Half space object classification via incident angle based fusion of radar and infrared sensors

doi:10.23919/JSEE.2022.000100

Journal of Systems Engineering and Electronics ›› 2022, Vol. 33 ›› Issue (5): 1025-1031.doi: 10.23919/JSEE.2022.000100

• ELECTRONICS TECHNOLOGY • Next Articles

Half space object classification via incident angle based fusion of radar and infrared sensors

Zhenyu HE^1,²(), Xiaodong ZHUGE¹, Junxiang WANG³, Shihao YU¹(), Yongjun XIE^1,^4,*(), Yuxiong ZHAO⁵

¹ School of Electronic Information and Engineering, Beihang University, Beijing 100191, China
² Beijing Institute of Electronic System Engineering, Beijing 100854, China
³ Beijing Institute of Astronautical Systems Engineering, Beijing 100076, China
⁴ Shenzhen Institute of Beihang University, Shenzhen 518038, China
⁵ School of Software, Beihang University, Beijing 100191, China

Received:2020-08-13 Online:2022-10-27 Published:2022-10-27
Contact: Yongjun XIE E-mail:hzy1015@buaa.edu.cn;shyu_ee@163.com;yjxie@buaa.edu.cn
About author:|HE Zhenyu was born in 1994. He received his B.S. degree from the School of Electronic Information and Engineering from Beihang University, Beijing, China. He is currently studying in Beihang University for his M.S. degree. His current interests include radar target recognition in half space and artificial intelligence. E-mail: hzy1015@buaa.edu.cn||ZHUGE Xiaodong was born in 1982. He received his M.S. and Ph.D. degrees from the Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, the Netherlands, in 2006 and 2010, respectively. From 2011 to 2014, he was a Research Scientist at FEI Electron Optics, Eindhoven, the Netherlands. He was with the National Research Institute for Mathematics and Computer Science, the Netherlands as a Researcher from 2014 to 2017. Since 2017, he has been an associate professor with Beihang University, Beijing, China. His research interests include microwave and millimeter wave sensing and systems, with a strong focus on near-field imaging and measurements. E-mail: zhuge@buaa.edu.cn||WANG Junxiang was born in 1987. He received his M.S. degree in School of Automation at Northwestern Polytechnical University. He is now working at Beijing Institute of Astronautical Systems Engineering. His research interests are controlled modeling and radar. E-mail: wangjunxiang87928@126.com||YU Shihao was born in 1993. He received his B.S. degree in School of Electronic Information and Engineering from Beihang University, Beijing, China. He is currently studying in Beihang University for his master's degree. His current interests include radar target recognition in half space and artificial intelligence. E-mail: shyu_ee@163.com||XIE Yongjun was born in 1968. He received his B.S., M.S., and Ph.D. degrees from Xidian University, Xi’an, China, in 1990, 1993, and 1996, respectively, in electronic engineering. From 1998 to 1999, he was with the University of Texas at Dallas, Dallas, TX, USA, as a post-doctoral research associate. From 1999 to 2001, he was with Duke University, Durham, NC, USA, as a post-doctoral research associate. In 2004, he was supported by the Program for the New Century Excellent Talents at the Ministry of Education, China. He is currently a professor in Beihang University. His research interests include electromagnetic theory, microwave technology, and mobile telecommunication. E-mail: yjxie@buaa.edu.cn||ZHAO Yuxiong was born in 1998. He received his B.E. degree in software engineering from Beihang University. Currently, he is working toward his M.S. degree in data science and machine learning from National University of Singapore. His research interests include machine learning, computer vision and data mining. E-mail: zhaoyuxiong@buaa.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (61571022; 61971022).

