Mapping 2D Skeleton Sequences from Speed Climbing Videos onto a Virtual Reference Wall – Bc. Jan Pokorný
Bc. Jan Pokorný
Master's thesis
Mapping 2D Skeleton Sequences from Speed Climbing Videos onto a Virtual Reference Wall
Mapping 2D Skeleton Sequences from Speed Climbing Videos onto a Virtual Reference Wall
Abstract:
Lezení na rychlost je olympijský sport s rostoucím zájmem o automatickou analýzu výkonů. Navrhujeme, implementujeme a evaluujeme proces pro výpočet transformací videí lezení na rychlost na referenční zeď. Nejdříve je natrénován object detection model pro úkol detekce chytů. Dále jsou tyto detekce sledovány pomocí optických toků, a asociovány k referenční zdi pomocí algoritmu Coherent Point Drift. Nakonec …moreAbstract:
Speed climbing is an Olympic sport with a growing interest in automatic performance analysis. We design, implement and evaluate a pipeline to compute transformations of speed climbing videos to a reference wall. First, an object detection model is fine-tuned for the task of hold detection. Next, the detections are tracked using optical flow and associated to the reference wall using Coherent Point …more
Language used: English
Date on which the thesis was submitted / produced: 18. 5. 2021
Identifier:
https://is.muni.cz/th/zp7vz/
Thesis defence
- Date of defence: 25. 6. 2021
- Supervisor: RNDr. Petr Eliáš, Ph.D.
- Reader: RNDr. Petra Budíková, Ph.D.
Citation record
ISO 690-compliant citation record:
POKORNÝ, Jan. \textit{Mapping 2D Skeleton Sequences from Speed Climbing Videos onto a Virtual Reference Wall}. Online. Master's thesis. Brno: Masaryk University, Faculty of Informatics. 2021. Available from: https://theses.cz/id/a3xdnn/.
Full text of thesis
Contents of on-line thesis archive
Published in Theses:- světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Computer systems, communication and security / Software systems
Theses on a related topic
-
Deep Learning for Object Detection
Radoslav Pitoňák -
Fast object detection on mobile platforms using neural networks
Tomáš Repák -
Static object detection from visualisation of moving objects
Martin Kostka -
Evaluation of Self-Supervised Learning for Vehicle-Type Detection in Autonomous Driving
Manaf AHMED -
Labeled Dataset of Speed Climbing Performances
Veronika Škvarlová -
Analyzing Data Lakehouse: The Latest Evolution of Big Data Architectures and Its Benefits for Data Science
Ondřej Holub -
Data Quality Management in Data Integration
Rithy Ly -
Overview and Analysis of Data Vault 2.0 - Flexible Data Warehousing Methodology
Adam Hospodka