A camouflage target detection method based on local minimum difference constraints

doi:10.23919/JSEE.2022.000049

Journal of Systems Engineering and Electronics ›› 2023, Vol. 34 ›› Issue (3): 696-705.doi: 10.23919/JSEE.2022.000049

• • 上一篇

收稿日期:2021-05-25 出版日期:2023-06-15 发布日期:2023-06-30

A camouflage target detection method based on local minimum difference constraints

Yuanying GAN(), Chuntong LIU(), Hongcai LI(), Zhongye LIU()

¹ School of Missile Engineering, Rocket Force University of Engineering, Xi’an 710025, China

Received:2021-05-25 Online:2023-06-15 Published:2023-06-30
Contact: Yuanying GAN E-mail:yiran_gan@sina.cn;Liuchuntong72@.sina.com;1013312965@qq.com;zhongye_liu81192@163.com
About author:
GAN Yuanying was born in 1993. She received her M.S. degree from Xi’an Shiyou University, Xi’an, China, in 2018. She is currently pursuing her Ph.D. degree with the Rocket Force University of Engineering, China. Her current research interests include image processing and camouflage image analysis. E-mail: yiran_gan@sina.cn

LIU Chuntong was born in 1972. He received his B.S., M.S., and Ph.D degrees in the Second Artillery College 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 are photoelectric technology and optical fiber sensing technology and application. E-mail: Liuchuntong72@.sina.com

LI Hongcai was born in 1983. He received his B.S., M.S., and Ph.D degrees in the Second Artillery College of Engineering, Xi’an, China, in 2005, 2008 and 2012, respectively. He is currently with the Rocket Force University of Engineering, China. His major research interest is photoelectric protection theory and technology. E-mail: 1013312965@qq.com

LIU Zhongye was born in 1996. He received his B.S. degree from Hebei University of Science and Technology, Shijiazhuang, China, in 2019. He is currently pursuing his M.S. degree with the Rocket Force University of Engineering, China. His current research interests include image processing and image segmentation. E-mail: zhongye_liu81192@163.com

摘要/Abstract

Abstract:

To address the problems of missing inside and incomplete edge contours in camouflaged target detection results, we propose a camouflaged moving target detection algorithm based on local minimum difference constraints (LMDC). The algorithm first uses the mean to optimize the initial background model, removes the stable background region by global comparison, and extracts the edge point set in the potential target region so that each boundary point (seed) grows along the center of the target. Finally, we define the minor difference constraints term, combine the seed path and the target space consistency, and calculate the attributes of each pixel in the potential target area to realize camouflaged moving target detection. The algorithm of this paper is verified based on a public data sofa video and test videos and compared with the five classic algorithms. The experimental results show that the proposed algorithm yields good results based on integrity, accuracy, and a number of objective evaluation indexes, and its overall performance is better than that of the compared algorithms.

Key words: camouflage target detection, moving target, local contrast

. [J]. Journal of Systems Engineering and Electronics, 2023, 34(3): 696-705.

Yuanying GAN, Chuntong LIU, Hongcai LI, Zhongye LIU. A camouflage target detection method based on local minimum difference constraints[J]. Journal of Systems Engineering and Electronics, 2023, 34(3): 696-705.

