Xianwei Han

Dr. Xianwei Han

School of Physics and Electronics, Henan University

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
20 January 2011 in Journal of Electronics & Information Technology
Verified
Journal Article
Closed access
XHXianwei Han
Xianwei Han
YFYi-Li Fu
Yi-Li Fu
GLGang Li
Gang Li

2 February 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
WGWei Gao
Wei Gao
YSYu Sun
Yu Sun
XHXianwei Han
Xianwei Han
YZYimin Zhang
Yimin Zhang
LZLei Zhang
Lei Zhang
YHYunliang Hu
Yunliang Hu
Building change detection (CD) from remote sensing images (RSI) has great significance in exploring the utilization of land resources and determining the building damage after a disaster. This paper proposed an attention-based multi-scale input-output network, named AMIO-Net, for building CD in high-resolution RSI. It is able to overcome partial drawbacks of existing CD methods, such as insufficient utilization of information (details of building edges) of original images and poor detection effect of small targets (small-scale buildings or small-area changed buildings that are disturbed by other buildings). In AMIO-Net, the input image is scaled down to different sizes, and performed the convolution to extract features. Then the feature maps are fed into the encoding stage so that the network can fully utilize the feature information (FI) of the original image. More importantly, we design two attention mechanism modules: the pyramid pooling attention module (PPAM) and the Siamese attention mechanism module (SAMM). PPAM combines a pyramid pooling module and an attention mechanism to fully consider the global information and focus on the FI of changed pixels in the image. The input of SAMM is the parallel multi-scale output diagram of the decoding portion and deep feature maps of the network so that AMIO-Net can utilize the global contextual semantic FI and strengthen detection ability for small targets. Experiments on three datasets show that the proposed method achieves higher detection accuracy and F1 score compared with the state-of-the-art methods.

15 March 2022 in Physical Chemistry Chemical Physics
Verified
Journal Article
Closed access
PDF file
XSXiaobo Shi
Xiaobo Shi
SJShujuan Jiang
Shujuan Jiang
XHXianwei Han
Xianwei Han
MWMin Wei
Min Wei
BWBing Wang
Bing Wang
HYHuabing Yin
Huabing Yin
InSeBr-Type monolayers, ternary In(Se,S)(Br,Cl) compounds, are typical two-dimensional (2D) Janus materials and can be exfoliated from their bulk crystals. The structural stability, electronic properties, mechanical flexibility, and intrinsic piezoelectricity of these InSeBr-type 2D Janus monolayers are comprehensively investigated by first-principles calculations. Our calculations show that the stable InSeBr-type monolayers exhibit ultrahigh mechanical flexibility with low Young's moduli. Due to the amazing flexibility of the InSeBr monolayer with an ultra-low Young's modulus of 0.81 N m−1, the piezoelectric strain coefficient d11 can reach 103 pm V−1 orders of magnitude (around 2361–3224 pm V−1), which is larger than those of reported 2D materials and even superior to those of conventional perovskite bulk materials. Such a superior piezoelectric response of InSeBr-type monolayers could facilitate their practical applications in sensors and energy harvesters.

20 November 2024 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
YSYu Sun
Yu Sun
YZYujuan Zhao
Yujuan Zhao
XHXianwei Han
Xianwei Han
WGWei Gao
Wei Gao
YHYunliang Hu
Yunliang Hu
YZYimin Zhang
Yimin Zhang

31 October 2024 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
GYGuanghui Yang
Guanghui Yang
XHXianwei Han
Xianwei Han
LZLei Zhang
Lei Zhang
WGWei Gao
Wei Gao
YHYunliang Hu
Yunliang Hu
CSCheng Sun
Cheng Sun

4 March 2022 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
SZShichao Zhang
Shichao Zhang
XHXianwei Han
Xianwei Han
YZYimin Zhang
Yimin Zhang
GYGuanghui Yang
Guanghui Yang
Though it has great significance for military and civilian applications, detecting aircraft from large-scale remote sensing images remains a challenge. This is a typical small target detection problem, which has not been solved well yet. Because a large-scale satellite image usually encompasses >150 km2 and over 500 million pixels, while the aircrafts are often minuscule (only about 80 pixels). To solve this problem, we propose an aircraft detection method based on visual saliency and convolutional neural networks. First, the improved Fast R-CNN network is used to classify the airport. YOLOv4-Less, an improved YOLOv4 network, judges whether an aircraft is at the airport. In experiments, the network model was trained and tested through an image data set collected from Google Earth. The results showed that the accuracy of the model can reach 98.04% and the recall rate can reach 97.84%. Furthermore, the proposed algorithm detected aircraft in remote sensing images from different satellite platforms, and the experimental results showed that its adaptability is strong, and detection efficiency was improved compared to existing methods.