基于空间多特征综合推理的航迹航路关联
收稿日期: 2015-05-26
修回日期: 2015-11-23
网络出版日期: 2015-12-17
基金资助
国家自然科学基金(611350001,61374023)
Track-to-airline association based on multi-feature reasoning
Received date: 2015-05-26
Revised date: 2015-11-23
Online published: 2015-12-17
Supported by
National Natural Science Foundation of China (611350001, 61374023)
针对航迹分类问题,研究了基于空间多特征的综合推理在航路判读中的应用。首先根据空管系统对航路以及飞机飞行的要求,对航迹航路相关问题进行建模。然后根据已知的传感器系统输出的目标特性(位置,航向)与已知的多个航路信息分别进行相关度计算,构造基本信任函数,通过对其融合,得到目标单特征识别结果。其中,通过合理地引入复合类,实现了对目标类别的广义信任分类。建立了多特征折扣融合算法,对多特征基本信任函数进行折扣后再融合,得到目标多特征识别结果。仿真结果以及空管实际数据测试表明:该算法不仅可以实现航迹分类,同时可以有效地降低分类的错误率。
梁彦 , 王晓华 , 李立 , 张金凤 , 史志远 , 杨峰 . 基于空间多特征综合推理的航迹航路关联[J]. 航空学报, 2016 , 37(5) : 1595 -1602 . DOI: 10.7527/S1000-6893.2015.0318
Considering track classification problem, the application of complex reasoning in the multi-feature track decision is studied. Firstly, according to the requirements of air traffic control system for airway and flight, an association model of track-to-airline is developed. Secondly, similarities between target features(position, direction) and information of known tracks are computed, basic belief assignments are constructed and then the target single feature classification results are obtained by fusion. The introduction of meta-class brings out the generalized credit classification for targets class. A multi-feature discount method is developed, giving the discount on features' basic belief assignments before fusion to get the target multi-feature classification results. The simulations and the test on real data of air traffic control system show that the method not only make the track classification, but also decrease the fault rate of classification.
[1] 王增福, 潘泉, 陈丽平,等. 基于航路-航迹关联的天波超视距雷达航迹分类[J]. 系统工程与电子技术, 2012, 34(10):2018-2022 WANG Z F, PAN Q, CHEN L P, et al. Tracks classification based on airway-track association for over-the-horizon radar[J]. Systems Engineering and Electronics, 2012, 34(10):2018-2022(in Chinese).
[2] HAYKIN S, STEHWIEN W, DENG C, et al. Classification of radar clutter in an air traffic control environment[J]. Proceedings of the IEEE, 1991, 79(6):742-772.
[3] NOYES S P. Track classification in naval defense radar using fuzzy logic[C]//Proceedings of Colloquium on Target Tracking and Data Fusion. Pisscataway, NJ:IEEE Press, 1998:1-6.
[4] GHADAKI H. Feature formation and classification of radar targets[D]. Toronto:University of Toronto, 2006:14-15.
[5] 程铭, 陈宇寒. 飞行计划和雷达航迹关联目标识别算法[J]. 四川兵工学报, 2010, 31(5), 107-109. CHENG M, CHEN Y H. Target recognition algorithm of association with flight plan and radar dynamic track[J]. Journal of Sichuan Ordnance, 2010, 31(5):107-109(in Chinese).
[6] OXENHAM M. Automatic air target to airline association[C]//Proceedings of the 3rd International Conference on Information. Piscataway, NJ:IEEE Press, 2000:4-19.
[7] MAFTIN H. Multi-sensor track classification in ro-torcraft pilot's associate data fusion[C]//Proceedings of 53th Annual Forum-American Helicopter Society. Virginia:American Helicopter Society, 1997:271-280.
[8] LEUNG H, WU J. Bayesian and dempster-shafer target identification for radar surveillace[J]. Aerospace and Electronic Systems, 2000, 36(2):432-447.
[9] MERCIER D, LEFÈVRE É, JOLLY D. Object association with belief functions, an application with vehicles[J]. Information Sciences, 2011, 181(24):5485-5500
[10] WARTELLE N, DELMOTTE F, GAQUER D. Classification de scènes à nombre d'objets inconnu[C]//MAnifestation des Jeunes Chercheurs STIC, Lorient:Presse Universitaires Française (PUF), 2006:22-24.
[11] ZOGHBY N, CHERFAOUI V. Optimal object association from pairwise evidential mass functions[C]//Proceedings of the 16th International Conference on Information Fusion. Pisscataway, NJ:IEEE Press, 2013:774-780.
[12] HACHOUR S, DELMOTTE F, MERCIER D. Tracking and identification of multiple targets[C]//Proceedings of the 7th Workshop Interdisciplinaire sur la Sécurité Globale. Troyes, France:Agence Nationale de Recherche (ANR), 2013:13-18.
[13] HACHOUR S, DELMOTTE F, MERIER D, et al. Object tracking and credal classification with kinematic data in a multi-target context[J]. Information Fusion, 2014, 20:174-188.
[14] DENOEUX T, MASSON M H. EVCLUS:Evidential clus-tering of proximity data[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B:Cybernetics, 2004, 34(1):95-109.
[15] MASSON M H, DENOEUX T. ECM:An evidential version of the fuzzy c-means algorithm[J]. Pattern Recognition. 2008, 41(4):1384-1397.
[16] BEZDEK J C. Pattern recognition with fuzzy objective function algorithms[M]. New York:Plenum Press, 1981:203-239.
[17] DAVE R N. Clustering of relational data containing noise and outliers[C]//Proceedings of the 1998 IEEE International Conference on Fuzzy Systems.Piscataway, NJ:IEEE Press, 1998:1411-1416.
[18] ALTINCAY H.Ensembling evidential k-nearest neighbor classifiers through multi-modal perturbation[J]. Applied Soft Computing, 2007, 7(3):1072-1083.
[19] LIU Z, PAN Q, DEZERT J. Classification of uncertain and imprecise data based on evidence theory[J]. Neuro Computing, 2014, 133:459-470.
[20] LIU Z, PAN Q, DEZERT J. A new belief-based K-nearest neighbor classification method[J]. Pattern Recognition, 2013, 46(3):834-844.
/
| 〈 |
|
〉 |
CJA