Prof. Lin Wang Profile

Prof. Lin Wang

at Northwest Univ

SPIE Involvement:

Author

Publications (6)

SPIE Journal Paper | 22 March 2024

Deblurring method for remote sensing image via dual scale parallel spatial fusion network

Hang An, Xiaoxuan Chen, Lin Wang, Baopu Hou, Zhichao Jin, Na Meng, Bo Jiang, Yaowei Li

JARS, Vol. 18, Issue 01, 014527, (March 2024) https://doi.org/10.1117/12.10.1117/1.JRS.18.014527

KEYWORDS: Deblurring, Remote sensing, Image fusion, Image sharpness, Deep learning, Semantics, Image quality, Education and training, Image processing, Image restoration

Read Abstract +

Proceedings Article | 9 August 2023 Poster + Presentation + Paper

Hyperspectral image fusion based on dual-resolution fusion feature mutual guidance network

Lu Liu, Kai Ma, Jing Yan, Fulai Xing, Wanqing Zhao, Shenglin Peng, Lin Wang

Proceedings Volume 12620, 126200H (2023) https://doi.org/10.1117/12.2673754

KEYWORDS: Image fusion, Hyperspectral imaging, Feature fusion, Feature extraction, RGB color model, Spatial resolution, Image resolution, Image restoration, Image processing, Image quality

Read Abstract +

Proceedings Article | 9 August 2023 Presentation + Paper

Multi-scale convolutional autoencoder network-based implicit information mining of cultural relics

Kai Yu, Zhichao Li, Yi Duan, Lin Wang, Jun Wang, Jinye Peng

Proceedings Volume 12620, 1262003 (2023) https://doi.org/10.1117/12.2673753

KEYWORDS: Data hiding, Mining, Convolution, Machine learning, Hyperspectral imaging, Feature extraction, Data modeling, Principal component analysis, Data processing, Image fusion

Read Abstract +

Implicit information exploration techniques are of great importance for the restoration and conservation of cultural relics. At present, the hyperspectral image analysis technique is one of the main methods to extract hidden information, which mainly contains two analysis methods such as principal component analysis (PCA) and minimum noise fraction rotation (MNF), both of which have achieved certain information extraction effects. In recent years, with the development of artificial intelligence, deep learning, and other technologies, nonlinear methods such as neural networks are expected to further improve the effect of implicit information mining. Therefore, this paper is oriented to the problem of extracting hidden information from pottery artifacts and tries to study and explore the hidden information mining method based on deep neural networks, expecting to obtain more stable and richer hidden information. In this paper, an auto-encoder-based implied information mining method is proposed first, and the auto-encoder (AE) framework achieves good performance in feature learning by automatically learning low-dimensional embedding and reconstructing data. However, during the experiments, it is found that some important detailed information (e.g., implicit information) is often lost in the reconstruction process because the traditional autoencoder network only focuses more on the pixel-level reconstruction loss and ignores the overall distribution. Therefore, this paper further proposes a multi-scale convolutional autoencoder network (MSCAE). It constructs a multi-scale convolutional module based on the traditional AE and designs a cyclic consistency loss in addition to the reconstruction loss, to reduce the loss of detailed information in the reconstruction process and improve the implicit information mining effect. In the experiments, we find that the proposed method can achieve effective implied information mining by extracting implied information from cocoon-shaped pots, and its visual effect has been improved compared with the traditional AE network.

SPIE Journal Paper | 11 October 2021

Attention deep and shallow network union HR optical flow compensation for video super-resolution

Xuan Zhu, Yuying Jin, Lin Wang, Jun Wang, Zhixiang Lan, Peirong Chen, Yifei Sun

OE, Vol. 60, Issue 10, 103102, (October 2021) https://doi.org/10.1117/12.10.1117/1.OE.60.10.103102

KEYWORDS: Video, Optical flow, Lawrencium, Super resolution, Optical networks, Video acceleration, Optical engineering, Visualization, Zoom lenses, Convolution

Read Abstract +

SPIE Journal Paper | 14 September 2021

Temporal–spatial feature compensation combines with multi-feature discriminators for video super-resolution perceptual quality improvement

Xuan Zhu, Xin Liu, Lin Wang, Zhenpeng Guo, Jun Wang, Rongzhi Wang, Yifei Sun

JEI, Vol. 30, Issue 05, 053005, (September 2021) https://doi.org/10.1117/12.10.1117/1.JEI.30.5.053005

KEYWORDS: Video, Lawrencium, Video surveillance, Optical flow, Visualization, Gallium nitride, Super resolution, Convolution, Surveillance, Distortion

Read Abstract +

SPIE Journal Paper | 3 May 2021 Open Access

Fast radar detection method based on two-dimensional trilinear autocorrelation function for maneuvering target with jerk motion

Zhongying Liang, Yanyan Li, Jinping Niu, Lin Wang, XiaoXuan Chen, Ling Wang

JARS, Vol. 15, Issue 02, 026508, (May 2021) https://doi.org/10.1117/12.10.1117/1.JRS.15.026508

KEYWORDS: Radar, Target detection, Design for manufacturing, Francium, Signal to noise ratio, Doppler effect, Hough transforms, 3D acquisition, Phase compensation, Motion estimation

Read Abstract +

DOWNLOAD PAPER

Showing 5 of 6 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years