Yoshihide Sekimoto 研究室

主宰者：Yoshihide Sekimoto

東京大学

AI 要約（直近 5 年の研究成果）

Sekimoto研究室は、衛星画像やスマートフォンのデータといった大規模な空間・時間情報を活用して、都市や社会の課題を解決する研究を行っています。建物の位置や高さの自動抽出、交通需要の予測、人間の移動パターンの分析など、多様な都市データを機械学習や深層学習により処理・分析することで、都市計画や防災、交通管理に向けた実践的な知見を生み出しています。研究の手法としては、人工知能を用いた画像認識や生成技術、グラフネットワークを用いた空間データの解析、大規模言語モデルによる人間行動の合成データ生成など、最新の計算手法を多角的に活用しています。また、複数国にまたがるデータを協調的に学習するフェデレーション学習や、住民の主観的な評価を組み込んだ都市環境改善など、プライバシーと実用性を両立させるアプローチも特徴です。これらの研究を通じて、研究室は3次元都市モデルの自動構築、浸水時の避難行動シミュレーション、気候変動下の健康リスク評価、街路空間の知覚的質の向上といった具体的な都市課題への対応を実現しています。デジタルツインやスマートシティの実現に向け、データ駆動型の意思決定を可能にする基盤技術の開発を推進しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（88 件）

[2026] Reducing Annotation Effort: An Innovative Weakly Supervised System for Nationwide Building Extraction Leveraging Open-Source Data
DOI: https://doi.org/10.1109/jstars.2026.3697411
[2026] TransFM: A foundation model for cross-city multimodal transportation demand prediction
DOI: https://doi.org/10.1016/j.trc.2026.105618
[2026] Toward Smart City Digital Twins: Bridging Preparation and Response Phases in Urban Flood Evacuation through Agent-Based Modeling
DOI: https://doi.org/10.24251/hicss.2026.219
[2026] Socioeconomic disparities in heat exposure in India: A mobility-based analysis
DOI: https://doi.org/10.1016/j.scs.2026.107437
[2025] Leveraging Spatial–Temporal Heterogeneity and Cross-Mode Interactions: A Meta-Learning Approach for Multimodal Transportation Demand Prediction
DOI: https://doi.org/10.1109/tits.2025.3614270
[2025] ControlBldg: A variable-controlled generative framework for conditioned modeling of vast 3D urban buildings
DOI: https://doi.org/10.1016/j.isprsjprs.2025.09.026
[2025] Designing for Perception: Weather-Aware Streetscapes via Generative Modeling and Global Datasets
DOI: https://doi.org/10.5194/isprs-archives-xlviii-4-w16-2025-149-2025
[2025] Predicting Building Height from Footprint and Urban Planning information for Digital Twin Generation
DOI: https://doi.org/10.5194/isprs-archives-xlviii-4-w15-2025-107-2025
[2025] A Perspective on the Standardization Process of 3D City Models in Japan: History of Geospatial Information Policy and Government Commitment to Standardization
DOI: https://doi.org/10.5194/isprs-archives-xlviii-4-w15-2025-171-2025
[2025] BldgWeaver: An appearance-contingent generation solution with a three-dimensional automated creation of building digital cousins model using pre-trained transformer architecture
DOI: https://doi.org/10.5194/isprs-annals-x-4-w6-2025-145-2025

