Research on infrared dim and small target detection algorithm based on low-rank tensor recovery

doi:10.23919/JSEE.2023.000004

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (4): 861-872.doi: 10.23919/JSEE.2023.000004

• • 上一篇

收稿日期:2020-12-23 出版日期:2023-08-18 发布日期:2023-08-28

Research on infrared dim and small target detection algorithm based on low-rank tensor recovery

Chuntong LIU¹(), Hao WANG¹^,²^,*()

¹ College of Missile Engineering, Rocket Force University of Engineering, Xi’an 710025, China
² Beijing Institute of Remote Sensing Equipment, Beijing 100854, China

Received:2020-12-23 Online:2023-08-18 Published:2023-08-28
Contact: Hao WANG E-mail:liuchuntong72@sina.com;17791821514@163.com
About author:
LIU Chuntong was born in 1972. He received his B.S., M.S., and Ph.D degrees in the Rocket Force University of Engineering, Xi ’an, China, in 1993, 1996 and 2009, respectively. He is currently with the Rocket Force University of Engineering, China. His major research interests include photoelectric technology and optical fiber sensing technology and application. E-mail: liuchuntong72@sina.com

WANG Hao was born in 1991. He received his B.S and M.S degrees in the Rocket Force University of Engineering, Xi’an, China, in 2014 and 2017, respectively. He is currently with the Rocket Force University of Engineering, China. His major research interests include infrared small and dim target detection technology. E-mail: 17791821514@163.com

摘要/Abstract

Abstract:

In order to rapidly and accurately detect infrared small and dim targets in the infrared image of complex scene collected by virtual prototyping of space-based downward-looking multiband detection, an improved detection algorithm of infrared small and dim target is proposed in this paper. Firstly, the original infrared images are changed into a new infrared patch tensor mode through data reconstruction. Then, the infrared small and dim target detection problems are converted to low-rank tensor recovery problems based on tensor nuclear norm in accordance with patch tensor characteristics, and inverse variance weighted entropy is defined for self-adaptive adjustment of sparseness. Finally, the low-rank tensor recovery problem with noise is solved by alternating the direction method to obtain the sparse target image, and the final small target is worked out by a simple partitioning algorithm. The test results in various space-based downward-looking complex scenes show that such method can restrain complex background well by virtue of rapid arithmetic speed with high detection probability and low false alarm rate. It is a kind of infrared small and dim target detection method with good performance.

Key words: complex scene, infrared block tensor, tensor kernel norm, low-rank tensor restoration, weighted inverse entropy, alternating direction method

. [J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 861-872.

Chuntong LIU, Hao WANG. Research on infrared dim and small target detection algorithm based on low-rank tensor recovery[J]. Journal of Systems Engineering and Electronics, 2023, 34(4): 861-872.

