Yongchao Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yongchao Zhao has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Luyan Ji
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
3 shared publications - Haoran Jiang
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2 shared publications - Guangyao Zhou
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication - Hong Guan
UTAN Technology Co., Ltd., Hangzhou 310012, China
1 shared publication - Hongsheng Zhang
Department of Geography, The University of Hong Kong
1 shared publication - Huixian Wang
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication
Latest Publications
- Open Access
- 22 December 2025
- Published by MDPI AG in Remote Sensing
- Vol. 18 (1) , 27
Shift-Invariant Unsupervised Pansharpening Based on Diffusion Model
Pansharpening is a crucial topic in remote sensing, and numerous deep learning-based methods have recently been proposed to explore the potential of deep neural networks (DNNs). However, existing approaches are often sensitive to spatial translation errors between high-resolution panchromatic (HRPan) and low-resolution multispectral (LRMS) images, leading to noticeable artifacts in the fused results. To address this issue, we propose an unsupervised pansharpening method that is robust to translation misalignment between HRPan and LRMS inputs. The proposed framework integrates a shift-invariant module to estimate subpixel spatial offsets and a diffusion-based generative model to progressively enhance spatial and spectral details. Moreover, a multi-scale detail injection module is designed to guide the diffusion process with fine-grained structural information. In addition, a carefully formulated loss function is established to preserve the fidelity of fusion results and facilitate the estimation of translation errors. Experiments conducted on the GaoFen-2, GaoFen-1, and WorldView-2 datasets demonstrate that the proposed method achieves superior fusion quality compared with state-of-the-art approaches and effectively suppresses artifacts caused by translation errors.
- 22 December 2025
- Published by MDPI AG in Remote Sensing
- Vol. 18 (1) , 27
Open AccessShift-Invariant Unsupervised Pansharpening Based on Diffusion Model
Pansharpening is a crucial topic in remote sensing, and numerous deep learning-based methods have recently been proposed to explore the potential of deep neural networks (DNNs). However, existing approaches are often sensitive to spatial translation errors between high-resolution panchromatic (HRPan) and low-resolution multispectral (LRMS) images, leading to noticeable artifacts in the fused results. To address this issue, we propose an unsupervised pansharpening method that is robust to translation misalignment between HRPan and LRMS inputs. The proposed framework integrates a shift-invariant module to estimate subpixel spatial offsets and a diffusion-based generative model to progressively enhance spatial and spectral details. Moreover, a multi-scale detail injection module is designed to guide the diffusion process with fine-grained structural information. In addition, a carefully formulated loss function is established to preserve the fidelity of fusion results and facilitate the estimation of translation errors. Experiments conducted on the GaoFen-2, GaoFen-1, and WorldView-2 datasets demonstrate that the proposed method achieves superior fusion quality compared with state-of-the-art approaches and effectively suppresses artifacts caused by translation errors.
- Open Access
- 18 December 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (24) , 4066
FANet: Frequency-Aware Attention-Based Tiny-Object Detection in Remote Sensing Images
In recent years, deep learning-based remote sensing object detection has achieved remarkable progress, yet the detection of tiny objects remains a significant challenge. Tiny objects in remote sensing images typically occupy only a few pixels, resulting in low contrast, poor resolution, and high sensitivity to localization errors. Their diverse scales and appearances, combined with complex backgrounds and severe class imbalance, further complicate the detection tasks. Conventional spatial feature extraction methods often struggle to capture the discriminative characteristics of tiny objects, especially in the presence of noise and occlusion. To address these challenges, we propose a frequency-aware attention-based tiny-object detection network with two plug-and-play modules that leverage frequency-domain information to enhance the targets. Specifically, we introduce a Multi-Scale Frequency Feature Enhancement Module (MSFFEM) to adaptively highlight the contour and texture details of tiny objects while suppressing background noise. Additionally, a Channel Attention-based RoI Enhancement Module (CAREM) is proposed to selectively emphasize high-frequency responses within RoI features, further improving object localization and classification. Furthermore, to mitigate sample imbalance, we employ multi-directional flip sample augmentation and redundancy filtering strategies, which significantly boost detection performance for few-shot categories. Extensive experiments on public object detection datasets, i.e., AI-TOD, VisDrone2019, and DOTA-v1.5, demonstrate that the proposed FANet consistently improves detection performance for tiny objects, outperforming existing methods and providing new insights into the integration of frequency-domain analysis and attention mechanisms for robust tiny-object detection in remote sensing applications.
