Compressed Sensing Reconstruction of Hyperspectral Images Based on Adaptive Blocking

WANG Yang; YANG Mengyu; ZHAO Shoubo

doi:10.11999/JEIT220738

Volume 45 Issue 7

Jul. 2023

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2023 > 45(7): 2605-2613

WANG Yang, YANG Mengyu, ZHAO Shoubo. Compressed Sensing Reconstruction of Hyperspectral Images Based on Adaptive Blocking[J]. Journal of Electronics & Information Technology, 2023, 45(7): 2605-2613. doi: 10.11999/JEIT220738

Citation:

WANG Yang, YANG Mengyu, ZHAO Shoubo. Compressed Sensing Reconstruction of Hyperspectral Images Based on Adaptive Blocking[J]. Journal of Electronics & Information Technology, 2023, 45(7): 2605-2613. doi: 10.11999/JEIT220738

Citation:

PDF( 3079 KB)

Compressed Sensing Reconstruction of Hyperspectral Images Based on Adaptive Blocking

doi: 10.11999/JEIT220738

WANG Yang¹,
YANG Mengyu¹,
ZHAO Shoubo^{1, 2
,
,}

1.
School of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China
2.
School of Mechanical and Power Engineering, Guangdong Ocean University, Zhanjiang 524000, China

Funds: The National Natural Science Foundation of China (61801148), The Young Innovative Talents Training Plan of Heilongjiang Ordinary Undergraduate Colleges and Universities (UNPYSCT-2020187)

Received Date: 2022-06-06
Rev Recd Date: 2023-01-14

Available Online: 2023-02-03

Publish Date: 2023-07-10

Abstract

Abstract

In the study of sampling and reconstruction of hyperspectral images, global sampling and fixed block sampling do not take into account the complex texture distribution of hyperspectral images, and the use of the same measurement matrix results in poor image reconstruction quality. To solve this problem, an Adaptive Block Compressed Sensing-Image Entropy (ABCS-IE) is presented. In this method, 2-dimensional image entropy is used as a measure of texture details of hyperspectral images. The size of image blocks is adaptively changed according to the texture details distribution of the image. Then, specific sampling values are assigned to different image blocks, and a special measurement matrix is designed to compress the image blocks according to the assigned sampling values, and the sampled measurements are brought into the reconstruction algorithm for reconstruction. The experimental results show that when this method is applied to the compression-aware reconstruction algorithm to sample and reconstruct the hyperspectral image, the visual effect of the reconstructed image is significantly improved. The maximum Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM) are obtained. When the sampling rate is 0.4, the PSNR is increased by 2～4 dB and the SSIM is increased by 0.27, the Root Mean Square Error (RMSE) and the information entropy difference (ΔH) are also reduced, indicating that the reconstructed image is closer to the original image. Moreover, the operation time is reduced by 1～1.5 s. It can be seen that this method can make full use of texture features of hyperspectral images and improve effectively the quality of image reconstruction, and reduce the operation time of reconstruction.
- Hyperspectral image reconstruction,
- Adaptive blocking,
- Compression Sensing(CS),
- Image two-dimensional entropy

FullText(HTML)

References(22)

