HRRP target recognition based on kernel joint discriminant analysis

doi:10.21629/JSEE.2019.04.08

Journal of Systems Engineering and Electronics ›› 2019, Vol. 30 ›› Issue (4): 703-708.doi: 10.21629/JSEE.2019.04.08

收稿日期:2018-04-17 出版日期:2019-08-01 发布日期:2019-09-01

HRRP target recognition based on kernel joint discriminant analysis

Wenbo LIU^1,*(), Jiawen YUAN¹(), Gong ZHANG²(), Qian SHEN¹()

¹ College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
² College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China

Received:2018-04-17 Online:2019-08-01 Published:2019-09-01
Contact: Wenbo LIU E-mail:wenboliu@nuaa.edu.cn;yuanjiawen@nuaa.edu.cn;gzhang@nuaa.edu.cn;qianshen@nuaa.edu.cn
About author:LIU Wenbo was born in 1968. She received her Ph.D. degree from Nanjing University of Aeronautics and Astronautics in 2002. She is a professor in Nanjing University of Aeronautics and Astronautics. Her research interests are signal processing and pattern recognize. E-mail:wenboliu@nuaa.edu.cn|YUAN Jiawen was born in 1994. She is a Ph.D. candidate in Nanjing University of Aeronautics and Astronautics. Her research interests include radar signal processing and target recognition. E-mail:yuanjiawen@nuaa.edu.cn|ZHANG Gong was born in 1964. He received his Ph.D. degree from Nanjing University of Aeronautics and Astronautics in 2002. He is a professor in Nanjing University of Aeronautics and Astronautics. His research interests are SAR image processing, target detection and target recognition. E-mail:gzhang@nuaa.edu.cn|SHEN Qian was born in 1987. He is a Ph.D. candidate in Nanjing University of Aeronautics and Astronautics. His research interests are image encryption, compressive sensing and chaos theory. E-mail:qianshen@nuaa.edu.cn
Supported by:
the National Natural Science Foundation of China(61471191);the Aeronautical Science Foundation of China(20152052026);the Foundation of Graduate Innovation Center in NUAA(kfjj20170313);This work was supported by the National Natural Science Foundation of China (61471191), the Aeronautical Science Foundation of China (20152052026), and the Foundation of Graduate Innovation Center in NUAA (kfjj20170313)

摘要/Abstract

Abstract:

With the improvement of radar resolution, the dimension of the high resolution range profile (HRRP) has increased. In order to solve the small sample problem caused by the increase of HRRP dimension, an algorithm based on kernel joint discriminant analysis (KJDA) is proposed. Compared with the traditional feature extraction methods, KJDA possesses stronger discriminative ability in the kernel feature space. K-nearest neighbor (KNN) and kernel support vector machine (KSVM) are applied as feature classifiers to verify the classification effect. Experimental results on the measured aircraft datasets show that KJDA can reduce the dimensionality, and improve target recognition performance.

Key words: high resolution range profile (HRRP), target recognition, small sample problem, feature extraction, dimension reduction

. [J]. Journal of Systems Engineering and Electronics, 2019, 30(4): 703-708.

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.

