University of Twente Student Theses

Login
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.

Validation of a Monocular Computer Vision System for Basketball Shot Performance Analysis

Maare, Noah van (2025) Validation of a Monocular Computer Vision System for Basketball Shot Performance Analysis.

[img] PDF
11MB
Abstract:Analyzing basketball shot kinematics is crucial for improving player tech niques and understanding motor skill adaptation, yet current high-fidelity motion capture systems are often inaccessible. This study presents the devel opment andvalidation of a novel computer vision system designed to extract detailed shot kinematics of a basketball from a single, readily available cam era. The system employs a multi-stage pipeline, including object detection, pose estimation, a hybrid approach combining heuristics and a machine learning model for release event identification, and physics-based 3D trajec tory reconstruction in a calibrated World Coordinate System. The system’s accuracy in determining release parameters (position, time, initial velocity, and angles) and reconstructing free-flight trajectories is evaluated against an OptiTrack motion capture system. The findings quantify the system’s performance, highlighting its potential as an accessible tool for data-driven coaching, sports science research, and potentially for future investigations into complex motor control phenomena like functional solution manifolds in basketball shooting.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:https://purl.utwente.nl/essays/107322
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page