Letong Han

Letong Han

Auto-generated profile, based on publicly available information

Letong Han

School of Software Engineering, Tongji University, 4800 Caoan Road Jiading District, Shanghai 201804, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 May 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
QLQin Liu
Qin Liu
LHLetong Han
Letong Han
RTRui Tan
Rui Tan
HFHongfei Fan
Hongfei Fan
WLWeiqi Li
Weiqi Li
Sicong LiuSicong Liu
Sicong Liu
Pansharpening aims at fusing the rich spectral information of multispectral (MS) images and the spatial details of panchromatic (PAN) images to generate a fused image with both high resolutions. In general, the existing pansharpening methods suffer from the problems of spectral distortion and lack of spatial detail information, which might prevent the accuracy computation for ground object identification. To alleviate these problems, we propose a Hybrid Attention mechanism-based Residual Neural Network (HARNN). In the proposed network, we develop an encoder attention module in the feature extraction part to better utilize the spectral and spatial features of MS and PAN images. Furthermore, the fusion attention module is designed to alleviate spectral distortion and improve contour details of the fused image. A series of ablation and contrast experiments are conducted on GF-1 and GF-2 datasets. The fusion results with less distorted pixels and more spatial details demonstrate that HARNN can implement the pansharpening task effectively, which outperforms the state-of-the-art algorithms.

4 February 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
HZHongming Zhu
Hongming Zhu
ZWZeju Wang
Zeju Wang
LHLetong Han
Letong Han
MXManxin Xu
Manxin Xu
WLWeiqi Li
Weiqi Li
BDBowen Du
Bowen Du
Optical remote sensing is heavily affected by clouds, and thus cloud removal is a critical task for obtaining accurate and reliable results. Traditional methods for remote sensing data reconstruction include spectral-based, spatial-based, timebased, and hybrid-based methods. However, these methods have inherent limitations in handling cloud removal due to the imaging mechanism of optical images. Synthetic Aperture Radar (SAR) images have been used in remote sensing image de-clouding in recent years due to their unique imaging mechanism. However, the domain gap between SAR images and multi-spectral images, the non-uniformity of cloud distribution, and the lack of mining self-similarity and correlation between different spectra of multispectral images pose challenges for SAR-based cloud removal. In this study, we propose a SAR-based cross-attention network for multi-spectral image de-clouding reconstruction. The crossattention mechanism helps regions with heavy cloud cover to refer more to the features of SAR images during reconstruction while avoiding interference from the noise interference of SAR images. Experimental results show that the proposed method outperforms state-of-the-art methods in terms of reconstruction accuracy and visual quality, demonstrating its effectiveness and potential for cloud removal in remote sensing.

9 February 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HZHongming Zhu
Hongming Zhu
RTRui Tan
Rui Tan
LHLetong Han
Letong Han
HFHongfei Fan
Hongfei Fan
ZWZeju Wang
Zeju Wang
QLQin Liu
Qin Liu
Over the past few years, deep learning algorithms have held immense promise for better multi-spectral (MS) optical remote sensing image (RSI) analysis. Most of the proposed models, based on convolutional neural network (CNN) and fully convolutional network (FCN), have been applied successfully on computer vision images (CVIs). However, there is still a lack of exploration of spectra correlation in MS RSIs. In this study, a deep neural network with a spectrum separable module (DSSM) is proposed for semantic segmentation, which enables the utilization of MS characteristics of RSIs. The experimental results obtained on Zurich and Potsdam datasets prove that the spectrum-separable module (SSM) extracts more informative spectral features, and the proposed approach improves the segmentation accuracy without increasing GPU consumption.