Zhengyi Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhengyi Chen has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Yifan He
School of Physics and the Institute of Space Optics, Xian Jiaotong University, Xian, China
4 shared publications Biyun Zhang
BA Trade Company Ltd., Guangzhou, China
3 shared publicationsChunmin Zhang
School of Physics and the Institute of Space Optics, Xian Jiaotong University, Xian, China
3 shared publications- Tingkui Mu
MOE Key Laboratory for Non‐equilibrium Synthesis and Modulation of Condensed Matter, School of Physics Xi'an Jiaotong University Xi'an Shaanxi 710049 P. R. China
2 shared publications - Chunmin Zhang
Xi’an Jiaotong University
1 shared publication - Qian Tang
School of Physics and the Institute of Space Optics, Xi’an Jiaotong University, Xi’an, China
1 shared publication
Latest Publications
- Open Access
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 1435-1450
Passive Observation of Martian Atmosphere Using O2(a 1Δ g ) Airglow Radiation: Forward Simulation and Wind Retrieval
The passive monitoring of Martian wind fields is crucial for deciphering the Martian atmosphere. With the 3 strong spectral lines in the 1.27 μm O 2 ( a 1 Δ g ) airglow emission band, this article designs the Martian Static Wind Imaging Michelson Interferometer (M-SWIMI) to measure the atmospheric profiles within the altitude range of 10–50 km. Specifically, a forward model to simulate the entire process from the emission transmission through the Martian atmosphere to the eventual formation of the images observed by the instrument is developed. In addition, a robust retrieval algorithm with the bidirectional smoothing (BS) regularization and the multispectral consistency (MC) constraint is proposed. The BSMC algorithm leverages the smoothness of atmospheric parameters in both horizontal and vertical directions and exploits the inherent correlations among different spectral lines, ensuring the accuracy of Volume Emission Rates (VER), temperature and wind. Experimental results demonstrate the superior noise robustness of the retrieval algorithm, supported by comprehensive ablation studies and performance assessments under various noise scenarios, thereby validating the efficacy of the proposed approach in the study of Martian atmospheric dynamics.
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 1435-1450
Open AccessPassive Observation of Martian Atmosphere Using O2(a 1Δ g ) Airglow Radiation: Forward Simulation and Wind Retrieval
The passive monitoring of Martian wind fields is crucial for deciphering the Martian atmosphere. With the 3 strong spectral lines in the 1.27 μm O 2 ( a 1 Δ g ) airglow emission band, this article designs the Martian Static Wind Imaging Michelson Interferometer (M-SWIMI) to measure the atmospheric profiles within the altitude range of 10–50 km. Specifically, a forward model to simulate the entire process from the emission transmission through the Martian atmosphere to the eventual formation of the images observed by the instrument is developed. In addition, a robust retrieval algorithm with the bidirectional smoothing (BS) regularization and the multispectral consistency (MC) constraint is proposed. The BSMC algorithm leverages the smoothness of atmospheric parameters in both horizontal and vertical directions and exploits the inherent correlations among different spectral lines, ensuring the accuracy of Volume Emission Rates (VER), temperature and wind. Experimental results demonstrate the superior noise robustness of the retrieval algorithm, supported by comprehensive ablation studies and performance assessments under various noise scenarios, thereby validating the efficacy of the proposed approach in the study of Martian atmospheric dynamics.
- 15 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Triplet Contrastive Learning Framework With Adversarial Hard-Negative Sample Generation for Multimodal Remote Sensing Images
Supervised learning models have achieved remarkable success in the field of remote sensing, but their applicability is limited by the significant requirement of high-quality labeled data. This article presents the triplet adversarial contrastive learning (TACL) model, as a self-supervised feature extractor. Considering the potential contrastive semantic conflicts, which may occur due to the different descriptive abilities of various modalities, TACL constructs a triplet contrastive learning framework aligning the two original modalities and a fused modality. To augment the acquired representations of the model, TACL introduces an adversarial hard-negative sample generation (AHSG) strategy, aiming to boost the resemblance between the feature vectors of negative samples and anchors. In addition, a ConvNeXt-based lightweight encoder is designed as the foundational backbone of the model, specifically enriching the expression of central features. A series of few-shot classification experiments substantiate the exceptional performance of the features extracted by TACL, with the simplistic classifier support vector machine (SVM). As a label-free pretraining approach, TACL holds great potential for enhancing the performance of various multimodal remote sensing tasks in scenarios with limited label availability.
