Associate Professor at IRIDeS, Tohoku University.
Focusing on Photogrammetry & Remote Sensing, Machine Learning.

E-mail

wei.yuan@tohoku.ac.jp

Research Subjects

Dr.Yuan's research interests including Photogrammetry & Remote Sensing, Computervision and Machine Learning.

Dr.Yuan mainly focus on Aerial/Satellite image based image processing such as automatic DEM/DSM generation, stereo matching, urban infrastructure extraction and change detection with application to Urban Monitering and Disaster Science.

Academic/Teaching Experience

• 2024.02 - present, Associate Professor, International Research Institute of Disaster Science, Tohoku University.
• 2020.04 - 2024.01, Project Assistant Professor, Center for Spatial Information Science, The University of Tokyo.
• 2018.10 - 2020.03, Project Researcher, Center for Spatial Information Science, The University of Tokyo.

Educations

• 2012.09 - 2020.06, Ph.D., Photogrammetry and Remote Sensing, Wuhan University.
• 2015.10 - 2018.09, Ph.D., Civil Engineering, The University of Tokyo.
• 2014.10 - 2015.09, Master, Civil Engineering, The University of Tokyo.

Funded Projects

• 2024.04, Enabling Human-Centered Digital Twin for Community Resilience, Japan Science and Technology Agency. (CI)
• 2023.04, Multi-task learning based post-disaster mapping via multi-modal remote sensing observations, Japan Society for Promotion of Science. (PI)
• 2022.04, Heterogeneous Graph Neural Network based Federated Mobile Crowdsensing, Japan Society for Promotion of Science. (CI)
• 2019.04, A study of satellite-based mapping of real estate price and its applications, Japan Society for Promotion of Science. (CI)

Honors and Awards

• 2022.07 Best Young Author paper award (co-authured), ISPRS2022, Nice, France.
• 2015.10 MEXT Scholarship (Ph.D.), The University of Tokyo. Tokyo, Japan.
• 2014.10 MEXT Scholarship (Master), The University of Tokyo. Tokyo, Japan.
• 2012.06 Outstanding Graduate Award of Hubei Province, Wuhan, China.

Selected Publications

Dense Image Matching

• Dense image-matching via optical flow field estimation and fast-guided filter refinement,Wei Yuan, Xiuxiao Yuan, Shu Xu, Jianya Gong, Ryosuke Shibasaki.
• Fully automatic DOM generation method based on optical flow field dense image matching, Wei Yuan, Xiuxiao Yuan, Yang Cai, Ryosuke Shibasaki.
• Few-Shot Depth Completion Using Denoising Diffusion Probabilistic Model, Weihang Ran, Wei Yuan*, Ryosuke Shibasaki.
• Unsupervised Multi-Constraint Deep Neural Network for Dense Image Matching, Wei Yuan, Zipei Fan, Xiuxiao Yuan, Jianya Gong, Ryosuke Shibasaki.
• Research developments and prospects on dense image matching in photogrammetry, Xiuxiao Yuan, Wei Yuan, Shu Xu, Yanhua Ji.
• An aerial-image dense matching approach based on optical flow field, Wei Yuan, Shiyu Chen, Yong Zhang, Jianya Gong, Ryosuke Shibasaki.

Tie Point Matching

• Poor textural image tie point matching via graph theory, Xiuxiao Yuan, Shiyu Chen, Wei Yuan*, Yang Cai
• A cluster-based disambiguation method using pose consistency verification for structure from motion, Ye Gong, Pengwei Zhou, Changfeng Liu, Yan Yu, Jian Yao, Wei Yuan, Li Li.
• An automatic detection method of mismatching points in remote sensing images based on graph theory, Xiuxiao Yuan, Wei Yuan*, Shiyu Chen.
• Matching multi-sensor remote sensing images via an affinity tensor, Shiyu Chen, Xiuxiao Yuan, Wei Yuan*, et al.

Urban Object Detection

• Multi-Constraint Transformer based Automatic Building Extraction from High Resolution Remote Sensing Images, Wei Yuan, Weihang Ran, Xiaodan Shi, Ryosuke Shibasaki
• Graph Encoding based Hybrid Vision Transformer for Automatic Road Network Extraction, Wei Yuan, Weihang Ran, Xiaodan Shi, Zipei Fan, Yang Cai, Ryosuke Shibasaki. (Oral)
• Hybrid Feature Embedding for Automatic Building Outline Extraction, Weihang Ran, Wei Yuan*, Xiaodan Shi, Zipei Fan, Ryosuke Shibasaki.
• Cross-Scale Attention-based Tree Crown Detection via UAV imagery, Wei Yuan, Xiaodan Shi, Zhiling Guo, Zipei Fan, Jianya Gong, Ryosuke Shibasaki. (Oral)
• Graph neural network based multi-feature fusion for building change detection, Wei Yuan, Xiuxiao Yuan, Zipei Fan, Zhiling Guo, Xiaodan Shi, Jianya Gong, Ryosuke Shibasaki. (Oral)
• Automatic building segmentation of aerial imagery using multi-constraint fully convolutional networks, Guangming Wu, Xiaowei Shao, Zhiling Guo, Qi Chen, Wei Yuan, Xiaodan Shi, Yongwei Xu, Ryosuke Shibasaki.

Others

• MetaTraj: meta-learning for cross-scene cross-object trajectory prediction, Xiaodan Shi, Haoran Zhang, Wei Yuan, Ryosuke Shibasaki.
• Voronoi centerline-based seamline network generation method, Xiuxiao Yuan, Yang Cai, Wei Yuan.
• Online trajectory prediction for metropolitan scale mobility digital twin, Zipei Fan, Xiaojie Yang, Wei Yuan, Renhe Jiang, Quanjun Chen, Xuan Song, Ryosuke Shibasaki.
• Learning Social Compliant Multi-Modal Distributions of Human Path in Crowds, Xiaodan Shi, Haoran Zhang, Wei Yuan, Dou Huang, Zhiling Guo, Ryosuke Shibasaki. (Best Young Author Paper Award)
• Optimal seamline detection for orthoimage mosaicking by combining deep convolutional neural network and graph cuts, Li Li, Jian Yao, Yahui Liu, Wei Yuan, Shuzhu Shi, Shenggu Yuan.