Article
Engineering, Electrical & Electronic
Yanfa Xiang, Xu Yang, Qiming Ren, Guochen Wang, Jie Gao, Khian-Hooi Chew, Rui-Pin Chen
Summary: This paper proposes a method for underwater image restoration using deep learning technology. By training and testing different polarization component images and considering the physical model of polarization dehazing imaging, it achieves high-quality restoration of hazy images.
IEEE PHOTONICS JOURNAL
(2022)
Review
Environmental Sciences
Xiaobo Li, Lei Yan, Pengfei Qi, Liping Zhang, Francois Goudail, Tiegen Liu, Jingsheng Zhai, Haofeng Hu
Summary: Polarimetric imaging (PI) techniques have significant advantages in various fields, and deep learning (DL) has been successfully combined with PI to provide new solutions for image restoration, object detection, image fusion, scene classification, and resolution improvement tasks. This review introduces the relevant concepts and models of PI and DL, and covers the state-of-the-art works combining PI with DL algorithms, as well as recommends potential future research directions.
Article
Optics
Pengfei Qi, Xiaobo Li, Yilin Han, Liping Zhang, Jianuo Xu, Zhenzhou Cheng, Tiegen Liu, Jingsheng Zhai, Haofeng Hu
Summary: Unsupervised polarimetric generative adversarial network (UR)-R-2-pGAN is proposed for unpaired underwater-image recovery. The method overcomes the reliance on strictly paired images in traditional learning-based methods and significantly improves restoration performance. The inclusion of polarization losses in the network enhances details restoration. Imaging experiments conducted under varying turbidity with different objects and viewing conditions demonstrate an average improvement of 3.4 dB in peak signal to noise ratio. The new method can be readily applied to practical underwater applications.
OPTICS AND LASERS IN ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Gao Huang, Zhuang Liu, Geoff Pleiss, Laurens van der Maaten, Kilian Q. Weinberger
Summary: Recent work has shown that adding shorter connections in convolutional networks can make the network deeper, more accurate, and more efficient in training. This paper introduces Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward manner. DenseNets alleviate the vanishing-gradient problem, encourage feature reuse, and improve parameter efficiency, leading to significant improvements in object recognition tasks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Optics
Haofeng Hu, Huifeng Jin, Hedong Liu, Xiaobo Li, Zhenzhou Cheng, Tiegen Liu, Jingsheng Zhai
Summary: In this paper, a deep transfer learning-based solution for polarimetric image denoising is proposed. By fine-tuning a denoising model pre-trained on a large-scale color image dataset and using a small-scale polarimetric dataset, the proposed network achieves almost the same denoising performance as that with a large-scale dataset. The method also demonstrates good generalization ability for different materials and noise levels.
OPTICS AND LASER TECHNOLOGY
(2023)
Article
Geochemistry & Geophysics
Hossein Aghababaei, Giampaolo Ferraioli, Alfred Stein, Sergio Vitale
Summary: Synthetic Aperture Radar (SAR) systems can have different polarimetric modalities, but most spaceborne SAR systems use dual-polarimetric data to capture more information about the Earth's surface and cover a wider area. This article proposes a new framework that uses deep learning to reconstruct fully polarimetric information from typical dual-pol data without relying on model assumptions. Experimental results show that the proposed framework outperforms traditional reconstruction methods and the reconstructed pseudo-fully polarimetric data closely matches actual fully polarimetric images acquired by radar systems, confirming the reliability and effectiveness of the proposed method.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Chemistry, Multidisciplinary
Fei Liu, Xuan Li, Pingli Han, Xiaopeng Shao
Summary: A CP imaging method combined with multi-scale analysis in the frequency domain is proposed in this study to enhance vision in rainy conditions by utilizing the CP characteristics of light. The method successfully removes the water spray effect and improves the quality of degraded rainy-day images.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Yongzhi Long, Haitao Jia, Yida Zhong, Yadong Jiang, Yuming Jia
Summary: This study introduces a novel unsupervised network called RXDNFuse for infrared/visible light fusion task, utilizing a combination of ResNeXt and DenseNet structures. The method automatically estimates information preservation levels and incorporates loss function strategies for network parameter training, improving quality of detailed information. The results demonstrate effective preservation of textural details and thermal radiation information, aligning well with human visual perception system.