続きを表示（残り 78 件）

[2025] Development of the Standard Data Product Specification for 3D City Models Using CityGML
DOI: https://doi.org/10.5194/isprs-annals-x-4-w6-2025-129-2025
[2025] Virtual 3D City Model Generation in CityGML
DOI: https://doi.org/10.5194/isprs-annals-x-4-w6-2025-257-2025
[2025] Advancing the Sensitivity Frontier in digital contact tracing: Comparative analysis of proposed methods toward maximized utility
DOI: https://doi.org/10.1016/j.imu.2025.101622
[2025] Large Language Models for Human Mobility Generation: Methods, Applications and Open Issues
DOI: https://doi.org/10.5638/thagis.33.si-98
[2025] Street Space Quality Improvement: Fusion of Subjective Perception in Street View Image Generation
DOI: https://doi.org/10.1016/j.inffus.2025.103467
[2025] Toward Smart City Digital Twins: Bridging Preparation and Response Phases in Urban Flood Evacuation through Agent-Based Modeling
[2025] Linking Urban Morphology and Human Activity Patterns: An Empirical Study Based on Mobility Survey Data from the Paris Region
DOI: https://doi.org/10.1109/bigdata66926.2025.11402166
[2025] Insights from the Road Damage Detection Challenge Series (2018–2024)
DOI: https://doi.org/10.1038/s42256-025-01132-5
[2024] G2Viz: an online tool for visualizing and analyzing a public transit system from GTFS data
DOI: https://doi.org/10.1007/s12469-024-00362-x
[2024] A digital twin prototype to visualize heterogeneous seismic damage simulation results on web-GIS
DOI: https://doi.org/10.1080/13467581.2024.2342883
[2024] Federated learning–based global road damage detection
DOI: https://doi.org/10.1111/mice.13186
[2024] Evaluating the subjective perceptions of streetscapes using street-view images
DOI: https://doi.org/10.1016/j.landurbplan.2024.105073
[2024] YJMob100K: City-scale and longitudinal dataset of anonymized human mobility trajectories
DOI: https://doi.org/10.1038/s41597-024-03237-9
[2024] A Preliminary Study on Dynamic Urban Knowledge Graph Construction using Heterogeneous Spatio-temporal Data
DOI: https://doi.org/10.1109/bigdata62323.2024.10825457
[2024] Geometric-based approach for linking various building measurement data to a 3D city model
DOI: https://doi.org/10.1371/journal.pone.0296445
[2024] Agentic Large Language Models for Generating Large-Scale Urban Daily Activity Patterns
DOI: https://doi.org/10.1109/bigdata62323.2024.10825138
[2024] ORDDC’2024: State of the art Solutions for Optimized Road Damage Detection
DOI: https://doi.org/10.1109/bigdata62323.2024.10825254
[2024] Road Damage Detection Across Borders: Federated Learning Insights from Japan, China, Norway and the USA
DOI: https://doi.org/10.1109/swc62898.2024.00223
[2024] MobGLM: A Large Language Model for Synthetic Human Mobility Generation
DOI: https://doi.org/10.1145/3678717.3691311
[2024] Enhanced Road Damage Detection with Federated Learning Across Diverse and Heterogeneous Global Datasets
DOI: https://doi.org/10.1145/3678717.3695758
[2024] Explainable Hierarchical Urban Representation Learning for Commuting Flow Prediction
DOI: https://doi.org/10.1145/3678717.3691273
[2024] Long-Term Demand Prediction for Public Bicycle Sharing System: A Spatio-Temporal Attentional Graph Convolution Networks Approach
DOI: https://doi.org/10.1109/tits.2024.3469169
[2024] Emotions, behaviors and places: Mapping sentiments with behaviors in Japanese tweets
DOI: https://doi.org/10.1016/j.cities.2024.105449
[2024] Revamping Building Extraction with Yolov8: A Multi-Domain Assessment in Bangkok's Diverse Land-Use-Types
DOI: https://doi.org/10.1109/igarss53475.2024.10641251
[2024] Enhanced large-scale building extraction evaluation: developing a two-level framework using proxy data and building matching
DOI: https://doi.org/10.1080/22797254.2024.2374844
[2024] <scp>RDD2022</scp>: A multi‐national image dataset for automatic road damage detection
DOI: https://doi.org/10.1002/gdj3.260
[2024] A cost-and-effect simulation model for compact city approaches: A case study in Japan
DOI: https://doi.org/10.1016/j.cities.2024.105212
[2024] Nationwide synthetic human mobility dataset construction from limited travel surveys and open data
