优化稀疏表示的迷彩伪装目标高光谱识别方法研究

doi:10.3964/j.issn.1000-0593(2024)12-3534-09

Abstract
References
Related Citation (15)

Download: PDF (41862 KB)
Export: BibTeX | EndNote (RIS)

Abstract Referring to the current use of sparse representation algorithms to extract camouflaged targets from hyperspectral images, the selection of the background dictionary is affected by the “same spectrum of different objects” of the hidden targets, resulting in the inability to detect camouflaged targets accurately. In this paper, we take the grassland camouflage net and desert camouflage net as the research objects, collect the visible-near-infrared reflectance spectra of the camouflage net and airborne hyperspectral images respectively, and analyze the spectral characteristics of the background pixels and camouflage target pixels in the camouflage net and airborne images measured outdoors. Taking advantage of the fact that the spectra of the camouflage nets measured outdoors and the background in the airborne images are different and the possibility of neighboring image elements belonging to the same feature is high, the background dictionary selection method based on the constraints of Euclidean distances and image homogeneity features is proposed, and the sparse representation of the background dictionary is further utilized to identify the target. The results show that (1) in the wavelength range of 750~1 000 nm for grass camouflage, the reflectance of the background pixel spectrum in the image is higher than that of the camouflage net spectrum. For desert camouflage: in the range of 550～700 nm, the reflectance of the background pixel spectrum in the image is higher than that of the camouflage net spectrum. (2) By establishing spatial and spectral feature constraints with the maximum spectral Euclidean distance to the target image element and the highest homogeneity with neighboring image elements, 413 background image elements in the grass camouflage image and 507 background image elements in the desert camouflage image were selected as the background dictionary. (3) Based on the improved background dictionary selection method, the sparse representation algorithm is utilized to identify the camouflage targets, and the results can accurately discriminate the location and number of camouflage targets. The area under the curve (AUC) of the receiver operating characteristics for the detection of grass camouflage targets and desert camouflage targets reaches 0.96 and 0.98, respectively, indicating that the algorithm has good detection performance for both grass camouflage targets and desert camouflage targets.

Key words：Airborne hyperspectral; Visible-near infrared spectra; Camouflage netting; Background dictionary; Sparse representation

Received: 2023-11-29 Accepted: 2024-05-11

ZTFLH:

TP79

Corresponding Authors: BAO Ni-sha E-mail: baonisha@mail.neu.edu.cn

Cite this article:

XU Jing-yu,BAO Ni-sha,LANG Jie-shuang, et al. A Hyperspectral Recognition Method for Camouflaged Targets Based on Background Dictionary Sparse Representation[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(12): 3534-3542.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2024)12-3534-09 OR https://www.gpxygpfx.com/EN/Y2024/V44/I12/3534

[1] LI Shu-tao, WU Qiong, KANG Xu-dong(李树涛, 吴琼, 康旭东). Acta Geodaetica et Cartographica Sinica(测绘学报), 2023, 52(7): 1059.
[2] YU Xu-chu, LIU Bing, XUE Zhi-xiang(余旭初, 刘冰, 薛志祥). Acta Geodaetica et Cartographica Sinica(测绘学报), 2023, 52(7): 1115.
[3] GUO Jia-qi, ZHANG Zhi-gang, HU Ze-bin, et al(郭家齐, 张志刚, 胡泽斌, 等). Infrared Technology(红外技术), 2016, 38(2): 96.
[4] Olshausen B A, Field D J. Nature, 1996, 381: 607.
[5] Liu Y, Chen X, Ward K R, et al. IEEE Signal Processing Letters, 2016, 23(12): 1882.
[6] Yang J, Wright J, Huang S T, et al. IEEE Transactions on Image Processing, 2010, 19(11): 2861.
[7] Ma W, Xu F. Journal of Real-Time Image Processing, 2021, 18: 407.
[8] Chen Y, NaSTDabadi N M, Tran T D. IEEE Journal of Selected Topics in Signal Processing, 2011, 5(3): 629.
[9] TAO Yang, LIN Fei-peng, YANG Wen, et al(陶洋, 林飞鹏, 杨雯, 等). Application of Electronic Technique(电子技术应用), 2022, 48(1): 124.
[10] Wei C, Jiang Z, Yuan Y. Weighed Hierarchical Sparse Representation for Hyperspectral Target Detection, IGARSS 2020 International Geoscience and Remote Sensing Symposium, 2020, 2428.
[11] Peng J, Jiang X, Chen N, et al. Neurocomputing, 2019, 334: 239.
[12] CHEN Shan-xue, HE Yu-feng(陈善学, 何宇峰). Acta Optica Sinica(光学学报), 2023, 43(1): 66.
[13] NING Hong-zhang, TAN Xin, LI Yu-hang, et al(宁鸿章, 谭鑫, 李宇航, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(12): 3699.
[14] Zhang Y, Du B, Zhang L. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(3): 1346.
[15] Tropp J A, Gilbert A C. IEEE Transactions on Information Theory, 2007, 53(12): 4655.
[16] WANG Jun, WU Hong-qiao, SONG Zhao-qi(王骏, 吴虹桥, 宋兆祺). Radiologic Practice(放射学实践), 2000, 3: 201.
[17] Reed S I, Yu X. IEEE Trans. Acoustics, Speech, and Signal Processing, 1990, 38(10): 1760.
[18] Chang C I, Chiang SS. IEEE Transactions on Geoscience and Remote Sensing, 2002，(6): 40.
[19] Manolakis D, Lockwood R B, Cooley T, et al. Proceedings of SPIE, 2009, 7334: 733402.