INFORMATION FUSION
(2021)
Article
Engineering, Electrical & Electronic
Xinyu Zhang, Zichen Wang, Rong Fu, Di Wang, Xiaoyan Chen, Xiaoyong Guo, Huaxiang Wang
Summary: In this article, a supervised deep convolutional neural network (CNN)-V-shaped dense denoising net (VDD-Net) is proposed for electrical impedance tomography (EIT) to generate reliable reconstruction images. The performance of VDD-Net is compared with other methods, and the reconstruction quality is quantitatively measured using various metrics.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Optics
Yufeng Wu, Jiachen Wu, Shangzhong Jin, Liangcai Cao, Guofan Jin
Summary: Digital holographic imaging reconstructs phase and 3D information from a 2D lensless hologram using a Dense-U net, with a Dense_Block design enhancing the traditional U-net model to achieve full particle characterization. The network training is accomplished with fewer parameters and faster speeds using a specially designed dense connection module.
OPTICS COMMUNICATIONS
(2021)
Article
Optics
Xueyan Ding, Yafei Wang, Xianping Fu
Summary: This paper proposes a learning-based method for clear underwater color polarization imaging. By using multi-polarization fusion adversarial generative networks, the method learns the relationship between polarization information and object radiance. Experimental results show that the proposed method can effectively remove backscattered light and recover object radiance.
OPTICS AND LASERS IN ENGINEERING
(2022)
Article
Optics
Jian Liang, Liyong Ren, Rongguang Liang
Summary: The polarimetric dehazing method shows promise in enhancing image quality in scattering media, but is sensitive to noise, requiring digital image processing algorithms for stability. A novel method utilizing a low pass filter was proposed in this paper to effectively handle dense haze.
Article
Computer Science, Artificial Intelligence
Lun Zhang, Junhua Zhang
Summary: This article introduces a generative adversarial network structure (GAN-RW) that uses residual dense connectivity and weighted joint loss to improve the limitations of traditional image denoising algorithms, achieving advanced performance in ultrasound image denoising.
PEERJ COMPUTER SCIENCE
(2022)
Article
Engineering, Biomedical
Jinming Li, Chen Xi, Houjiao Dai, Jing Wang, Yang Lv, Puming Zhang, Jun Zhao
Summary: In this study, a new unsupervised learning method was developed to improve lesion detectability in patient studies. The deep progressive learning strategy was applied to bridge the gap between the input image and the target image. The results showed significant improvements in image noise performance and lesion detectability.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
Article
Geochemistry & Geophysics
Sheng-Jie Liu, Haowen Luo, Qian Shi
Summary: This study introduces an active ensemble deep learning (AEDL) approach for PolSAR image classification, utilizing active learning and multiview learning to evaluate the informativeness of unlabeled instances. The proposed AEDL outperformed standard active learning strategies by leveraging snapshot committee from deep learning models and achieved better performance on PolSAR image classification tasks with limited training samples.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Qing Jia, Qun Han, Zhizhuang Liang, Zhenzhou Cheng, Haofeng Hu, Shuang Wang, Kun Ren, Junfeng Jiang, Tiegen Liu
Summary: A temperature compensation method for fiber current sensors is proposed and experimentally demonstrated in this paper. By introducing a static bias and measuring rotation angles, temperature compensation can effectively reduce the sensor's relative error to an acceptable range.
IEEE SENSORS JOURNAL
(2022)
Article
Physics, Applied
Weicheng Chen, Jingwen Wu, Dian Wan, Jie Wang, Jiaqi Wang, Yi Zou, Zhenzhou Cheng, Tiegen Liu
Summary: The study demonstrated high coupling efficiency and bandwidth of subwavelength grating couplers in the spectral range of 2.2-2.5 μm. Reproducibility of fabricated grating couplers and design and fiber coupling tolerance were also investigated in the study.
JOURNAL OF PHYSICS D-APPLIED PHYSICS
(2022)
Article
Optics
Rongxiang Guo, Haoran Gao, Tiegen Liu, Zhenzhou Cheng
Summary: This study demonstrates an ultra-thin focusing subwavelength-grating coupler for mid-IR ultra-thin suspended subwavelength-grating-cladding waveguide coupling. The results show high coupling efficiency and fiber alignment tolerance, paving the way for the development of mid-IR ultra-thin photonic integrated circuits.
Article
Engineering, Electrical & Electronic
Rongxiang Guo, Weicheng Chen, Haoran Gao, Yang Zhao, Tiegen Liu, Zhenzhou Cheng
Summary: This study proposes the feasibility of developing mid-infrared Ge-based Kerr frequency combs, and analyzes their physical properties and generation mechanisms by establishing a comprehensive model. The study also demonstrates the conditions for generating frequency combs at specific pump wavelengths. This research provides useful guidance for the development of mid-IR Kerr frequency combs using CMOS technology.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2022)
Article
Optics
Hedong Liu, Yizhu Zhang, Zhenzhou Cheng, Jingsheng Zhai, Haofeng Hu
Summary: This Letter introduces an attention-based neural network for polarimetric image denoising, showing superior performance in restoring image details.