DOI: https://doi.org/10.1111/mice.13285
[2024] End-to-End Framework for the Automatic Matching of Omnidirectional Street Images and Building Data and the Creation of 3D Building Models
DOI: https://doi.org/10.3390/rs16111858
[2024] Assessing internal displacement patterns in Ukraine during the beginning of the Russian invasion in 2022
DOI: https://doi.org/10.1038/s41598-024-59814-w
[2023] WindSR: Improving Spatial Resolution of Satellite Wind Speed Through Super-Resolution
DOI: https://doi.org/10.1109/access.2023.3292966
[2023] Social segregation levels vary depending on activity space types: Comparison of segregation in residential, workplace, routine and non-routine activities in Tokyo metropolitan area
DOI: https://doi.org/10.1016/j.cities.2023.104745
[2023] Label Freedom: Stable Diffusion for Remote Sensing Image Semantic Segmentation Data Generation
DOI: https://doi.org/10.1109/bigdata59044.2023.10386381
[2023] Unveiling the Road Matrix: Development of Versatile Pavement Surface Models from Low-resolution Aerial Images
DOI: https://doi.org/10.1109/bigdata59044.2023.10386733
[2023] Enhancing geospatial retail analysis by integrating synthetic human mobility simulations
DOI: https://doi.org/10.1016/j.compenvurbsys.2023.102058
[2023] Generating Diverse Optimal Road Management Plans in Post-Disaster by Applying Envelope Multi-Objective Deep Reinforcement Learning
DOI: https://doi.org/10.20965/jdr.2023.p0884
[2023] Are Utility Poles Within Sight? Unleashing the Power of Computer Vision for Effortless Roadside Management
DOI: https://doi.org/10.1109/itsc57777.2023.10421927
[2023] Deep Learning Approach to Logistics Trips Generation: Enhancing Pseudo People Flow with Agent-Based Modeling
DOI: https://doi.org/10.1109/itsc57777.2023.10422374
[2023] Real-time classification of longitudinal conveyor belt cracks with deep-learning approach
DOI: https://doi.org/10.1371/journal.pone.0284788
[2023] Realtime damage detection in long conveyor belts using deep learning approach
DOI: https://doi.org/10.22260/isarc2023/0017
[2023] Quantitative land price analysis via computer vision from street view images
DOI: https://doi.org/10.1016/j.engappai.2023.106294
[2023] People Flow Trend Estimation Approach and Quantitative Explanation Based on the Scene Level Deep Learning of Street View Images
DOI: https://doi.org/10.3390/rs15051362
[2023] Deep Learning Approach for Classifying the Built Year and Structure of Individual Buildings by Automatically Linking Street View Images and GIS Building Data
DOI: https://doi.org/10.1109/jstars.2023.3237509
[2023] A Cost-and-Effect Simulation Model for Multiple Urban Planning Scenarios Using Pseudo-People-Flow Data
DOI: https://doi.org/10.2139/ssrn.4396161
[2022] Data Resampling and Ensemble Learning for Vehicle Class and Orientation Detection
DOI: https://doi.org/10.1109/bigdata55660.2022.10020642
[2022] Pseudo-Pflow: Development of Nationwide Synthetic Open Dataset for People Movement Based on Limited Travel Survey and Open Statistical Data
DOI: https://doi.org/10.2139/ssrn.4098791
[2022] Efficient Visualization of Nationwide People Flow Data Using Vector Tiling Technology
DOI: https://doi.org/10.5638/thagis.30.85
[2022] Development of a Large-Scale Roadside Facility Detection Model Based on the Mapillary Dataset
DOI: https://doi.org/10.3390/s22249992
[2022] Crowdsensing-based Road Damage Detection Challenge (CRDDC’2022)
DOI: https://doi.org/10.1109/bigdata55660.2022.10021040
[2022] Road Rutting Detection using Deep Learning on Images
DOI: https://doi.org/10.1109/bigdata55660.2022.10020458
[2022] Vehicle re-identification and trajectory reconstruction using multiple moving cameras in the CARLA driving simulator
DOI: https://doi.org/10.1109/bigdata55660.2022.10020814
[2022] Spatial Attention Based Grid Representation Learning For Predicting Origin–Destination Flow
DOI: https://doi.org/10.1109/bigdata55660.2022.10021023
[2022] Road Damage Detection for Multiple Countries
DOI: https://doi.org/10.1109/bigdata55660.2022.10020619