图/表 16

参考文献 31

1	JIANG T X, HUANG T Z, ZHAO X L, et al Multi-dimensional imaging data recovery via minimizing the partial sum of tubal nuclear norm. Journal of Computational and Applied Mathematics, 2020, 372, 112680.
2	ZHANG W C, CHEN J, GAO Y. Infrared small and dim target detection based on weighted nuclear norm minimization. Ordnance Industry Automation, 2018, 37(6): 7. (in Chinese)
3	FAN Z L, BI D Y, XIONG L, et al Dim infrared image enhancement based on convolutional neural network. Neurocomputing, 2018, 272, 396- 404. doi: 10.1016/j.neucom.2017.07.017
4	LIU M Q, HUANG Z C, FAN Z, et al. Infrared dim target detection and tracking based on particle filte. Proc. of the 36th Chinese Control Conference, 2017: 5372−5378.
5	BAI X Z, BI Y G Derivative entropy-based contrast measure for infrared small-target detection. IEEE Trans. on Geoscience and Remote Sensing, 2018, 56 (4): 2452- 2466. doi: 10.1109/TGRS.2017.2781143
6	WANG W X, FU Y T, DONG F, et al Infrared ship target detection method based on deep convolution neural network. Acta Optica Sinica, 2018, 38 (7): 0712006. doi: 10.3788/AOS201838.0712006
7	MARVASTI F S, MOSAVI M R, NASIRI M Flying small target detection in IR images based on adaptive toggle operator. IET Computer Vision, 2018, 12 (4): 527- 534. doi: 10.1049/iet-cvi.2017.0327
8	WANG X Y, PENG Z M, ZHANG P, et al Infrared small target detection via nonnegativity-constrained variational mode decomposition. IEEE Gecscience and Remote Sensing Letters, 2017, 14 (10): 1700- 1704. doi: 10.1109/LGRS.2017.2729512
9	PENTLAND A P Fractal-based description of natural scenes. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1984, 6 (6): 661- 674.
10	TOM V T, PELI T, LEUNG M, et al. Morphology-based algorithm for point target detection in infrared backgrounds. Proc. of the Optical Engineering and Photonics in Aero-space Sensing, 1993: 2−11.
11	DESHPANDE S D, MENG H E, VENKATESWARLU R, et al. Max-mean and max-median filters for detection of small targets. Proc. of the SPIE’s International Symposium on Optical Science, Engineering, and Instrumentation, 1999: 74−83.
12	DENG L Z, ZHU H, ZHOU Q, et al Adaptive top-hat filter based on quantum genetic algorithm for infrared small target detection. Multimedia Tools and Applications, 2018, 77 (9): 10539- 10551.
13	ZHANG Y, TIAN X, REN P. An adaptive bilateral filter based framework for image denoising. Neurocomputing, 2014, 140(22): 299−316.
14	ZHANG S F, HUANG X H, WANG M. Background suppression algorithm for infrared images based on robinson guard filter. Proc. of the 2nd International Conference on Multimedia and Image processing, 2017: 250−254.
15	WANG X Y, PENG Z M. ZHANG P, et al Infrared small target detection via nonnegativity-constrained variational mode decomposition. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (10): 1700- 1704.
16	YI X, WANG B J, ZHOU H X, et al Dim and small infrared target fast detection guided by visual saliency. Infrared Physics & Technology, 2019, 97, 6- 14.
17	CHEN C L P, LI H, WEI Y, et al A local contrast method for small infrared target detection. IEEE Geoscience Remote Sensing Letters, 2014, 52 (1): 574- 581. doi: 10.1109/TGRS.2013.2242477
18	WEI Y T, YOU X G, LI H Multiscale patch-based contrast measure for small infrared target detection. Pattern Recognition, 2016, 58, 216- 226. doi: 10.1016/j.patcog.2016.04.002
19	NIE J Y, QU S C, WEI Y T, et al An infrared small target detection method based on multiscale local homogeneity measure. Infrared Physics & Technology, 2018, 90, 186- 194.
20	HAN J H, LIANG K, ZHOU B, et al Infrared small target detection utilizing the multiscale relative local contrast measure. IEEE Geoscience and Remote Sensing Letters, 2018, 15 (4): 612- 616. doi: 10.1109/LGRS.2018.2790909
21	DENG H, SUN X P, LIU M L, et al Small infrared target detection based on weighted local difference measure. IEEE Trans. on Geoscience and Remote Sensing, 2016, 54 (7): 4204- 4214. doi: 10.1109/TGRS.2016.2538295
22	QIAN K, ZHOU H X, WANG B J, et al Infrared dim moving target tracking via sparsity-based discriminative classifier and convolutional network. Infrared Physics & Technology, 2017, 86, 103- 115.
23	SUN Y, YANG J G, LONG Y L, et al Infrared small target detection via spatial-temporal total variation regularization and weighted tensor nuclear norm. IEEE Access, 2019, 7, 56667- 56682. doi: 10.1109/ACCESS.2019.2914281
24	GAO C Q, MENG D Y, YANG Y, et al Infrared patch-image model for small target detection in a single image. IEEE Trans. on Image Processing, 2013, 22 (12): 4996- 5009. doi: 10.1109/TIP.2013.2281420
25	MA M Y, WANG D J, SUN H, et al Infrared dim-small target detection based on robust principal component analysis and multi-point constant false alarm. Acta Optica Sinica, 2019, 39 (8): 0810001. doi: 10.3788/AOS201939.0810001
26	DAI Y M, WU Y Q, SONG Y, et al Non-negative infrared patch-image model: robust target-background separation via partial sum minimization of singular values. Infrared Physics & Technology, 2017, 81, 182- 194.
27	DAI Y M, WU Y Q Reweighted infrared patch-tensor model with both nonlocal and local priors for single-frame small target detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10 (8): 3752- 3767. doi: 10.1109/JSTARS.2017.2700023
28	ZHANG L D, PENG Z M Infrared small target detection based on partial sum of the tensor nuclear norm. Remote Sensing, 2019, 11 (4): 382. doi: 10.3390/rs11040382
29	DU P, HAMDULLA A Infrared small target detection using homogeneity-weighted local contrast measure. IEEE Geoscience and Remote Sensing Letters, 2019, 17 (3): 514- 518.
30	GAO J Y, GUO Y L, LIN Z P, et al Robust infrared sm all target detection using multiscale gray and variance difference measures. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11 (12): 5039- 5052. doi: 10.1109/JSTARS.2018.2877501
31	KANG H, XIA M Detectability of infrared small targets. Infrared Physics & Technology, 2010, 53, 208- 217.

