Lightweight infrared polarization image enhancement method via spatial-frequency collaborative learning

WANG Binglu; WU Jianzhen; WANG Shunzhou

doi:null

您当前的位置：

首页 >

文章列表页 >

Lightweight infrared polarization image enhancement method via spatial-frequency collaborative learning

更新时间：2026-05-20

- Lightweight infrared polarization image enhancement method via spatial-frequency collaborative learning
- Chinese Journal on Internet of Things (2026)
- 作者机构：
  
  1.西安建筑科技大学信息与控制工程学院，陕西西安 710399
  2.西北工业大学航天学院，陕西西安 710129
  3.河南大学人工智能学院，河南郑州 450046
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62401447);Key Research and Development Program of Shaanxi Province(2024GX-YBXM-051);Natural Science Basic Research Program of Shaanxi(2025JC-YBQN-877);Key R&D and Promotion Projects of Henan Province(262102210162)
- DOI：
  CLC：
- Received：26 January 2026，
  
  Revised：2026-03-25，
  
  Accepted：25 March 2026，
- 稿件说明：
移动端阅览
WANG Binglu, WU Jianzhen, WANG Shunzhou. Lightweight infrared polarization image enhancement method via spatial-frequency collaborative learning[J/OL]. Chinese Journal on Internet of Things, 2026.
DOI：

WANG Binglu, WU Jianzhen, WANG Shunzhou. Lightweight infrared polarization image enhancement method via spatial-frequency collaborative learning[J/OL]. Chinese Journal on Internet of Things, 2026. DOI：

摘要

复杂背景的目标识别是物联网边缘感知体系中很重要的任务，而红外偏振图像在安防，伪装检测领域展现出优越的目标背景对比度。然而，由于成像系统计算速度慢以及传感器硬件缺陷问题，长波红外焦平面分割偏振成像系统在实际应用中难以高效获取高质量的图像，阻碍下游检测等任务的精度。为此，提出一种基于空频域协同的轻量级红外偏振图像联合去噪与去马赛克方法，该方法通过构建三阶段学习网络，在保证低计算复杂度的同时提升偏振图像重建质量。所设计的双域交互去噪模块充分利用频域信息的统计性特征，有效抑制噪声并保留偏振特性；同时，在粗糙去马赛克之后引入轻量化精细重建模块，通过深度分组卷积压缩模型参数量并提升重建性能。实验结果表明，所提方法在 IR-DoT 与 IR-DoFP 数据集上在保持低计算开销的前提下取得了优于现有方法的重建效果，为物联网边缘终端提供了一种低功耗、高质量的感知数据预处理方案。

Abstract

Object recognition in complex scenes is an important task in the Internet of Things (IoT) based edge perception systems. Infrared polarization images show superior foreground–background contrast in security monitoring and camouflage detection. However

due to the limited hardware resources of imaging systems

it is difficult for long-wave infrared division-of-focal-plane (DoFP) polarization imaging systems to achieve high-quality images in practical applications

which adversely affects edge perception performance. To this end

a lightweight joint denoising and demosaicking network for infrared polarization images is developed via spatial-frequency collaborative learning. The proposed method employs a three-stage learning network to enhance the quality of polarization image reconstruction while maintaining low computational complexity. The dual-domain interactive denoising block leverages the statistical properties of the frequency domain to suppress noise while preserving polarization features. After coarse demosaicking

a lightweight fine reconstruction module is adopted to generate the final results. Depthwise grouped convolutions are used to reduce model parameter count and improve reconstruction quality. Extensive experiments are performed on the IR-DoT and IR-DoFP datasets. The results show that the proposed method achieves superior performance compared with other leading approaches while maintaining low computational overhead

making it a low-power

high-quality data preprocessing approach for IoT-based edge devices.

关键词

Keywords

references

李磊磊 , 黄海霞 , 郭阳 , 等 . 基于红外辐射偏振成像的目标三维重建方法 [J ] . 红外与毫米波学报 , 2021 , 40 ( 3 ): 413 .

LI L L ， HUANG H X ， GUO Y , et al . 3D reconstruction method of target based on infrared radiation polarization imaging [J ] . Infrared Millim. Waves , 2021 , 40 ( 3 ): 413 .

赵永强 , 李宁 , 潘泉 . 分焦平面红外偏振摄像技术 [M ] . 北京 : 科学出版社 , 2022 : 7 - 11 .

ZHAO Y Q , LI N , PAN Q . Division of focal plane infra⁃ red polarization photography [M ] . Beijing : Science Press , 2022 : 7 - 11 .

赵永强 , 乔新博 , 李宁 , 等 . 偏振视觉 [J ] . 中国科学: 信息科学 , 2024 , 54 ( 7 ): 1620 - 1645 .

ZHAO Y Q , QIAO X B , LI N , et al . Polarization vision [J ] . Scientia Sinica (Informationis) , 2024 , 54 ( 7 ): 1620 - 1645 .

周强国 , 黄志明 , 周炜 . 偏振成像技术的研究进展及应用 [J ] . 红外技术 , 2021 , 43 ( 9 ): 817 - 828 .