- 15 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Triplet Contrastive Learning Framework With Adversarial Hard-Negative Sample Generation for Multimodal Remote Sensing Images
Supervised learning models have achieved remarkable success in the field of remote sensing, but their applicability is limited by the significant requirement of high-quality labeled data. This article presents the triplet adversarial contrastive learning (TACL) model, as a self-supervised feature extractor. Considering the potential contrastive semantic conflicts, which may occur due to the different descriptive abilities of various modalities, TACL constructs a triplet contrastive learning framework aligning the two original modalities and a fused modality. To augment the acquired representations of the model, TACL introduces an adversarial hard-negative sample generation (AHSG) strategy, aiming to boost the resemblance between the feature vectors of negative samples and anchors. In addition, a ConvNeXt-based lightweight encoder is designed as the foundational backbone of the model, specifically enriching the expression of central features. A series of few-shot classification experiments substantiate the exceptional performance of the features extracted by TACL, with the simplistic classifier support vector machine (SVM). As a label-free pretraining approach, TACL holds great potential for enhancing the performance of various multimodal remote sensing tasks in scenarios with limited label availability.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
FSPnP: Plug-and-Play Frequency–Spatial-Domain Hybrid Denoiser for Thermal Infrared Image
Maritime thermal infrared (IR) imaging is susceptible to various types of mixed noise interference, such as Gaussian, stripe, and internal stray radiation noise, due to atmospheric radiation and complex dynamic backgrounds. These factors directly hinder subsequent image processing applications such as target detection and tracking. In this paper, we propose a hybrid denoising model based on a model reconstruction framework to jointly address non-uniformity issues in single-frame thermal IR images. Stripe noise, due to its directional nature, exhibits distinct physical characteristics in both the spatial and frequency domains. Most existing methods rely on designing prior constraints based on features from only one domain. To adapt to diverse stripe distribution patterns, we introduce spatial priors for stripes in the hybrid denoising model, concurrently pioneering the introduction of frequency domain priors in a plug-and-play technology for the first time. This approach facilitates mutual enhancement of multi-domain characteristic constraints in stripe removal. Furthermore, we employ polynomial fitting to characterize the distribution of internal stray radiation noise, which possesses global smoothness characteristics. The hybrid model effectively mitigates the impact of stripe distribution on the smoothing correction. Experiments demonstrate the effectiveness and superior performance of the proposed hybrid model in addressing mixed noise. Furthermore, we degraded the hybrid model into a de-striping model and demonstrated its outstanding performance in the standalone de-striping task. The proposed method can provide valuable references for the restoration of thermal IR or hyperspectral remote sensing images, and offer additional information for IR target detection and tracking tasks.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
FSPnP: Plug-and-Play Frequency–Spatial-Domain Hybrid Denoiser for Thermal Infrared Image
Maritime thermal infrared (IR) imaging is susceptible to various types of mixed noise interference, such as Gaussian, stripe, and internal stray radiation noise, due to atmospheric radiation and complex dynamic backgrounds. These factors directly hinder subsequent image processing applications such as target detection and tracking. In this paper, we propose a hybrid denoising model based on a model reconstruction framework to jointly address non-uniformity issues in single-frame thermal IR images. Stripe noise, due to its directional nature, exhibits distinct physical characteristics in both the spatial and frequency domains. Most existing methods rely on designing prior constraints based on features from only one domain. To adapt to diverse stripe distribution patterns, we introduce spatial priors for stripes in the hybrid denoising model, concurrently pioneering the introduction of frequency domain priors in a plug-and-play technology for the first time. This approach facilitates mutual enhancement of multi-domain characteristic constraints in stripe removal. Furthermore, we employ polynomial fitting to characterize the distribution of internal stray radiation noise, which possesses global smoothness characteristics. The hybrid model effectively mitigates the impact of stripe distribution on the smoothing correction. Experiments demonstrate the effectiveness and superior performance of the proposed hybrid model in addressing mixed noise. Furthermore, we degraded the hybrid model into a de-striping model and demonstrated its outstanding performance in the standalone de-striping task. The proposed method can provide valuable references for the restoration of thermal IR or hyperspectral remote sensing images, and offer additional information for IR target detection and tracking tasks.