Abstract

Abstract:

In this paper, we introduce an incident angle based fusion method for radar and infrared sensors to improve the recognition rate of complex targets under half space scenarios, e.g., vehicles on the ground in this paper. For radar sensors, convolutional operation is introduced into the autoencoder, a “winner-take-all (WTA)” convolutional autoencoder (CAE) is used to improve the recognition rate of the radar high resolution range pro?le (HRRP). Moreover, different from the free space, the HRRP in half space is more complex. In order to get closer to the real situation, the half space HRRP is simulated as the dataset. The recognition rate has a growth more than 7% compared with the traditional CAE or denoised sparse autoencoder (DSAE). For infrared sensor, a convolutional neural network (CNN) is used for infrared image recognition. Finally, we combine the two results with the Dempster-Shafer (D-S) evidence theory, and the discounting operation is introduced in the fusion to improve the recognition rate. The recognition rate after fusion has a growth more than 7% compared with a single sensor. After the discounting operation, the accuracy rate has been improved by 1.5%, which validates the effectiveness of the proposed method.

Key words: convolutional autoencoder (CAE), half space, high-resolution range profile (HRRP), incident angle based fusion, target recognition

Zhenyu HE, Xiaodong ZHUGE, Junxiang WANG, Shihao YU, Yongjun XIE, Yuxiong ZHAO. Half space object classification via incident angle based fusion of radar and infrared sensors[J]. Journal of Systems Engineering and Electronics, 2022, 33(5): 1025-1031.

Figures/Tables 11

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Table 1

Table 2

Fig 6

Table 3

Fig 7

Fig 8

References 17

1	GAO F, HUANG T, WANG J, et al A novel multi-input bidirectional LSTM and HMM based approach for target recognition from multi-domain radar range profiles. Electronics, 2019, 8, 535.
2	LI X F, XIE Y J, WANG P, et al High-frequency method for scattering from electrically large conductive targets in half-space. IEEE Antennas and Wireless Propagation Letters, 2007, 6, 259- 262. doi: 10.1109/LAWP.2007.897509
3	RIUS J M, FERRANDO M GRECO: graphical electromagnetic computing for RCS prediction in real time. IEEE Antennas & Propagation Magazine, 1993, 35 (2): 7- 17.
4	YAN H Q, ZHANG Z H, XIONG G, et al Radar HRRP recognition based on sparse denoising autoencoder and multi-layer perceptron deep model. Proc of the Fourth International Conference on Ubiquitous Positioning, Indoor Navigation and Location Based Services, 2016, 283- 288.
5	ZHANG Y X, WANG X D, YAO X, et al HRRP recognition for polarization radar based on Bagging-SVM dynamic ensemble. Systems Engineering and Electronics, 2012, 34 (7): 1366- 1371.
6	YUAN J, LIU W, ZHANG G Application of dictionary learning algorithm in HRRP based on statistical modeling. Systems Engineering and Electronics, 2018, 40 (4): 762- 767.
7	TAI G X, WANG Y H, LI Y, et al Radar HRRP target recognition based on stacked denosing sparse autoencoder. The Journal of Engineering, 2019, 2019, (21): 7945- 7949.
8	YU S H, XIE Y J Application of a convolutional autoencoder to half space radar HRRP recognition. Proc of the International Conference on Wavelet Analysis and Pattern Recognition, 2018, 48- 53.
9	JIAO Z B, WANG Y F. A D-S evidence theory-based relay protection system hidden failures detection method in smart grid. Proc. of the IEEE Power & Energy Society General Meeting, 2017. DOI: 10.1109/PESGM.2017.8274673.
10	SHEN X H, LIU K Y, LIU Z, et al A wind turbine fault diagnosis method using adaptive weighting algorithm and D-S evidence theory. Proc. of the IEEE 2nd Advanced Information Management, Communicates, Electronic and Automation Control Conference, 2018, 626- 630.
11	DONG G G, KUANG G Y Target recognition via information aggregation through Dempster –Shafer ’s evidence theory. IEEE Geoscience and Remote Sensing Letters, 2015, 12 (6): 1247- 1251.
12	MASCI J, MEIER U, CIRESAN D, et al Stacked convolutional auto-encoders for hierarchical feature extraction. Artificial Neural Networks and Machine Learning, 2011, 52- 59.
13	MAKHZANI A, FREY B J Winner-take-all autoencoders. Proc. of the 28th International Conference on Neural Information Processing Systems, 2015, 2, 2791- 2799.
14	GU J X, WANG Z H, KUEN J, et al Recent advances in convolutional neural networks. Pattern Recognition, 2018, 77 (C): 354- 377.
15	MOATE C P, HAYWARD S D, ELLIS J S, et al Vehicle detection in infrared imagery using neural networks with synthetic training data. Proc. of the International Conference Image Analysis and Recognition, 2018, 453- 461.
16	MERCIER D, QUOST B, DENŒUX T Refined modeling of sensor reliability in the belief function framework using contextual discounting. Information Fusion, 2008, 9 (2): 246- 258. doi: 10.1016/j.inffus.2006.08.001
17	WANG Z Y, WU Z H, BAO H J, et al. Synthesis of infrared ground target and its background. https://doi.org/10.1117/12.441571.

