Classification of Bird and Drone Targets Based on Motion Characteristics and Random Forest Model Using Surveillance Radar Data

被引:18
作者
Liu, Jia [1 ]
Xu, Qun Yu [2 ]
Chen, Wei Shi [3 ]
机构
[1] Beihang Univ, Res Inst Frontier Sci, Beijing 100191, Peoples R China
[2] China Acad Civil Aviat Sci & Technol, Res Inst Civil Aviat Law Regulat & Standardizat, Beijing 100028, Peoples R China
[3] China Acad Civil Aviat Sci & Technol, Airport Res Inst, Beijing 100028, Peoples R China
关键词
Radar tracking; Drones; Birds; Target tracking; Radar; Oscillators; Radar cross-sections; Target detection; radar tracking; target classification; feature extraction; machine learning; SMALL UAVS; INSECTS;
D O I
10.1109/ACCESS.2021.3130231
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Accurate detection and tracking of birds and drones are of great significance in various low altitude airspace surveillance scenarios. Radar is currently the most proper long range surveillance technology for this problem but also challenged by various difficulties on effective distinguishing between birds and drones. This paper explores the inherent flight mechanic and behavior mode of birds and drones. A target classification method is proposed by extracting target motion characteristics from radar tracks. The random forest model is selected for target classification in the new feature space. The proposed method is verified by real bird surveillance radar systems deployed in airport region. Classification results on birds, quadcopter drones and dynamic precipitations indicate that the proposed method could provide good classification accuracy. The Gini importance descriptors in random forest model provide extra reference on motion characteristic evaluation and mining. High sample flexibility and efficiency make the classification system capable of handling complicated low altitude target surveillance and classification problems. Limitations of the existing method and potential optimization strategy are also discussed as future works.
引用
收藏
页码:160135 / 160144
页数:10
相关论文
共 31 条
[11]   Evaluation of an avian radar system in a midwestern landscape [J].
Gerringer, Michael B. ;
Lima, Steven L. ;
DeVault, Travis L. .
WILDLIFE SOCIETY BULLETIN, 2016, 40 (01) :150-159
[12]  
Jahangir M, 2017, INT RADAR SYMP PROC
[13]   Detection and Identification of Low-Slow-Small Rotor Unmanned Aerial Vehicle Using Micro-Doppler Information [J].
Ji, Guangyu ;
Song, Chen ;
Huo, Hongtao .
IEEE ACCESS, 2021, 9 :99995-100008
[14]  
Jian M, 2017, IEEE RAD CONF, P854, DOI 10.1109/RADAR.2017.7944322
[15]   A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data [J].
Menze, Bjoern H. ;
Kelm, B. Michael ;
Masuch, Ralf ;
Himmelreich, Uwe ;
Bachert, Peter ;
Petrich, Wolfgang ;
Hamprecht, Fred A. .
BMC BIOINFORMATICS, 2009, 10
[16]  
Mohajerin N, 2014, IEEE RAD CONF, P674, DOI 10.1109/RADAR.2014.6875676
[17]  
Molchanov P, 2013, EUROP RADAR CONF, P172
[18]   Classification of small UAVs and birds by micro-Doppler signatures [J].
Molchanov, Pavlo ;
Harmanny, Ronny I. A. ;
de Wit, Jaco J. M. ;
Egiazarian, Karen ;
Astola, Jaakko .
INTERNATIONAL JOURNAL OF MICROWAVE AND WIRELESS TECHNOLOGIES, 2014, 6 (3-4) :435-444
[19]  
Moses A, 2011, IEEE INTL CONF CONTR, P933, DOI 10.1109/CCA.2011.6044363
[20]   Review of radar classification and RCS characterisation techniques for small UAVs or drones [J].
Patel, Jarez S. ;
Fioranelli, Francesco ;
Anderson, David .
IET RADAR SONAR AND NAVIGATION, 2018, 12 (09) :911-919