人々の流動を計測し行動モデルと組合せて推定する。
Estimating People Flow in Combination of Sensing and Behavior Modeling
様々なコンテクストにおける人々の移動をデータから解明する。
Unravelling People Movement in Specific Contexts
都市インフラを低廉・迅速にモニタリングする
Monitoring Urban Infrastructure Rapidly and Cheaply
国や地域の情報流通を設計・構築し、都市を駆動する
Operating Cities by Designing and Establishing Information Distribution
キャンパス公開2023 – 研究ポスター
代表的な研究のポスターを一覧で表示しています。これら以外にも、さまざま研究を行っています。詳細については、【研究活動】から移動できるテーマ別の研究紹介ページをご覧ください。
各ポスターの内容は、画像をクリックすることで閲覧可能です。
関本研究室研究紹介 / Sekimoto Lab Research Introduction
社会連携研究部門デジタルスマートシティイニシアティブ紹介 / Social Cooperation Program for Digital Smart City Initiative Introduction
REO: Regional Economics Optimization
Left: Advancing Building Extraction in Thailand: Fine-tuning and Validation of YOLOv8 Segment Model on Open-source Data across Diverse Land Use Types
Center: Enhancing large-scale footprint extraction evaluation: a two-level approach with proxy data and optimized building-unit matching
Right: Label Freedom: Stable diffusion on Remote Sensing Semantic Segmentation Data Generation
HMS: Human Mobility Simulation
Left: Pseudo-PFLOW: A Nationwide Synthetic Open Dataset for People Flow based on Limited
Center: Estimation of carbon emissions due to car usage in Susono
Right: Spatial Attention Based Grid Representation Learning For Predicting Origin–Destination Flow
Left: 感染拡大リスクを下げるための携帯電話の活用に関する研究開発
Right: Deep Learning Approach to Logistics Trips Generation: Enhancing Pseudo-PFlow* with Agent-Based Modeling
DCBC: Digital City & Behavior Changes
Left: Enhancing geospatial retail analysis by integrating mobility behavior
Center: Development of A Citizen-oriented Web-based Regional Planning Support Tool: A Case Study in Susono City, Shizuoka
Right: Do open data impact citizens’ behavior? Assessing face mask panic buying behaviors during the Covid-19 pandemic
Left: Gender differences in income-based segregation level varies with family life cycle stage
Right: Mapping emotional geographical trends based on Japanese Tweets
MLI: Machine Learning based Image processing
Left: Vehicle re-identification and trajectory reconstruction using multiple moving cameras in the CARLA driving simulator
Center: Multinational advancements for AI-driven road inspection
Right: 建物に関する様々な計測データの3D都市モデルへの効率的なマッチング
Left: Are Utility Poles within Sight? Unleashing the Power of Vision for Effortless Roadside Management
Center: Road Rutting Detection using Deep Learning on Images
Right: Large-scale Urban Pavement Segment Model Reconstruction From Open-source Aerial Images