- 18 December 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (24) , 4066
Open AccessFANet: Frequency-Aware Attention-Based Tiny-Object Detection in Remote Sensing Images
In recent years, deep learning-based remote sensing object detection has achieved remarkable progress, yet the detection of tiny objects remains a significant challenge. Tiny objects in remote sensing images typically occupy only a few pixels, resulting in low contrast, poor resolution, and high sensitivity to localization errors. Their diverse scales and appearances, combined with complex backgrounds and severe class imbalance, further complicate the detection tasks. Conventional spatial feature extraction methods often struggle to capture the discriminative characteristics of tiny objects, especially in the presence of noise and occlusion. To address these challenges, we propose a frequency-aware attention-based tiny-object detection network with two plug-and-play modules that leverage frequency-domain information to enhance the targets. Specifically, we introduce a Multi-Scale Frequency Feature Enhancement Module (MSFFEM) to adaptively highlight the contour and texture details of tiny objects while suppressing background noise. Additionally, a Channel Attention-based RoI Enhancement Module (CAREM) is proposed to selectively emphasize high-frequency responses within RoI features, further improving object localization and classification. Furthermore, to mitigate sample imbalance, we employ multi-directional flip sample augmentation and redundancy filtering strategies, which significantly boost detection performance for few-shot categories. Extensive experiments on public object detection datasets, i.e., AI-TOD, VisDrone2019, and DOTA-v1.5, demonstrate that the proposed FANet consistently improves detection performance for tiny objects, outperforming existing methods and providing new insights into the integration of frequency-domain analysis and attention mechanisms for robust tiny-object detection in remote sensing applications.
- Open Access
- 29 March 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (7) , 1223
A Mobile Triaxial Stabilized Ship-Borne Radiometric System for In Situ Measurements: Case Study of Sentinel-3 OLCI Validation in Highly Turbid Waters
This study presents the “Mobile Triaxial Stabilized Water-leaving Reflectance Measurement System” (MTS-WRMS), a ship-borne radiometric system designed for high-precision acquisition of water-leaving radiance (Lw) and remote sensing reflectance (Rrs) in mobile aquatic environments. The system employs a triaxial stabilized gimbal to maintain the orientation of three spectrometers, effectively mitigating angular deviations. The system also features automatic azimuth adjustment to maintain the relative sun-sensor azimuth angle within the optimal range of 90° ≤ φ ≤ 135° and supports long-range wireless telemetry for autonomous real-time monitoring. The system’s accuracy was validated through the “direct approach” experiments, which demonstrated low systematic bias, with a mean weighted absolute percentage deviation (WAPD) of 4.42% in the 440–720 nm range, which covers 90% of radiant energy. Additionally, ground validation involving 296 matched spectra from Gaoyou and Zhuhai revealed that Sentinel-3 A/B OLCI products tend to overestimate Rrs in highly turbid waters, with weighted percentage deviation (WPD) and WAPD values of about 16% and 31%, respectively. The overestimation was particularly pronounced in the 400–443 nm range, likely due to low Rrs and inadequate atmospheric correction. The MTS-WRMS provides an advanced tool for accurate, real-time Rrs measurements, offering valuable insights into temporal and spatial variations in water bodies.
- 29 March 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (7) , 1223
Open AccessA Mobile Triaxial Stabilized Ship-Borne Radiometric System for In Situ Measurements: Case Study of Sentinel-3 OLCI Validation in Highly Turbid Waters
This study presents the “Mobile Triaxial Stabilized Water-leaving Reflectance Measurement System” (MTS-WRMS), a ship-borne radiometric system designed for high-precision acquisition of water-leaving radiance (Lw) and remote sensing reflectance (Rrs) in mobile aquatic environments. The system employs a triaxial stabilized gimbal to maintain the orientation of three spectrometers, effectively mitigating angular deviations. The system also features automatic azimuth adjustment to maintain the relative sun-sensor azimuth angle within the optimal range of 90° ≤ φ ≤ 135° and supports long-range wireless telemetry for autonomous real-time monitoring. The system’s accuracy was validated through the “direct approach” experiments, which demonstrated low systematic bias, with a mean weighted absolute percentage deviation (WAPD) of 4.42% in the 440–720 nm range, which covers 90% of radiant energy. Additionally, ground validation involving 296 matched spectra from Gaoyou and Zhuhai revealed that Sentinel-3 A/B OLCI products tend to overestimate Rrs in highly turbid waters, with weighted percentage deviation (WPD) and WAPD values of about 16% and 31%, respectively. The overestimation was particularly pronounced in the 400–443 nm range, likely due to low Rrs and inadequate atmospheric correction. The MTS-WRMS provides an advanced tool for accurate, real-time Rrs measurements, offering valuable insights into temporal and spatial variations in water bodies.