[2022] Deep Learning for Destination Choice Modeling: A Fundamental Approach for National Level People Flow Reconstruction
DOI: https://doi.org/10.1109/bigdata55660.2022.10020165
[2022] Uncertainty of Traffic Congestion Estimation Using Nationwide Pseudo Trip Data and Agent-Based Simulation
DOI: https://doi.org/10.1109/bigdata55660.2022.10020749
[2022] Large-scale individual building extraction from open-source satellite imagery via super-resolution-based instance segmentation approach
DOI: https://doi.org/10.1016/j.isprsjprs.2022.11.006
[2022] Realtime Safety Analysis System using Deep Learning for Fire Related Activities in Construction Sites
DOI: https://doi.org/10.1109/iceccme55909.2022.9987855
[2022] Do open data impact citizens’ behavior? Assessing face mask panic buying behaviors during the Covid-19 pandemic
DOI: https://doi.org/10.1038/s41598-022-22471-y
[2022] Citywide reconstruction of traffic flow using the vehicle-mounted moving camera in the CARLA driving simulator
DOI: https://doi.org/10.1109/itsc55140.2022.9921927
[2022] Vision-Based Traffic Sign Detection and Localization in Tokyo Metropolitan Area
DOI: https://doi.org/10.1109/itsc55140.2022.9921902
[2022] Development of current estimated household data and agent-based simulation of the future population distribution of households in Japan
DOI: https://doi.org/10.1016/j.compenvurbsys.2022.101873
[2022] Real-time citywide reconstruction of traffic flow from moving cameras on lightweight edge devices
DOI: https://doi.org/10.1016/j.isprsjprs.2022.07.022
[2022] Scene Level People Flow Trend Prediction by Swin Transformer
DOI: https://doi.org/10.1109/igarss46834.2022.9883597
[2022] Online real-time pedestrian tracking from medium altitude aerial footage with camera motion cancellation
DOI: https://doi.org/10.1016/j.cviu.2022.103386
[2022] Road-reconstruction after multi-locational flooding in multi-agent deep RL with the consideration of human mobility - Case study: Western Japan flooding in 2018 -
DOI: https://doi.org/10.1016/j.ijdrr.2021.102780
[2022] Large-Scale Building Footprint Extraction from Open-Sourced Satellite Imagery via Instance Segmentation Approach
DOI: https://doi.org/10.1109/igarss46834.2022.9884762
[2021] Study Concept on the Development of an Urban Cyber Physical System for Enhancing the Capability to Respond to Large-Scale Earthquakes
DOI: https://doi.org/10.20965/jdr.2021.p0287
[2021] Joining Street-View Images and Building Footprint GIS Data
DOI: https://doi.org/10.1145/3486640.3491395
[2021] Computation of Infection Risk via Confidential Locational Entries: A Precedent Approach for Contact Tracing With Privacy Protection
DOI: https://doi.org/10.1109/access.2021.3087478
[2021] Early warning of COVID-19 hotspots using human mobility and web search query data
DOI: https://doi.org/10.1016/j.compenvurbsys.2021.101747
[2021] Citywide reconstruction of cross-sectional traffic flow from moving camera videos
DOI: https://doi.org/10.1109/bigdata52589.2021.9671751
[2021] Development of a Reinforcement Learning based Agent Model and People Flow Data to Mega Metropolitan Area
DOI: https://doi.org/10.1109/bigdata52589.2021.9671399
[2021] Simulating Human Mobility with Agent-based Modeling and Particle Filter Following Mobile Spatial Statistics
DOI: https://doi.org/10.1145/3474717.3484203
[2021] Development of current estimated household data and a future forecast model for nationwide agent simulation
DOI: https://doi.org/10.11361/journalcpij.56.603
[2021] Deep learning-based road damage detection and classification for multiple countries
DOI: https://doi.org/10.1016/j.autcon.2021.103935
[2021] Prototyping of A Citizen-oriented Regional Planning Tool to Automated Digital Design Process
DOI: https://doi.org/10.11361/reportscpij.20.2_277
[2021] RDD2020: An annotated image dataset for automatic road damage detection using deep learning
DOI: https://doi.org/10.1016/j.dib.2021.107133
[2021] Estimation of earthquake damage to urban environments using sparse modeling
DOI: https://doi.org/10.1177/2399808320986560

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（88 件）

科研費（0 件）

所属学会・役職（0 件）