ZHOU Q G ， HUANG Z M ， ZHOU W . Research Progress and Application of Polarization Imaging Technology [J ] . Infrared Technology , 2021 , 43 ( 9 ): 817 - 828 .

SARGENT G C , RATLIFF B M , ASARI V K . Conditional generative adversarial network demosaicing strategy for division of focal plane polarimeters [J ] . Optics Express , 2020 , 28 ( 25 ): 38419 - 38443 .

YE W , LI S , ZHAO X , et al . AK times singular value decomposition based image denoising algorithm for DoFP polarization image sensors with Gaussian noise [J ] . IEEE Sensors Journal , 2018 , 18 ( 15 ): 6138 - 6144 .

LIU H , ZHANG Y , CHENG Z , et al . Attention-based neural network for polarimetric image denoising [J ] . Optics Letters , 2022 , 47 ( 11 ): 2726 - 2729 .

LIU J , DUAN J , HAO Y , et al . Polarization image demosaicing and RGB image enhancement for a color polarization sparse focal plane array [J ] . Optics Express , 2023 , 31 ( 14 ): 23475 - 23490 .

LI Z , JIANG H , CAO M , et al . Polarized color image denoising [C ] // 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE , 2023 : 9873 - 9882 .

XING W , EGIAZARIAN K . End-to-end learning for joint image demosaicing, denoising and super-resolution [C ] // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition . 2021 : 3507 - 3516 .

GO J , SOHN K , LEE C . Interpolation using neural networks for digital still cameras [J ] . IEEE Transactions on Consumer Electronics , 2000 , 46 ( 3 ): 610 - 616 .

KAPAH O , HEL-OR H Z . Demosaicking using artificial neural networks [C ] // Applications of Artificial Neural Networks in Image Processing V . SPIE , 2000 , 3962 : 112 - 120 .

LI N , WANG B , GOUDAIL F , et al . Joint denoising-demosaicking network for long-wave infrared division-of-focal-plane polarization images with mixed noise level estimation [J ] . IEEE Transactions on Image Processing , 2023 , 32 : 5961 - 5976 .

赵军辉 , 李怀城 , 王东明 , 等 . 物联网中模型剪枝技术：现状、方法和展望 [J ] . 物联网学报 , 2024 , 8 ( 04 ): 1 - 13 .

ZHAO J H , LI H C , WANG D M , et al . Model pruning techniques in the Internet of things: state of the art, methods and perspectives [J ] . Chinese Journal on Internet of Things , 2024 , 8 ( 04 ): 1 - 13 .

GAO N , JIANG X , ZHANG X , et al . Efficient frequency-domain image deraining with contrastive regularization [C ] // European Conference on Computer Vision . Cham : Springer Nature Switzerland , 2024 : 240 - 257 .

WANG X , YU K , WU S , et al . Esrgan: Enhanced super-resolution generative adversarial networks [C ] // Proceedings of the European conference on computer vision (ECCV) workshops . 2018 : 1 - 10 .

WAN C , YU H , LI Z , et al . Swift parameter-free attention network for efficient super-resolution [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 2024 : 6246 - 6256 .

USMANI K , O’CONNOR T , SHEN X , et al . Three-dimensional polarimetric integral imaging in photon-starved conditions: performance comparison between visible and long wave infrared imaging [J ] . Optics Express , 2020 , 28 ( 13 ): 19281 - 19294 .

LEFKIMMIATIS S , Non-local color image denoising with convolutional neural networks [C ] // Proceedings of the IEEE conference on computer vision and pattern recognition . 2017 : 3587 - 3596 .

BUADES A , COLL B , MOREL J M . A non-local algorithm for image denoising [C ] // 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05) . Ieee , 2005 , 2 : 60 - 65 .

PORTILLA J , STRELA V , WAINWRIGHT M J , et al . Image denoising using scale mixtures of Gaussians in the wavelet domain [J ] . IEEE Transactions on Image processing , 2003 , 12 ( 11 ): 1338 - 1351 .

DABOV K , FOI A , KATKOVNIK V , et al . Image denoising by sparse 3-D transform-domain collaborative filtering [J ] . IEEE Transactions on image processing , 2007 , 16 ( 8 ): 2080 - 2095 .

GUO Q , ZHANG C , ZHANG Y , et al . An efficient SVD-based method for image denoising [J ] . IEEE transactions on Circuits and Systems for Video Technology , 2015 , 26 ( 5 ): 868 - 880 .

JIANG B , LU Y , WANG J , et al . Deep image denoising with adaptive priors [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2022 , 32 ( 8 ): 5124 - 5136 .

REN C , HE X , WANG C , et al . Adaptive consistency prior based deep network for image denoising [C ] // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition . 2021 : 8596 - 8606 .

ZHANG K ; ZUO W ; CHEN Y , et al . Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising [J ] . IEEE transactions on image processing , 2017 , 26 ( 7 ): 3142 - 3155 .

HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition [C ] // Proceedings of the IEEE conference on computer vision and pattern recognition . 2016 : 770 - 778 .

ZHANG Q , XIAO J , TIAN C , et al . A parallel and serial denoising network [J ] . Expert Systems with Applications , 2023 , 231 : 120628 .