图/表 6

参考文献 23

1	GAO F, MEI J Y, SUN J P, et al. Target detection and recognition in SAR imagery based on KFDA. Journal of Systems Engineering and Electronics, 2015, 26 (4): 720- 731.
2	BAI X, ZHOU F, BAO Z, et al. High-resolution range profiles. IEEE Trans. on Geoscience and Remote Sensing, 2014, 52 (5): 2369- 2381. doi: 10.1109/TGRS.2013.2260342
3	LIU H W, FENG B, CHEN B, et al. Radar high-resolution range profiles target recognition based on stable dictionary learning. IET Radar, Sonar and Navigation, 2016, 10 (1): 228- 237.
4	GUO Y, XIAO H T, KAN Y Z, et al. Learning using privileged information for HRRP-based radar target recognition. IET Signal Processing, 2018, 12 (2): 188- 197. doi: 10.1049/iet-spr.2016.0625
5	NATALIA A, JOSEPH A. Thresholding method for dimensionality reduction in recognition systems. IEEE Trans. on Information Theory, 2001, 47 (7): 2903- 2920. doi: 10.1109/18.959269
6	GARZON-GUERRERO J A, RUIZ D P, CARRION M C. Classification of geometrical targets using natural resonances and principal components analysis. IEEE Trans. on Antennas and Propagation, 2013, 61 (9): 4881- 4884. doi: 10.1109/TAP.2013.2266091
7	KARI T, GAO W. Power transformer fault diagnosis using FCM and improved PCA. The Journal of Engineering, 2017, 14, 2605- 2608.
8	FU J S, LIAO K, YANG W L. Radar HRRP target recognition using multi-KFD-based LDA algorithm. Progress in Electromagnetics Research C, 2012, 30, 15- 26. doi: 10.2528/PIERC11121804
9	BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs. Fisherfaces:recognition using class specific linear projection. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 711- 720. doi: 10.1109/34.598228
10	MIKA S, RATSCH G, WESTON J, et al. Fisher discriminant analysis with kernels. Proc. of the IEEE Neural Networks for Signal Processing IX, 1999, 41- 48.
11	HU W, HU H. Heterogeneous face recognition based on modality-independent kernel Fisher discriminant analysis joint sparse auto-encoder. Electronics Letters, 2016, 52 (21): 1753- 1755. doi: 10.1049/el.2016.2661
12	FENG G Y, XIAO H T, FU Q. Local sampling mean discriminant analysis with kernels. Electronics Letters, 2012, 48 (1): 22- 23. doi: 10.1049/el.2011.2969
13	JUWEI L, PLATANIOTIS K N, VENETSANOPOULOS A N. Face recognition using kernel direct discriminant analysis algorithms. IEEE Trans. on Neural Networks, 2003, 14 (1): 117- 126.
14	YOU D, HAMSICI O C, MARTINEZ A M. Kernel optimization in discriminant analysis. IEEE Trans. on Pattern Analysis&Machine Intelligence, 2010, 33 (3): 631- 638.
15	PAN M, DU L, WANG P H, et al. Noise-robust modification method for Gaussian-based models with application to radar HRRP recognition. IEEE Geoscience and Remote Sensing Letters, 2013, 10 (3): 662- 668.
16	BAI X, ZHOU F, BAO Z, et al. High-resolution radar imaging of space targets based on HRRP series. IEEE Trans. on Geoscience and Remote Sensing, 2014, 52 (5): 2369- 2381. doi: 10.1109/TGRS.2013.2260342
17	GUO Y, XIAO H, FU Q. Least square support vector data description for HRRP-based radar target recognition. Applied Intelligence, 2017, 46 (2): 365- 372. doi: 10.1007/s10489-016-0836-5
18	PAN M, JIANG J, KONG Q, et al. Radar HRRP target recognition based on t-SNE segmentation and discriminant deep belief network. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (9): 1609- 1613. doi: 10.1109/LGRS.2017.2726098
19	ZHANG H, DING D, FAN Z, et al. Adaptive neighborhoodpreserving discriminant projection method for HRRP-based radar target recognition. IEEE Antennas and Wireless Propagation Letters, 2015, 14, 650- 653. doi: 10.1109/LAWP.2014.2376591
20	CHAI J, LIU H, BAO Z. Generalized re-weighting local sampling mean discriminant analysis. Pattern Recognition, 2010, 43 (10): 3422- 3432. doi: 10.1016/j.patcog.2010.04.017
21	CHAI J, LIU H, BAO Z. Combinatorial discriminant analysis:supervised feature extraction that integrates global and local criteria. Electronics Letters, 2009, 45 (18): 934- 935. doi: 10.1049/el.2009.1423
22	ALTMAN N S. An introduction to kernel and nearest-neighbor nonparametric regression. American Statistician, 1992, 46 (3): 175- 185.
23	GAO L P, ZHANG X L, GAO G P, et al. Fusion image based radar signal feature extraction and modulation recognition. IEEE Access, 2019, 7, 13135- 13148. doi: 10.1109/ACCESS.2019.2892526

Aircraft	Length	Width	Height
An-26	23.80	29.20	9.83
Cessna Citation S/II	14.40	15.90	4.57
Yark-42	36.38	34.88	9.83

Algorithm	Recognition via training percentage
Algorithm	20% $\delta =0.01$	40%$\delta=1$	60%$\delta =100$	80%$\delta =1~000$
LDA	70.38	75.73	78.83	80.06
LSMDA	68.99	75.47	83.50	85.12
CDA	70.98	77.90	86.52	86.60
KLDA	81.06	88.65	94.88	97.76
KLSMDA	83.42	88.70	95.04	97.83
KJDA	83.76	90.38	96.21	98.15

HRRP target recognition based on kernel joint discriminant analysis

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 23

相关文章 0

编辑推荐

Metrics

本文评价