Article
Engineering, Electrical & Electronic
Jiaqi Wang, Zhiwei Wei, Huabin Qiu, Zhengkun Xing, Yuzhi Chen, Youfu Geng, Yu Du, Xuejin Li, Zhenzhou Cheng
Summary: This study investigates the influence of UV-light irradiation on silicon photonic devices by probing the resonant wavelength shifts of a racetrack microring resonator. The experimental results show that the resonator exhibits temporary variations in the resonant wavelength and has a recovery time under different UV-light exposure durations. The study comprehensively analyzes and compares the refractive index changes induced by plasmon dispersion effect, thermal optical effect, and photon-induced silica densification effect, providing useful guidelines for in-situ silicon photonic testing and packaging.
IEEE PHOTONICS JOURNAL
(2022)
Article
Optics
Haoran Gao, Rongxiang Guo, Shujiao Zhang, Chunzhen Lin, Tiegen Liu, Zhenzhou Cheng
Summary: Mid-infrared (Mid-IR) silicon photonics has great potential in various applications. However, polarization-dependent losses have been a challenge in mid-IR grating couplers. This study presents an ultra-thin mid-IR polarization-insensitive grating coupler with improved coupling efficiency and reduced polarization-dependent loss, providing a promising solution for the development of mid-IR photonic integrated circuits.
Article
Engineering, Electrical & Electronic
Zhizhuang Liang, Qun Han, Teng Zhang, Yuliang Tang, Junfeng Jiang, Zhenzhou Cheng
Summary: By analyzing the nonlinearity originations, temperature dependency, and magnetic domain variations in a FOCS, this article develops a method utilizing a neural network and optimization algorithm to compensate for these factors, resulting in a significant reduction in relative error and meeting accuracy requirements.
IEEE SENSORS JOURNAL
(2022)
Article
Optics
Rongxiang Guo, Shujiao Zhang, Haoran Gao, Ganapathy Senthil Murugan, Tiegen Liu, Zhenzhou Cheng
Summary: Short-wavelength mid-infrared silicon photonics has been growing for applications in free-space optical communications, laser ranging, and biochemical sensing. However, grating couplers at 2-2.5 μm wavelengths still have low efficiencies due to moderated directionality and poor diffraction-field tailoring capability. In this study, a blazed subwavelength coupler was developed to improve light coupling efficiency, bandwidth, and tolerance.
PHOTONICS RESEARCH
(2023)
Article
Optics
Weicheng Chen, Dian Wan, Qi He, Jiaqi Wang, Haofeng Hu, Tiegen Liu, Hon Ki Tsang, Zhenzhou Cheng
Summary: Short-wavelength mid-infrared (MIR) silicon photonics has various applications in optical communications, chemical analysis, and environmental monitoring. In this study, a relaxed-tolerance subwavelength grating (SWG) coupler design with dual-hole structures was demonstrated to overcome fabrication variations and improve reproducibility. The relaxed-tolerance SWG coupler achieved a peak coupling efficiency of -6.2 dB at a wavelength of 2.038 μm with a 1-dB bandwidth of about 30 nm.
OPTICS AND LASER TECHNOLOGY
(2023)
Article
Optics
Qi He, Senmiao Han, Weicheng Chen, Haofeng Hu, Tiegen Liu, Zhenzhou Cheng
Summary: Mid-infrared (Mid-IR) silicon photonics has gained significant attention in the development of chip-integrated molecular sensors. Microring resonators (MRRs) with high-quality factors, reproducibility in fabrication, and compact footprints are useful for sensing purposes. However, the limited availability and high cost of mid-IR equipment, such as tunable lasers or spectrometers, hinder the applications of MRR-based sensors. In this study, we propose a theoretical approach to overcome this limitation by using an MRR-based nitrogen dioxide gas sensor that utilizes a monochromatic mid-IR laser. Additionally, graphene is employed as a sensitizing medium to modify the phase of the propagating light in the silicon waveguide after gas molecule adsorption. The proposed sensor achieves a theoretical sensitivity of 1.259 x 10-5 RIU/ppm, a limit of detection of 5.1 ppm, and a detection range of 5135 ppm. This research is expected to pave the way for the development of chip-integrated, low-cost, and highly sensitive optical gas sensors.
