Linhui Wei

Ms. Linhui Wei

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
7 December 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
WLWeikun Lv
Weikun Lv
LWLinhui Wei
Linhui Wei
DZDian Zheng
Dian Zheng
YLYu Liu
Yu Liu
YWYumei Wang
Yumei Wang
The Mars exploration mission of China named Tianwen-1 is being carried out as scheduled. The Navigation and Terrain Cameras (NaTeCam) equipped on the Zhurong Rover play an essential role in obstacle recognition. The main obstacles on the Martian surface are rocks of different sizes, which influence the path planning of Zhurong Rover in scientific exploration. Most existing semantic segmentation methods are based on the U-Net architecture with ResNet or other backbones, and features extracted by these methods lack of the long-range dependencies. To fully exploit the context information, we propose the MarsNet framework for Mars image, which combines Transformers with the convolutional neural network as the backbone, and hybrid dilated convolution (HDC) is also employed to the decoder path to help detect the huge rocks. Besides, since there are few open-source datasets for rock segmentation for Mars, we establish a segmentation dataset from Martian surface image, named TWMARS, captured by NaTeCam. Extensive experiments are conducted on TWMARS dataset, and the experimental results demonstrate that MarsNet achieves accurate rock segmentation and outperforms state-of-the-art methods. The source code is available at: https://github.com/BUPT-ANT-1007/MarsNet.

6 September 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
DZDian Zheng
Dian Zheng
LWLinhui Wei
Linhui Wei
WLWeikun Lv
Weikun Lv
YLYu Liu
Yu Liu
YWYumei Wang
Yumei Wang
Rocks, prominent features on the surface of Mars, are a primary focus of Mars exploration missions. The accuracy of recognizing rock information, including size and position, deeply affects the path planning for rovers on Mars and the geological exploration of Mars. In this paper, we present a rock measurement method for the Mars surface based on a Rover Attitude and Camera Parameter (RACP). We analyze the imaging process of the Navigation and Terrain Camera (NaTeCam) on the Zhurong rover, which involves utilizing a semi-spherical model (SSM) to characterize the camera’s attitude, a projection model (PM) to connect the image data with the three-dimensional (3D) environment, and then estimating the distance and size of rocks. We conduct a test on NaTeCam images and find that the method is effective in measuring the distance and size to Martian rocks and identifying rocks at specific locations. Furthermore, an analysis of the impact of uncertain factors is conducted. The proposed RACP method offers a reliable solution for automatically analyzing the rocks on Mars, which provides a possible solution for the route planning in similar tasks.

4 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LWLinhui Wei
Linhui Wei
CCChen Chang
Chen Chang
YLYu Liu
Yu Liu
YWYumei Wang
Yumei Wang
The satellite-terrestrial integrated network (STIN), as an integration of the satellite network and terrestrial, has become a promising architecture to support global coverage and ubiquitous connection. The architecture of software-defined networking (SDN) is utilized to intelligently coordinate the global STIN, in which the placement schemes of SDN controllers, including the locations, number, and roles, would produce various performances. However, the uneven distribution of global users leads to the unbalanced energy consumption of satellite resources, which brings a heavy burden for satellites to maintain the control flows for network management. To provide green communication for international economic trade in the countries along the Belt and Road, in this paper, we focus on the energy-efficient controller placement (EECP) problem in the software-defined STIN. The satellite gateways are located in the countries along the Belt and Road, which accounts for a large number of traffic demands and a dense population. The controllers are deployed on the LEO satellites, where each LEO satellite is a candidate controller. The energy consumption for the control paths and the user data links is modeled and then formulated as the flow processing-oriented optimization problem. A modified simulated annealing placement (MSAP) algorithm is developed to solve the EECP problem, in which we use the greedy way to obtain the initial set of controllers, and then the final optimal controller placement result is obtained by the simulated annealing algorithm. Extensive simulations are conducted on the simulated Iridium satellite network topology and statistics data. Compared with other algorithms, the results show that MSAP reduces network energy consumption by 20% and average latency by 25%.

1 January 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
JLJunjie Li
Junjie Li
WLWeikun Lv
Weikun Lv
LWLinhui Wei
Linhui Wei
YLYu Liu
Yu Liu
YWYumei Wang
Yumei Wang
ZZZhi Zeng
Zhi Zeng

16 May 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
DZDian Zheng
Dian Zheng
LWLinhui Wei
Linhui Wei
YLYu Liu
Yu Liu
YWYumei Wang
Yumei Wang
In China’s Tianwen-1 mission for Mars exploration, Zhurong rover carries the Navigation and Terrain Camera (NaTeCam) and collects a lot of terrains and topographic data. For the scientific popularization of Mars, a virtual reality roaming based on panoramic stitching presents the Martian surface in detail and provides an immersive experience for users. However, the current Mars roaming systems focus on global information instead of details, and the traditional panoramic stitching methods are not suitable for Mars images. This letter proposes a panoramic stitching method and develops a 3DoF+ Mars roaming system. The proposed stitching-combines-features-and-projection (SCFP) jointly considers the extracted features of images and projection based on intrinsic camera parameters, which improves the matching effect and execution efficiency. Experimental results indicate that the SCFP reduces the computational time and improves stitching results than state-of-the-art methods. Furthermore, we design and deploy the 3DoF+ roaming system based on panoramic stitching with datasets obtained from the Tianwen-1 mission.

21 July 2020 in IEEE Access
Verified
Journal Article
Open access
LWLinhui Wei
Linhui Wei
YWYumei Wang
Yumei Wang
YLYu Liu
Yu Liu
Light field (LF) can capture the spatial and angular information of the light in one single exposure. And the LF images are widely used in various fields, especially in immersive media. The rich imaging information in the LF poses great challenges for transmission. However, LF images are sparse and redundant to some extent, which makes LF compression possible. Besides, the compressed sensing (CS) theory shows that images can be recovered from a small number of measurements when they are sparse. In this paper, we propose a Tensor-based Compressed Sensing method to compress images and Epipolar Plane Images for reconstruction (TCSEPI). This method divides the viewpoints of LF images into several regions and stacks the images in each region into a 4D tensor, which conduct CS together and yields measurements with common characteristics. Subsequently, the epipolar plane images are used to reconstruct the LF images and restore the geometric consistency information. To achieve better reconstruction results, we design two cascaded convolutional neural networks to implement the measurement matrix optimization and LF images reconstruction sequentially. Experimental results show the superior performance of TCSEPI, which achieves at least 3dB gain in PSNR and outperforms state-of-the-art in the reconstruction quality.