Difficulty Classification of Moonboard Bouldering Problems – Bc. Eduard Minks
Bc. Eduard Minks
Bachelor's thesis
Difficulty Classification of Moonboard Bouldering Problems
Difficulty Classification of Moonboard Bouldering Problems
Abstract:
Cílem této práce je aplikovat existující přístupy hlubokého učení na úkol klasifikace stupně obtížnosti boulderingových problémů postavených na standardizované lezecké stěně MoonBoard. Pro klasifikaci obtížnosti jednotlivých cest jsou použity čtyři různé datové modality i) videa lezce, který leze daný problém ii) sekvence koster extrahovaná z oněch videí iii) podrobné, člověkem čitelné topografické …moreAbstract:
This work aims to apply existing approaches of deep learning to the task of the difficulty grade assignment to the bouldering problems set on a standardized MoonBoard wall. Four distinct modalities are used to classify the grade of bouldering problems: i) videos of climber climbing the problem, ii) skeleton sequences extracted from such videos, iii) detailed human-readable topographical images with …more
Language used: English
Date on which the thesis was submitted / produced: 15. 12. 2022
Identifier:
https://is.muni.cz/th/hhnxm/
Thesis defence
- Date of defence: 1. 2. 2023
- Supervisor: RNDr. Petr Eliáš, Ph.D.
- Reader: RNDr. Jakub Peschel
Citation record
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 InformaticsBachelor programme / field:
Informatics / Informatics
Theses on a related topic
-
Movement-Based Sentiment Classification in Human Interactions
Maroš Dubíny -
Evaluation of Human Pose Estimation Methods in Video Data
Zuzana Tunegová -
Automatic Human Pose Estimation using Neural Network
Jakub STRAKA -
Detection and correction of errors in human motion data
Dávid Rusnák -
Recognition and Classification Methods for Collection of Images
Martin Wenzl