 2012, 39(1): 67-74.
[5]	吴泽民;蒋叶金;任姝婕. 拓扑序列航迹相关的高效修正算法[J]. J4, 2011, 38(2): 180-186.
[6]	郭辉;姬红兵;武斌. 采用拟蒙特卡罗法的被动多传感器目标跟踪[J]. J4, 2010, 37(6): 1042-1047.
[7]	霍冠英;李庆武;石丹. 一种邻域一致性的NSCT域多传感器图像融合算法[J]. J4, 2010, 37(4): 770-776.
[8]	陈金广;李洁;高新波. 基于最小化测量误差的被动定位算法[J]. J4, 2010, 37(3): 447-453.
[9]	侯建强;牛中奇. 终端天线性能一致性检测系统研究[J]. J4, 2009, 36(4): 675-679.
[10]	毛永毅1;李明远2;张宝军1. 一种减小NLOS影响的TDOA／AOA数据融合定位算法 [J]. J4, 2008, 35(5): 942-945.
[11]	高军;曹祥玉;刘涛. 机载通信天线辐射特性分析 [J]. J4, 2008, 35(4): 754-758.
[12]	尚荣华;马文萍;焦李成;张伟. 用于求解多目标优化问题的克隆选择算法 [J]. J4, 2007, 34(5): 716-721.
[13]	王楠;梁昌洪;张玉;陈铭. NURBS-UTD方法的爬行波射线寻迹算法 [J]. J4, 2007, 34(4): 600-604.
[14]	王萌;陈晓洁;梁昌洪. UTD算法中平板二阶场的求解 [J]. J4, 2007, 34(3): 433-437.
[15]	苗春雨;史美林. Internet环境下的多数据库协作管理模型 [J]. J4, 2006, 33(6): 1000-1004.