prikaz prve stranice dokumenta Analiza vježbanja putem snimanja pokreta bez markera
  Download
PDF 1.27 MB
undergraduate thesis
Analiza vježbanja putem snimanja pokreta bez markera
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. urn:nbn:hr:200:498715
Leko, Ruža
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Leko, R. (2023). Analiza vježbanja putem snimanja pokreta bez markera (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:498715

Leko, Ruža. "Analiza vježbanja putem snimanja pokreta bez markera." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:498715

Leko, Ruža. "Analiza vježbanja putem snimanja pokreta bez markera." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:498715

Leko, R. (2023). 'Analiza vježbanja putem snimanja pokreta bez markera', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 27 November 2024, https://urn.nsk.hr/urn:nbn:hr:200:498715

Leko R. Analiza vježbanja putem snimanja pokreta bez markera [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 November 27] Available at: https://urn.nsk.hr/urn:nbn:hr:200:498715

R. Leko, "Analiza vježbanja putem snimanja pokreta bez markera", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:498715

Metadata
TitleAnaliza vježbanja putem snimanja pokreta bez markera
Title (english)Markerless motion capture exercise analysis
AuthorRuža Leko
MentorČaslav Livada (mentor)
Committee memberČaslav Livada (predsjednik povjerenstva)
Committee memberGoran Knežević (član povjerenstva)
Committee memberMirko Köhler (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2023-09-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
Zadatak ovog završnog rada je analizirati uspješnosti odrađivanja vježbe snimanjem pokreta bez markera u programskom jeziku Python. Za realizaciju programskog rješenja korištene su biblioteke MediaPipe, Scikit-learn i OpenCV. Pomoću MediaPipe biblioteke prikupljena su potrebna obilježja snimanja pokreta bez markera koja su korištena za treniranje modela za prepoznavanje vježbe algoritmom logističke regresije koji pruža Scikit-learn. Ostale funkcije uspoređuju izvođenje vježbe u stvarnom vremenu. Korištenjem spomenutih metoda ostvarena je aplikacija koja daje ocjenu ispravnosti izvođenja vježbe.
Abstract (english)
EXERCISE ANALYSIS USING MARKERLESS MOTION CAPTURE The task of this paper is to analyze performance using markerless motion capture in the Python programming language. To solve this problem, the MediaPipe, Scikit-learn, and OpenCV libraries, along with their functions, were used to improve the algorithm's performance. Using the MediaPipe library, the necessary landmarks were collected from markerless motion capture, which were then used to train a pose recognition model using the logistic regression algorithm provided by Scikit-learn. Other functions compare real-time exercise performance with the correct form of exercise. By employing these methods, an application was developed that grades the accuracy of exercises.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:498715
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-03-01 08:37:00