TIAN C , ZHENG M , LIN C W , et al . Heterogeneous window transformer for image denoising [J ] . IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2024 , 54 ( 11 ): 6621 - 6632

LEHTINEN J , MUNKBERG J , HASSELGREN J , et al . Noise2Noise: Learning image restoration without clean data [J ] . arXiv preprint arXiv: 1803.04189 , 2018 .

杜永生 , 蒿琳 , 石秦峰 . 低质量红外偏振图像热像特征提取方法 [J ] . 激光杂志 , 2022 , 43 ( 11 ): 159 - 163 .

DU YS , HAO l , SHI QF . Thermal image feature extraction method of low-quality infrared polarization image [J ] . Laser Journal , 2022 , 43 ( 11 ): 159 - 163 .

ZHANG L , DONG W , ZHANG D , et al . Two-stage image denoising by principal component analysis with local pixel grouping [J ] . Pattern recognition , 2010 , 43 ( 4 ): 1531 - 1549 .

CAI T T , WANG L . Orthogonal matching pursuit for sparse signal recovery with noise [J ] . IEEE Transactions on Information theory , 2011 , 57 ( 7 ): 4680 - 4688 .

HU H , JIN H , LIU H , et al . Polarimetric image denoising on small datasets using deep transfer learning [J ] . Optics & Laser Technology , 2023 , 166 : 109632 .

LIU H , LI X , CHENG Z , et al . Pol2Pol: self-supervised polarimetric image denoising [J ] . Optics Letters , 2023 , 48 ( 18 ): 4821 - 4824 .

HIRAKAWA K , PARKS T W . Adaptive homogeneity-directed demosaicing algorithm [J ] . IEEE Transactions on Image Processing , 2005 , 14 ( 3 ): 360 - 369 .

SU C Y . Highly effective iterative demosaicing using weighted-edge and color-difference interpolations [J ] . IEEE Transactions on Consumer Electronics , 2006 , 52 ( 2 ): 639 - 645 .

SYU N S , CHEN Y S , CHUANG Y Y . Learning deep convolutional networks for demosaicing [J ] . arXiv preprint arXiv: 1802.03769 , 2018 .

DONG Y , XIONG R , ZHAO J , et al . Learning a deep demosaicing network for spike camera with color filter array [J ] . IEEE Transactions on Image Processing , 2024 , 33 : 3634 - 3647 .

WU F , HUANG T , XU J , et al . Joint spatial and frequency domain learning for lightweight spectral image demosaicing [J ] . IEEE Transactions on Image Processing , 2025 .

GUO Y , DAI X , WANG S , et al . Attention-based progressive discrimination generative adversarial networks for polarimetric image demosaicing [J ] . IEEE Transactions on Computational Imaging , 2024 , 10 : 713 - 725 .

朱洪波 , 尹浩 . 智能化时代的物联网科技与产业发展分析及策略 [J ] . 物联网学报 , 2025 , 9 ( 03 ): 1 - 16 .

ZHU H B , YIN H . Analysis and strategies of IoT technology and industrial development in the intelligent era [J ] . Chinese Journal on Internet of Things , 2025 , 9 ( 03 ): 1 - 16 .

MA J , WANG G , ZHANG L , et al . Restoration and enhancement on low exposure raw images by joint demosaicing and denoising [J ] . Neural Networks , 2023 , 162 : 557 - 570 .

TYO J S . Optimum linear combination strategy for an N-channel polarization-sensitive imaging or vision system [J ] . Journal of the Optical Society of America A , 1998 , 15 ( 2 ): 359 - 366 .

TYO J S . Design of optimal polarimeters: maximization of signal-to-noise ratio and minimization of systematic error [J ] . Applied optics , 2002 , 41 ( 4 ): 619 - 630 .

ADAM K D P B J . A method for stochastic optimization [J ] . arXiv preprint arXiv:1412.6980, 2014 , 1412 ( 6 ).

CAO Y , YANG M Y , TISSE C L . Effective strip noise removal for low-textured infrared images based on 1-D guided filtering [J ] . IEEE transactions on circuits and systems for video technology , 2015 , 26 ( 12 ): 2176 - 2188 .

MAKITALO M , FOI A . Optimal inversion of the generalized Anscombe transformation for Poisson-Gaussian noise [J ] . IEEE transactions on image processing , 2012 , 22 ( 1 ): 91 - 103 .

LI N , LE T B , BOFFETY M , et al . No-reference physics-based quality assessment of polarization images and its application to demosaicking [J ] . IEEE Transactions on Image Processing , 2021 , 30 : 8983 - 8998 .

ZHANG Y , SUN W , CHEN Z . Joint image demosaicking and denoising with mutual guidance of color channels [J ] . Signal Processing , 2022 , 200 : 108674 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on time series generation and anomaly detection model based on variational autoencoder

Intent-driven dual-time-scale resource allocation approach for Internet of things

Research on low-latency transmission migration method for federated learning models in the Internet of vehicles

IoT application development and generation: from low-code to AI-native

AI-assisted ransomware：operating principles and defense methods

Related Author

No data

Related Institution

No data

⁰