Details

Automatic motion analysis of a gymnast in rhythmic gymnastics
ID Kolar, Maja (Author), ID Skočaj, Danijel (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (16,56 MB)
MD5: 7DC6E17A42F6424C2DCC458B6F93FF32

Abstract
Rhythmic gymnastics requires precise execution of complex movements, yet objective motion analysis and evaluation remain limited and largely dependent on human judgment. This thesis addresses this challenge through automatic motion analysis of Body Difficulty (BD) elements, defined by measurable body positions. We propose a modular pipeline that integrates 2D keypoint detection, 3D pose estimation, action recognition, and temporal segmentation to provide a structured breakdown of routines. On top of motion analysis, we explore grading of execution quality with a regression model. Experimental results show that the pipeline reliably detects and classifies BD elements, achieving strong performance at both the movement type and subtype level. Implemented methods robustly segment full routines, while the grading model, though limited by data, demonstrates the potential of extending motion analysis toward more objective evaluation in rhythmic gymnastics.

Language:English
Keywords:deep neural networks, computer vision, rhythmic gymnastics, pose estimation, movement classification, automatic scoring, machine learning
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FRI - Faculty of Computer and Information Science
Year:2025
PID:20.500.12556/RUL-174285 This link opens in a new window
COBISS.SI-ID:255322627 This link opens in a new window
Publication date in RUL:30.09.2025
Views:901
Downloads:416
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:Slovenian
Title:Avtomatska analiza gibanja telovadke v ritmični gimnastiki
Abstract:
Ritmična gimnastika zahteva natančno izvedbo kompleksnih gibov, vendar sta objektivna analiza gibanja in ocenjevanje še vedno omejena ter v veliki meri odvisna od človeške presoje. V tem delu se osredotočamo na avtomatsko analizo gibanja elementov telesne zahtevnosti (BD), ki so opredeljeni z merljivimi telesnimi položaji. Predlagamo modularen cevovod, ki združuje detekcijo 2D ključnih točk, 3D rekonstrukcijo poze, prepoznavanje gibov in časovno segmentacijo ter tako omogoča strukturirano razčlenitev vaj. Na osnovi analize gibanja raziskujemo tudi ocenjevanje kakovosti izvedbe z regresijskim modelom. Eksperimentalni rezultati kažejo, da cevovod zanesljivo zaznava in razvršča BD elemente ter učinkovito razpoznava tipe in podtipe gibov. Implementirane metode omogočajo robustno segmentacijo celotnih vaj, model za ocenjevanje pa, kljub omejeni količini podatkov, kaže potencial za nadgradnjo analize gibanja v smeri bolj objektivnega ocenjevanja v ritmični gimnastiki.

Keywords:globoke nevronske mreže, računalniški vid, ritmična gimnastika, ocenjevanje telesne drže, klasifikacija gibov, samodejno ocenjevanje, strojno učenje

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back