OPTICS COMMUNICATIONS
(2023)
Article
Optics
Haofeng Hu, Shiyao Yang, Xiaobo LI, Zhenzhou Cheng, Tiegen Liu, Jingsheng Zhai
Summary: Reduced resolution of polarized images hinders the distinction of fine polarization information and the identification of small targets and weak signals. To address this problem, this paper proposes a deep convolutional neural network based polarization super-resolution reconstruction method, which is proven to outperform other methods in terms of quantitative and visual evaluation.
Article
Optics
Haofeng Hu, Huifeng Jin, Hedong Liu, Xiaobo Li, Zhenzhou Cheng, Tiegen Liu, Jingsheng Zhai
Summary: In this paper, a deep transfer learning-based solution for polarimetric image denoising is proposed. By fine-tuning a denoising model pre-trained on a large-scale color image dataset and using a small-scale polarimetric dataset, the proposed network achieves almost the same denoising performance as that with a large-scale dataset. The method also demonstrates good generalization ability for different materials and noise levels.
OPTICS AND LASER TECHNOLOGY
(2023)
Article
Optics
Hedong Liu, Xiaobo Li, Zhenzhou Cheng, Tiegen Liu, Jingsheng Zhai, Haofeng Hu
Summary: In this Letter, a self-supervised method called polarization to polarization (Pol2Pol) is introduced for polarimetric image denoising using only one-shot noisy images. A polarization generator is proposed to synthesize training image pairs from the one-shot noisy images by exploiting polarization relationships. The Pol2Pol method is extensible and compatible, allowing the deployment of any network that performs well in supervised image denoising tasks with proper modifications. Experimental results demonstrate that Pol2Pol outperforms other self-supervised methods and achieves comparable performance to supervised methods.
Article
Engineering, Electrical & Electronic
Hedong Liu, Xiaobo Li, Zhenzhou Cheng, Tiegen Liu, Jingsheng Zhai, Haofeng Hu
Summary: Color polarimetric imaging provides multidimensional information for object properties and has various applications. However, polarimetric images have lower SNR and are more sensitive to noise than conventional color images, leading to noisy images and degraded polarization analysis. In this article, a 3-D CNN is proposed to denoise color polarimetric images by utilizing the coherence among space, color, and polarization. Experiments show that this method effectively removes noise and restores polarization information, suggesting potential applications in multidimensional imaging tasks.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Optics
Yin Xiao, Lina Zhou, Wen Chen
Summary: This paper introduces a correspondence imaging approach for reconstructing high-quality objects through complex scattering media. By deriving a rectified theory and introducing temporal correction, the proposed method eliminates the effect of dynamic scaling factors. Experimental results demonstrate the advantages of the proposed method over conventional methods in complex scattering environments, and it can also be combined with other methods to further enhance the quality of reconstructed objects.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Zengxuan Jiang, Minghao Chao, Qingsong Liu, Bo Cheng, Guofeng Song, Jietao Liu
Summary: In this paper, a multi-focal metalens with high focusing efficiency controlled by circular polarization multiplexing is demonstrated. The metalens can generate four transversely distributed focal points under normal incidence of linearly polarized light, supporting both left-circularly polarized and right-circularly polarized conversion. Furthermore, an oblique incidence metalens is designed to achieve high total focusing efficiency for terahertz waves and provides potential new applications for polarization imaging and detection.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Yiran Wang, Yu Ji, Xuyang Zhou, Xiu Wen, Yutong Li, Zhengjun Liu, Shutian Liu
Summary: This work presents a new reconstruction framework for structured illumination microscopy (SIM), which only requires four raw images and avoids extensive iterative computation. By using checkerboard pattern illumination modulation instead of sinusoidal fringe illumination, the proposed method significantly reduces image acquisition time and achieves higher image reconstruction rate. Additionally, the reconstruction process is non-iterative and not limited by the field of view size.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Qian He, Li Pei, Jianshuai Wang, Jingjing Zheng, Tigang Ning, Jing Li
Summary: This paper proposes a 3D refractive index profile visualization method to demonstrate mode activation and evolution in fiber fusion splicing. The method is validated through experimental results and provides support for various fiber splicing operations and mode coupling modulation.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Qiwei Li, Qiyu Wang, Fang Lu, Yang Cao, Xu Zhao
Summary: LSHIP is a lenslet-array-based snapshot hyperspectral imaging polarimeter that combines spectral polarization modulation with integral field imaging spectrometry. It can simultaneously acquire three-dimensional spatial and spectral data-cubes for linear Stokes parameters in a single snapshot.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Huicong Li, Bing Lv, Meng Tian, Wenzhu Huang, Wentao Zhang
