From sports & exercise science to AI. I am Takashi Fukushima, a researcher and developer working across sports & exercise science, motion capture, and computer vision. My work focuses on markerless human pose estimation and AI-driven movement analysis, alongside XR development with Unity and Meta Quest.
Latest articles
- 3D Markerless Motion Capture: Which Setup? 3 Approaches Compared
Three ways to capture 3D movement without markers — single-camera AI depth, a depth sensor, or multiple cameras. Here’s how they compare on accuracy, cost, and setup, and how to choose. - Which Pose-Estimation Model Is Most Accurate? 6 Models vs the Gold Standard (VICON)
We benchmarked pose estimation accuracy across six models — MediaPipe, MeTRAbs, YOLO and MoveNet — against the VICON gold standard. Two clear tiers emerged; here’s which to use, and when. - Can AI Match the Gold Standard? Human Pose Estimation vs Marker-Based Motion Capture
Can markerless pose estimation replace marker-based motion capture in sports? Our validation study found a ~10-degree mean joint-angle difference — invisible to the eye, but too much for clinical precision. Here’s what that means. - Motion Capture & Performance Analysis (a foundational overview)
A foundational overview: marker-based vs markerless pose estimation, the OpenPose/MediaPipe/MeTRAbs coordinate systems, ~10 degree accuracy and why errors happen, kinematics vs kinetics, capture frameworks, and a single-camera to OpenSim example. - How To Use OpenPose and OpenCap (free markerless motion capture)A practical getting-started guide to two free markerless motion-capture tools: OpenPose (install the demo, fix the models, run it) and OpenCap (2 iOS cameras, calibration, and 3D capture).
- The Math Behind Joint Angle Calculation (why atan2 works)The math behind atan2d(det, dot): the determinant is the cross-product magnitude (|a||b|sin), the dot product is |a||b|cos, so their ratio is tan – and why the two-argument atan2 preserves sign and handles angles beyond 90 degrees.
Focus areas
- Human Pose Estimation (MediaPipe, OpenPose, latest methods)
- Motion Capture & Sports Biomechanics
- Computer Vision & AI movement analysis
- XR / Metaverse development with Unity & Meta Quest
プロフィール
Takashi Fukushima です。スポーツ科学・運動化学・モーションキャプチャ・コンピュータビジョンを横断して研究と開発を行っています。マーカーレスの姿勢推定（Human Pose Estimation）や AI を用いた動作分析を中心に、Unity・Meta Quest を使った XR 開発にも取り組んでいます。
研究・専門分野
- 姿勢推定 / Human Pose Estimation
- モーションキャプチャ・スポーツバイオメカニクス
- コンピュータビジョン・AI 動作分析
- Unity・Meta Quest を使った XR / メタバース開発
Links
- YouTube: Takashi Fukushima｜Sports Science & Pose Estimation
- GitHub: coming soon
- Papers: ORCID
- LinkedIn: coming soon
- Contact: coming soon