References

[1]	LIU Lei, SUN Min, REN Xiang, et al. Hyperspectral image quality based on convolutional network of multi-scale depth[J]. Journal of Visual Communication and Image Representation, 2020, 71: 102721. doi: 10.1016/j.jvcir.2019.102721
[2]	FABELO H, ORTEGA S, SZOLNA A, et al. In-vivo hyperspectral human brain image database for brain cancer detection[J]. IEEE Access, 2019, 7: 39098–39116. doi: 10.1109/ACCESS.2019.2904788
[3]	王建成, 朱猛. 高光谱侦察技术的发展[J]. 航天电子对抗, 2019, 35(3): 37–45. doi: 10.16328/j.htdz8511.2019.03.009 WANG Jiancheng and ZHU Meng. Development status of hyperspectral reconnaissance[J]. Aerospace Electronic Warfare, 2019, 35(3): 37–45. doi: 10.16328/j.htdz8511.2019.03.009
[4]	LU Bing, HE Yuhong, and DAO P D. Comparing the performance of multispectral and hyperspectral images for estimating vegetation properties[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(6): 1784–1797. doi: 10.1109/JSTARS.2019.2910558
[5]	王立国, 王丽凤. 结合高光谱像素级信息和CNN的玉米种子品种识别模型[J]. 遥感学报, 2021, 25(11): 2234–2244. WANG Liguo and WANG Lifeng. Variety identification model for maize seeds using hyperspectral pixel-level information combined with convolutional neural network[J]. National Remote Sensing Bulletin, 2021, 25(11): 2234–2244.
[6]	邓亚美, 王秀娟, 杨敏莉, 等. 成像技术在食品安全与质量控制中的研究进展[J]. 色谱, 2020, 38(7): 741–749. doi: 10.3724/SP.J.1123.202 DENG Yamei, WANG Xiujuan, YANG Minli, et al. Research advances in imaging technology for food safety and quality control[J]. Chinese Journal of Chromatography, 2020, 38(7): 741–749. doi: 10.3724/SP.J.1123.202
[7]	HU Meiqi, WU Chen, ZHANG Liangpei, et al. Hyperspectral anomaly change detection based on autoencoder[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 3750–3762. doi: 10.1109/JSTARS.2021.3066508
[8]	LUO Jiqiang, XU Tingfa, PAN Teng, et al. An efficient compression method of hyperspectral images based on compressed sensing and joint Optimization[J]. Integrated Ferroelectrics, 2020, 208(1): 194–205. doi: 10.1080/10584587.2020.1728625
[9]	SUN Zheng and YAN Xiangyang. Image reconstruction based on compressed sensing for sparse-data endoscopic photoacoustic tomography[J]. Computers in Biology and Medicine, 2020, 116: 103587. doi: 10.1016/j.compbiomed.2019.103587
[10]	LI Denghui and WANG Yanhong. Implementation of image resampling algorithm based on compressed sensing[J]. Journal of Physics:Conference Series, 2021, 1732: 012071. doi: 10.1088/1742-6596/1732/1/012071
[11]	WANG Rongfang, QIN Yali, WANG Zhenbiao, et al. Group-based sparse representation for compressed sensing image reconstruction with joint regularization[J]. Electronics, 2022, 11(2): 182. doi: 10.3390/electronics11020182
[12]	赵首博, 李秀红. 基于压缩感知的反射光谱重构算法研究[J]. 光谱学与光谱分析, 2021, 41(4): 1092–1096. doi: 10.3964/j.issn.1000-0593(2021)04-1092-05 ZHAO Shoubo and LI Xiuhong. Research on reflection spectrum reconstruction algorithm based on compressed sensing[J]. Spectroscopy and Spectral Analysis, 2021, 41(4): 1092–1096. doi: 10.3964/j.issn.1000-0593(2021)04-1092-05
[13]	WEI Ziran, ZHANG Jianlin, XU Zhiyong, et al. Optimization methods of compressively sensed image reconstruction based on single-pixel imaging[J]. Applied Sciences, 2020, 10(9): 3288.
[14]	TAO Chenning, ZHU Huanzheng, SUN Peng, et al. Simultaneous coded aperture and dictionary optimization in compressive spectral imaging via coherence minimization[J]. Optics Express, 2020, 28(18): 26587–26600. doi: 10.1364/OE.396260
[15]	ZHANG Hao, MA Xu, LAU D L, et al. Compressive spectral imaging based on hexagonal blue noise coded apertures[J]. IEEE Transactions on Computational Imaging, 2020, 6: 749–763. doi: 10.1109/TCI.2020.2979373
[16]	ZHAO Yushi, HE Wenjun, LIU Zhiying, et al. Optical design of an offner coded aperture snapshot spectral imaging system based on dual-DMDs in the mid-wave infrared band[J]. Optics Express, 2021, 29(24): 39271–39283. doi: 10.1364/OE.444460
[17]	WANG Zhongliang, HE Mi, YE Zhen, et al. Reconstruction of hyperspectral images from spectral compressed sensing based on a multitype mixing model[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 2304–2320. doi: 10.1109/JSTARS.2020.2994334
[18]	谌德荣, 吕海波, 李秋富, 等. 分块压缩感知的全变差正则化重构算法[J]. 电子与信息学报, 2019, 41(9): 2217–2223. doi: 10.11999/JEIT180931 CHEN Derong, LÜ Haibo, LI Qiufu, et al. Total variation regularized reconstruction algorithms for block compressive sensing[J]. Journal of Electronics &Information Technology, 2019, 41(9): 2217–2223. doi: 10.11999/JEIT180931
[19]	DAI Guangzhi, HE Zhiyong, and SUN Hongwei. Ultrasonic block compressed sensing imaging reconstruction algorithm based on wavelet sparse representation[J]. Current Medical Imaging, 2020, 16(3): 262–272. doi: 10.2174/1573405615666191209151746
[20]	ZHANG Zheng, BI Hongbo, KONG Xiaoxue, et al. Adaptive compressed sensing of color images based on salient region detection[J]. Multimedia Tools and Applications, 2020, 79(21): 14777–14791. doi: 10.1007/s11042-018-7062-6
[21]	WANG Xiaodong, LI Yunhui, WANG Zhi, et al. Self-adaptive block-based compressed sensing imaging for remote sensing applications[J]. Journal of Applied Remote Sensing, 2020, 14(1): 016513. doi: 10.1117/1.JRS.14.016513
[22]	KAZEMI V, SHAHZADI A, and BIZAKIi H K. Multifocus image fusion using adaptive block compressive sensing by combining spatial frequency[J]. Multimedia Tools and Applications, 2022, 81(11): 15153–15170. doi: 10.1007/s11042-022-12072-2