Summary: This study proposes a temperature compensation scheme for unbalanced interferometers using sensing fibers with different temperature coefficients, aiming to resolve the temperature disturbance and achieve high strain resolution. The experimental results confirm the effectiveness of the proposed scheme in high-resolution, long-term, low-frequency, and static strain sensing.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Hongxiang Chang, Rongtao Su, Yuqiu Zhang, Bowang Shu, Jinhu Long, Jinyong Leng, Pu Zhou
Summary: High-speed variable-focus optics provides new opportunities for fiber laser applications in various fields. This paper investigates a non-mechanical axial focus tuning method using coherent beam combining (CBC) technique and proposes a tilt modulation assisted method to extend the tuning range.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Yubo Ni, Shuai Fu, Chaoyang Su, Zhaozong Meng, Nan Gao, Zonghua Zhang
Summary: This paper proposes a surface adaptive fringe pattern generation method to accurately measure specular surfaces, eliminating the out-of-focus effect and improving measurement accuracy and reliability.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Zifan Wang, Tianfeng Zhou, Qian Yu, Zihao Zeng, Xibin Wang, Junjian Hu, Jiyong Zeng
Summary: Fast-axis collimation (FAC) lens arrays are crucial in laser systems, and their precision can be improved through the development of an optical collimation system and the use of thermal compensation to correct for non-uniform thermal expansion.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Jincheng Chen, Qiuyu Fang, Li Huang, Xin Ye, Luhong Jin, Heng Zhang, Yinqian Luo, Min Zhu, Luhao Zhang, Baohua Ji, Xiang Tian, Yingke Xu
Summary: This study developed a novel deep learning accelerated SRRF method that enables super-resolution reconstruction with only 5 low SNR images, and allows real-time visualization of microtubule dynamics and interactions with CCPs.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Pan Liu, Yongqiang Zhao, Ning Li, Kai Feng, Seong G. Kong, Chaolong Tang
Summary: This article presents a technique for inverse design of multilayer deep-etched gratings (MDEG) using a deep neural network with adaptive solution space. The proposed method trains a deep neural network to predict the probability distribution across the discretized space, enabling evaluation of an optimal solution. The results show improved efficiencies using only a reduced dataset and avoiding one-to-many mapping challenges.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Evelina Bibikova, Nazar Al-wassiti, Nataliya Kundikova
Summary: Light beams possess three types of angular momentum, namely spin angular momentum, extrinsic orbital angular momentum, and intrinsic orbital angular momentum. The interaction between these momenta leads to the spin-orbit interaction of light and topological effects. This study predicts a new topological effect resulting from the influence of extrinsic orbital angular momentum on spin angular momentum in converging asymmetrical light beams. It manifests as the transformation of linear polarized light into elliptically polarized light when an asymmetrical beam passes through the left or right half of the focal plane. The measured value of the topological circular amplitude anisotropy R was found to be R = +/- (0.60 +/- 0.08) x 10(-3). This new effect contributes to our understanding of light and has potential applications in developing sensors in optics.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Hamdy H. Wahba
Summary: This study combines multiple-beam Fizeau interference and single-shot digital holographic interferometry to study thick phase objects. By collecting optical phase at different focal planes, the angular spectrum method is used for the first time to retrieve optical phase maps through the focal depth. The proposed method proves to be effective in providing accurate numerical focusing and phase maps reconstruction.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Mohammed A. Isa, Richard Leach, David Branson, Samanta Piano
Summary: Due to the complexity of resolving object form and pose in images, new vision algorithms prioritize identification and perception over accurate coordinate measurement. However, the use of planar targets for coordinate measurement in vision systems has several drawbacks, including calibration difficulties and limited viewing angles. On the other hand, the use of sphere targets is infrequent in vision-based coordinate metrology due to the lack of efficient multi-view vision algorithms for accurate sphere measurements.
OPTICS AND LASERS IN ENGINEERING
(2024)
Article
Optics
Ildar Rakhmatulin, Donald Risbridger, Richard M. Carter, M. J. Daniel Esser, Mustafa Suphi Erden
Summary: This paper reviews the application of machine learning in laser systems. While machine learning has been widely used in general control automation and adjustment tasks, its application in specific tasks requiring skilled workforces for high-precision equipment assembly and adjustment is still limited. The paper presents promising research directions for using machine learning in mirror positional adjustment, triangulation, and optimal laser parameter selection, based on the recommendations of PRISMA.
OPTICS AND LASERS IN ENGINEERING
(2024)
