AI-powered multi-view boxing analytics system using Computer Vision, Pose Estimation, Tracking, Punch Detection, Tactical Modeling, and Sequential Strategy Analysis.
Explore ProjectThe Smart Boxer Analytics System is an advanced AI-driven sports analytics platform developed for boxing performance analysis using synchronized top-view and side-view cameras.
The system performs boxer tracking, pose estimation, punch classification, target zone detection, strategy inference, probabilistic sequence modeling, and occlusion handling using multi-view fusion.
The project integrates YOLO pose estimation, segmentation, Markov models, Gaussian HMMs, temporal motion analysis, and contextual sequence prediction to generate tactical insights for coaches and athletes.
Integrated top-view and side-view camera synchronization for robust boxer identification under occlusion and detection failure.
Detects Left/Right Hook, Jab, Cross, and Uppercut using shoulder-elbow-wrist kinematic analysis.
Identifies whether punches target the head or body using opponent pose keypoints and spatial mapping.
Detects defensive guard posture based on wrist-to-face spatial relationships.
Infers attacking, neutral, and defensive tactical states using motion, distance, punch tempo, and contextual behavior.
Uses opponent-conditioned probabilistic sequence modeling to predict next punch and strategic transitions.
Allied Vision cameras capture synchronized top-view and side-view sparring sessions.
YOLO Pose + Segmentation + ByteTrack perform real-time boxer tracking and identity consistency.
Extracts skeletal keypoints for punch mechanics, guard posture, and engagement analysis.
Punches are classified using arm trajectories, wrist velocity, and elbow angles.
Markov Models and sequence learning infer strategy transitions and opponent-conditioned actions.
Real-time overlays, punch counters, tactical indicators, and analytics dashboards are generated.
Improved punch recognition reliability using top-view + side-view fusion under referee and boxer occlusions.
Opponent-conditioned Markov models achieved promising next-punch prediction performance.
Offensive, defensive, and neutral tactical states inferred from continuous movement behavior.
Converts raw training videos into actionable tactical insights for athlete performance optimization.
Computer Vision, Sports Analytics, Human Pose Estimation, Tactical AI.
Indian Institute of Technology Madras (IIT Madras)
Elite boxing performance analysis, training analytics, tactical coaching assistance, and combat sports AI.