Image	Sensor	Resolution	SNR	Detail
Sequence 1	Infrared	640×640	3	Single pixel point target is in the hilly area
Sequence 2	Infrared	640×640	3	Single pixel point target is in the water lake area
Sequence 3	Infrared	640×640	3	Single pixel point target is in the cloud area
Sequence 4	Infrared	640×640	1	Single pixel point target is around the border

Method	Scene
Method	Scene 1	Scene 2	Scene 3	Scene 4-1	Scene 4-2	Scene 4-3
Top-hat	1.09	1.02	2.07	3.79	19.03	40.66
LCM	4.82	5.67	10.87	24.58	10.44	23.78
NIPPS	70.44	259.67	123.34	29.50	25.19	117.56
RIPT	NaN	NaN	NaN	534.31	418.24	746.13
PSTNN	3.10	1.05	2.65	2.66	8.27	14.83
Proposed	438.93	639.53	497.69	Inf	Inf	Inf

Method	Scene
Method	Scene 1	Scene 2	Scene 3	Scene 4-1	Scene 4-2	Scene 4-3
Top-hat	0.92	0.83	0.99	0.07	0.06	0.05
LCM	0.76	0.80	0.73	0.78	0.83	0.76
NIPPS	0.10	0.09	0.16	0	0.01	0.01
RIPT	NaN	NaN	NaN	0	0	0
PSTNN	0.13	0.12	0.19	0.04	0.03	0.03
Proposed	0	0	0	0	0	0

Method	Scene
Method	Scene 1	Scene 2	Scene 3	Scene 4-1	Scene 4-2	Scene 4-3
Top-hat	0.89	0.88	0.87	0.98	0.98	0.91
LCM	12.72	9.14	8.86	8.86	8.62	8.77
NIPPS	618.71	619.26	613.05	612.90	614.34	611.72
RIPT	5.61	7.01	5.89	4.43	4.09	4.18
PSTNN	59.79	59.95	60.29	71.36	71.36	69.98
Proposed	3.90	3.83	3.71	3.78	3.81	4.09

Parameter	Value
$ {\lambda _1} $	0.15
$ {\lambda _2} $	0.11
$ {\lambda _3} $	0.12
${\lambda _{4{{ - } }1} }$	0.36
${\lambda _{4{{ - 2} } } }$	0.36
${\lambda _{4{{ - 3} } } }$	0.36

Research on infrared dim and small target detection algorithm based on low-rank tensor recovery

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 31

相关文章 0

编辑推荐

Metrics

本文评价

Rate	Method
Rate	Top-hat	LCM	NIPPS	RIPT	PSTNN	Proposed
TPR	0.512	0.685	0.691	0.524	0.429	0.947
FAR	0.401	0.418	0.432	0.509	0.614	0.053