- 13 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-13
Tensorial Multiview Subspace Clustering for Polarimetric Hyperspectral Images
Polarimetric hyperspectral images (PHSIs) can provide complementary representations of a scene from the perspectives of images, spectra, and polarization at the same time and are expected to improve the quality of scene description. In this article, the clustering for PHSI is deemed to be a multiview clustering task, and a tensorial polarimetric-spectral multiview subspace clustering (TPS-MSC) algorithm for PHSI is proposed. It constructs a small size dictionary, instead of a large self-representative dictionary, by pre-clustering each view independently to give a sparse representation of all the data. Then, the view-specific representation matrices are tensorized to explore the low-rank structure among different views, and the consistency of all views in pre-clustering is incorporated into the representation learning framework to strengthen the interview correlations. The proposed model is efficiently optimized by the alternative direction minimization of multipliers (ADMM) algorithm. Some experiments are carried out to validate the capacity of PHSI for target identification and to demonstrate the accuracy and efficiency of the proposed TPS-MSC algorithm.
- 13 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-13
Tensorial Multiview Subspace Clustering for Polarimetric Hyperspectral Images
Polarimetric hyperspectral images (PHSIs) can provide complementary representations of a scene from the perspectives of images, spectra, and polarization at the same time and are expected to improve the quality of scene description. In this article, the clustering for PHSI is deemed to be a multiview clustering task, and a tensorial polarimetric-spectral multiview subspace clustering (TPS-MSC) algorithm for PHSI is proposed. It constructs a small size dictionary, instead of a large self-representative dictionary, by pre-clustering each view independently to give a sparse representation of all the data. Then, the view-specific representation matrices are tensorized to explore the low-rank structure among different views, and the consistency of all views in pre-clustering is incorporated into the representation learning framework to strengthen the interview correlations. The proposed model is efficiently optimized by the alternative direction minimization of multipliers (ADMM) algorithm. Some experiments are carried out to validate the capacity of PHSI for target identification and to demonstrate the accuracy and efficiency of the proposed TPS-MSC algorithm.
- 15 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-14
Infrared Small Target Detection via Interpatch Correlation Enhancement and Joint Local Visual Saliency Prior
Small target detection is the primary technology for infrared search and tracking (IRST) systems and plays a vital role in practical applications. Existing algorithms have the following challenges: 1) insufficient local and nonlocal feature extraction and 2) imbalance between accuracy and real-time detection performance. In this study, a novel model for fast detection based on interpatch correlation enhancement (IPCE) and joint local visual saliency prior is proposed to overcome such issues. Regarding the correlation in interpatch dimension, the improved tensor nuclear norm is used to further extract the low-rank structure of the background tensor, which fully exploits the low-rank component and reduces the iteration times. Furthermore, with the hypothesis that the target is locally saliency, a prior model based on the visual saliency mechanism is proposed as the constraint of the target tensor. It effectively reduces the false detection of the sparse edge structure. In general, the proposed IPCE jointly exploits both local and nonlocal correlation of the original image, achieving robustness in different scenarios. Finally, the proposed model is solved by the alternating direction method of multipliers (ADMM). Experiments on seven datasets demonstrate that IPCE outperforms the state of the arts in terms of the balance between detection efficiency and accuracy.
- 15 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-14
Infrared Small Target Detection via Interpatch Correlation Enhancement and Joint Local Visual Saliency Prior
Small target detection is the primary technology for infrared search and tracking (IRST) systems and plays a vital role in practical applications. Existing algorithms have the following challenges: 1) insufficient local and nonlocal feature extraction and 2) imbalance between accuracy and real-time detection performance. In this study, a novel model for fast detection based on interpatch correlation enhancement (IPCE) and joint local visual saliency prior is proposed to overcome such issues. Regarding the correlation in interpatch dimension, the improved tensor nuclear norm is used to further extract the low-rank structure of the background tensor, which fully exploits the low-rank component and reduces the iteration times. Furthermore, with the hypothesis that the target is locally saliency, a prior model based on the visual saliency mechanism is proposed as the constraint of the target tensor. It effectively reduces the false detection of the sparse edge structure. In general, the proposed IPCE jointly exploits both local and nonlocal correlation of the original image, achieving robustness in different scenarios. Finally, the proposed model is solved by the alternating direction method of multipliers (ADMM). Experiments on seven datasets demonstrate that IPCE outperforms the state of the arts in terms of the balance between detection efficiency and accuracy.