Target	Length	Width	Height
T-80	9.720	3.560	2.740
UAZ-469	4.025	1.785	2.050
URAL-4320	7.366	2.500	3.005

Training set	Test set	Recognition rate/%
Free space	Free space	82.24
Free space	Half space	39.60
Half space	Half space	75.64
Half space	Free space	69.34

Target	DSAE	CAE	WTA-CAE	WTA-SCAE
T-80	68.40	69.51	71.57	74.41
UAZ-469	67.40	64.97	74.29	76.14
URAL-4320	68.72	68.49	74.40	75.03
Average	68.17	67.66	73.42	75.29

[1]	Pengcheng GUO, Zheng LIU, Jingjing WANG. Radar group target recognition based on HRRPs and weighted mean shift clustering [J]. Journal of Systems Engineering and Electronics, 2020, 31(6): 1152-1159.
[2]	Wenbo LIU, Jiawen YUAN, Gong ZHANG, Qian SHEN. HRRP target recognition based on kernel joint discriminant analysis [J]. Journal of Systems Engineering and Electronics, 2019, 30(4): 703-708.
[3]	Long Li, Zheng Liu, and Tao Li. Radar high resolution range profile recognition via multi-SV method [J]. Systems Engineering and Electronics, 2017, 28(5): 879-889.
[4]	Xinhai Wang, Gong Zhang, Fangqing Wen, and De Ben. Schemes for synthesizing high-resolution range profile with extended OFDM-MIMO [J]. Systems Engineering and Electronics, 2017, 28(3): 424-434.
[5]	Rui Zhang and Min Zhang. SAR target recognition based on active contour without edges [J]. Systems Engineering and Electronics, 2017, 28(2): 276-281.
[6]	Jingqing Li, Sisan He, Cunqian Feng, and Yizhe Wang. Method for compensating translational motion of rotationally symmetric target based on local symmetry cancellation [J]. Systems Engineering and Electronics, 2017, 28(1): 36-.
[7]	Fei Gao, Jingyuan Mei, Jinping Sun, Jun Wang, Erfu Yang, and Amir Hussain. Target detection and recognition in SAR imagery based on KFDA [J]. Journal of Systems Engineering and Electronics, 2015, 26(4): 720-.
[8]	Ning Tang, Xunzhang Gao, and Xiang Li. ISAR target recognition based on non-negative sparse coding [J]. Journal of Systems Engineering and Electronics, 2012, 23(6): 849-857.
[9]	Qingyu Hou?,Feng Chen,Hongwei Liu,and Zheng Bao. New statistical model for radar HRRP target recognition [J]. Journal of Systems Engineering and Electronics, 2010, 21(2): 204-210.
[10]	Yongpin Chen, Zaiping Nie, and Jun Hu. Fast and accurate analysis of electromagnetic scattering from targets situated in dielectric half space [J]. Journal of Systems Engineering and Electronics, 2010, 21(1): 37-40.
[11]	Liu Donghong, Zhang Yongshun, Chen Zhijie' & Cheng Junbin. UWB radar target recognition based on time-domain bispectrum [J]. Journal of Systems Engineering and Electronics, 2006, 17(2): 274-278.
[12]	Oxen Tianlu & Que Peiwen. Target recognition based on modified combination rule * [J]. Journal of Systems Engineering and Electronics, 2006, 17(2): 279-283.

Half space object classification via incident angle based fusion of radar and infrared sensors

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 11

References 17

Related Articles 12

Recommended Articles

Metrics

Comments