图/表 11

参考文献 31

1	CAO J, CHOLAKKAL H, RAO A, et al D2Det: towards high quality object detection and instance segmentation. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, 11482- 11491.
2	LIU S T, JIANG K H, LIU Z X. Ship target detection of aerial reconnaissance image based on region covariance and objectness. Systems Engineering and Electronics. 2019, 41(5): 972–980. (in Chinese)
3	YANG J Y, SHI W, YUE H J, et al. Spatiotemporally scalable matrix recovery for background modeling and moving object detection. Signal Processing, 2019, 168: 107362.
4	MERILAITA S, SCOTT-SAMUEL N E, CUTHILL I C. How camouflage works. Philosophical Transactions of the Royal Society of London, 2017, 372(1724): 20160341.
5	LI K J, LI Y B, ZHANG H R Evaluation of optical camouflage effect of air defense missile equipment. Laser & Infrared, 2019, 49 (5): 95- 100.
6	XU W D, WANG X W. Camouflage detection and evaluation theory and technology. Beijing: National Defense University Press, 2015.
7	CUI L Q, CHEN J J, REN Q Y, et al Saliency object detection based on multiple features and prior information. Journal of Image and Graphics, 2020, 25 (2): 321- 332.
8	OWENS A, BARNES C, FLINT A, et al Camouflaging an object from many viewpoints. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2014, 2782- 2789.
9	WANG Z, YAN Y H, JIAO X Y Multi-index comprehensive evaluation of camouflage based on gray theory. ACTA Armamentarii, 2013, 34 (10): 1250- 1257.
10	LIU J J, HOU Q, CHENG M M, et al A simple pooling-based design for real-time salient object detection. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, 3912- 3921.
11	ZHAO J X, LIU J J, FAN D P, et al Egnet: edge guidance network for salient object detection. Proc. of the IEEE/CVF International Conference on Computer Vision, 2019, 8778- 8787.
12	WANG B, MA Y J, LI P F Moving target detection based on improved three frame difference and background difference. Computer Systems & Applications, 2015, 24 (8): 154- 158.
13	BRUNYE T T, MARTIS S B, HORNER C, et al Visual salience and biological motion interact to determine camouflaged target detectability. Applied Ergonomics, 2018, 73, 1- 6. doi: 10.1016/j.apergo.2018.05.016
14	BRUNYE T T, MARTIS S B, KIREJCZYK J A, et al Camouflage pattern features interact with movement speed to determine human target detectability. Applied Ergonomics, 2019, 77, 50- 57. doi: 10.1016/j.apergo.2019.01.004
15	DAVIDSON M Perturbation approach to spatial brightness interaction in human vision. Journal of the Optical Society of America, 1968, 58 (9): 1300- 1308. doi: 10.1364/JOSA.58.001300
16	BARNICH O, DROOGENBROECK M V ViBE: a powerful random technique to estimate the background in video sequences. Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2009, 945- 948.
17	GONG W G, LIU R Y, ZHANG R Foreground segmentation under sudden illumination changes by feature fusion. Infrared and Laser Engineering, 2014, 43 (12): 4164- 4169.
18	TAO H J, LU X B Smoke vehicle detection based on robust codebook model and robust volume local binary count patterns. Image and Vision Computing, 2019, 86, 17- 27. doi: 10.1016/j.imavis.2019.03.008
19	WU Z J, GAO X Efficient practical codebook-precoding MIMO scheme based on signal space diversity. Journal of Systems Engineering and Electronics, 2016, 27 (1): 1- 9.
20	LI Y F, LEI L, SONG J X, et al Combination of local binary pattern operator with sample consensus model for moving objects detection. Infrared Physics & Technology, 2018, 92, 44- 52.
21	XIAO F, CUTHILL I C Background complexity and the detectability of camouflaged targets by birds and humans. Proc. of the Royal Society B: Biological Sciences, 2016, 283, 20161527.
22	CHEN D L, XU G L. Cross-domain person re-identification method based on attention mechanism to learn intra-domain variance. https://kns.cnki.net/kcms/detail/51.1307.TP.20210705.0904.004. html.
23	ZHAN Y F, WANG C Y, WANG X G A simple baseline for multi-object tracking, computer vision and pattern recognition. International Journal of Computer Vision, 2021, 129 (11): 3069- 3087. doi: 10.1007/s11263-021-01513-4
24	HAUNG H J, YANG W J, CHEN X T. EANet: enhancing alignment for cross-domain person re-identification. https://arxiv.org/abs/1812.11369.
25	ZHAO H S, SHI J P, QI X J Pyramid scene parsing network. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, 6230- 6239.
26	TSAI Y H, YANG M H, BLACK M J Video segmentation via object flow. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, 3899- 3908.
27	NARKI N, PERAZZI F, WANG O, et al Bilateral space video segmentation. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, 743- 751.
28	WANG Q, ZHANG L, BERTINETTO L Fast online object tracking and segmentation: a unifying approach. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, 1328- 1338.
29	OH S W, LEE J Y, SUNKAVALLI K, et al Fast video object segmentation by reference-guided mask propagation. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, 7376- 7385.
30	FAN D P, JI G P, SUN G, et al Camouflaged object detection. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, 2774- 2784.
31	MARGOLIN R, ZELNIKMANOR L, TAL A How to evaluate foreground maps? Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2014, 248- 255.

Indicator	Lab					Sofa
Indicator	ViBe	PSPNet	Siammask	SINet	LMDC	ViBe	PSPNet	Siammask	SINet	LMDC
A_D	0.2217	0.8898	1.0362	1.0508	1.0799	0.9775	1.0435	0.9637	0.9521	1.1046
R	1.4017	0.5450	0.0043	0.0037	0.0066	0.6951	0.2459	0.0049	0.0033	0.0078
MAPE	0.7519	0.9144	0.9349	0.9517	0.9067	0.8508	0.6262	0.5445	0.8632	0.8964
F_measure	0.7207	0.8898	0.9327	0.9201	0.9465	0.6358	0.5053	0.5302	0.6030	0.9478

Indicator	Commando					Jungle
Indicator	ViBe	PSPNet	Siammask	SINet	LMDC	ViBe	PSPNet	Siammask	SINet	LMDC
A_D	0	—	0.5436	1.0173	1.0631	0	—	0.3384	0	0.3179
R	2.7893	—	0.0057	0.0019	0.0012	1.0835	—	0.0082	0.0103	0.0009
MAPE	0.1581	—	0.8014	0.8662	0.8661	0.0518	—	0.3477	0.2018	0.4164
F_measure	0.1846	—	0.8242	0.6404	0.9282	0.1510	—	0.6403	0.4893	0.4152

A camouflage target detection method based on local minimum difference constraints

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 31

相关文章 0

编辑推荐

Metrics

本文评价