- Open Access
- 9 November 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 135
Cloud probability distribution of typical urban agglomerations in China based on Sentinel-2 satellite remote sensing
- 9 November 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 135
Open AccessCloud probability distribution of typical urban agglomerations in China based on Sentinel-2 satellite remote sensing
- Open Access
- 18 February 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (4) , 711
Analysis of the Substantial Growth of Water Bodies during the Urbanization Process Using Landsat Imagery—A Case Study of the Lixiahe Region, China
In the process of urbanization, water bodies bear considerable anthropogenic pressure, resulting in a reduction of their surface area in most instances. Nevertheless, in contrast to many other regions, the Lixiahe region in Jiangsu Province, located in China’s eastern plain, has experienced a continuous expansion of water bodies over the past few decades amid rapid urbanization. Using Landsat images spanning from 1975 to 2023, this study analyzed changes in water resources and the growth of impervious surfaces during urbanization. The findings revealed that the area of impervious surfaces in the region increased from 227.1 km2 in 1975 to 1883.1 km2 in 2023. Natural wetland suffered significant losses, declining from 507.2 km2 in 1975 to near disappearance by the year 2000, with no significant recovery observed thereafter. Simultaneously, the water area expanded from 459.3 km2 in 1975 to 2373.1 km2 in 2023, primarily propelled by the significant contribution of aquaculture ponds, accounting for 2175.0 km2 or 91.7% of the total water area. Driver analysis revealed that these changes were found to be influenced by factors such as population, economy, demand, and policies. However, alongside the economic development brought by urbanization, negative impacts such as lake shrinkage, eutrophication, and increased flood risks have emerged. The Lixiahe region, as a relatively underdeveloped part of Jiangsu Province, faces the challenge of striking a balance between economic growth and environmental conservation.
- 18 February 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (4) , 711
Open AccessAnalysis of the Substantial Growth of Water Bodies during the Urbanization Process Using Landsat Imagery—A Case Study of the Lixiahe Region, China
In the process of urbanization, water bodies bear considerable anthropogenic pressure, resulting in a reduction of their surface area in most instances. Nevertheless, in contrast to many other regions, the Lixiahe region in Jiangsu Province, located in China’s eastern plain, has experienced a continuous expansion of water bodies over the past few decades amid rapid urbanization. Using Landsat images spanning from 1975 to 2023, this study analyzed changes in water resources and the growth of impervious surfaces during urbanization. The findings revealed that the area of impervious surfaces in the region increased from 227.1 km2 in 1975 to 1883.1 km2 in 2023. Natural wetland suffered significant losses, declining from 507.2 km2 in 1975 to near disappearance by the year 2000, with no significant recovery observed thereafter. Simultaneously, the water area expanded from 459.3 km2 in 1975 to 2373.1 km2 in 2023, primarily propelled by the significant contribution of aquaculture ponds, accounting for 2175.0 km2 or 91.7% of the total water area. Driver analysis revealed that these changes were found to be influenced by factors such as population, economy, demand, and policies. However, alongside the economic development brought by urbanization, negative impacts such as lake shrinkage, eutrophication, and increased flood risks have emerged. The Lixiahe region, as a relatively underdeveloped part of Jiangsu Province, faces the challenge of striking a balance between economic growth and environmental conservation.
- Open Access
- 10 January 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (2) , 276
Hyperspectral Image Denoising Based on Principal-Third-Order-Moment Analysis
Denoising serves as a critical preprocessing step for the subsequent analysis of the hyperspectral image (HSI). Due to their high computational efficiency, low-rank-based denoising methods that project the noisy HSI into a low-dimensional subspace identified by certain criteria have gained widespread use. However, methods employing second-order statistics as criteria often struggle to retain the signal of the small targets in the denoising results. Other methods utilizing high-order statistics encounter difficulties in effectively suppressing noise. To tackle these challenges, we delve into a novel criterion to determine the projection subspace, and propose an innovative low-rank-based method that successfully preserves the spectral characteristic of small targets while significantly reducing noise. The experimental results on the synthetic and real datasets demonstrate the effectiveness of the proposed method, in terms of both small-target preservation and noise reduction.
- 10 January 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (2) , 276
Open AccessHyperspectral Image Denoising Based on Principal-Third-Order-Moment Analysis
Denoising serves as a critical preprocessing step for the subsequent analysis of the hyperspectral image (HSI). Due to their high computational efficiency, low-rank-based denoising methods that project the noisy HSI into a low-dimensional subspace identified by certain criteria have gained widespread use. However, methods employing second-order statistics as criteria often struggle to retain the signal of the small targets in the denoising results. Other methods utilizing high-order statistics encounter difficulties in effectively suppressing noise. To tackle these challenges, we delve into a novel criterion to determine the projection subspace, and propose an innovative low-rank-based method that successfully preserves the spectral characteristic of small targets while significantly reducing noise. The experimental results on the synthetic and real datasets demonstrate the effectiveness of the proposed method, in terms of both small-target preservation and noise reduction.