Vision-based feature extraction and analysis of a synchronized swimmer

Vision-based feature extraction of a synchronized swimmer doing figures was done in hopes of correcting and improving synchronized swimmers ability to do figures. Extracted feature through image processing techniques plays an important role in understanding the synchronized swimmers body kinematics....

Full description

Saved in:
Bibliographic Details
Main Author: Ong, Prane Mariel B.
Format: text
Language:English
Published: Animo Repository 2009
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/etd_masteral/3812
https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10650/viewcontent/CDTG004663_P.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
Language: English
id oai:animorepository.dlsu.edu.ph:etd_masteral-10650
record_format eprints
spelling oai:animorepository.dlsu.edu.ph:etd_masteral-106502024-01-31T07:02:36Z Vision-based feature extraction and analysis of a synchronized swimmer Ong, Prane Mariel B. Vision-based feature extraction of a synchronized swimmer doing figures was done in hopes of correcting and improving synchronized swimmers ability to do figures. Extracted feature through image processing techniques plays an important role in understanding the synchronized swimmers body kinematics. A member of the synchroswan team performed three types of figures synchronized swimming. These are Porpoise, Neptunus and Ballerina. In gathering data, two cameras were used to video capture the swimmers movements. One was stationed at a calculated distance above the water, and the other camera was placed underwater directly above other camera. Image processing was done not in real time under the Matlab environment. Threshold limits were empirically extracted base from skin color region and it serve as a tool to feature extract the foreground from the background. Centroid of each column or row data was measured producing a segmental outline of the body. This is analogous to a stick figure representation of the swimmer. Toe-ankle segment, ankle-knee segment, kneehip segment and hip-shoulder segment were the anatomical segments that were observed. Centroid measurements were done only at the figure transitions indicated by the FINA Manual for Synchronized Swimming. From the centroid values, two points were extracted per segment to be used in angle calculation. The calculated angle, angular velocity and angular acceleration of each body segments were used to analyze the swimmers motion. Systematic error and random errors were also considered and noted. Angle information became an indicative factor of whether the sychro swimmer did hit a specific figure transition or not. These collected data are essential in analyzing the synchro swimmers performance. 2009-01-01T08:00:00Z text application/pdf https://animorepository.dlsu.edu.ph/etd_masteral/3812 https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10650/viewcontent/CDTG004663_P.pdf Master's Theses English Animo Repository Synchronized swimmers Synchronized swimming Swimming Physics
institution De La Salle University
building De La Salle University Library
continent Asia
country Philippines
Philippines
content_provider De La Salle University Library
collection DLSU Institutional Repository
language English
topic Synchronized swimmers
Synchronized swimming
Swimming
Physics
spellingShingle Synchronized swimmers
Synchronized swimming
Swimming
Physics
Ong, Prane Mariel B.
Vision-based feature extraction and analysis of a synchronized swimmer
description Vision-based feature extraction of a synchronized swimmer doing figures was done in hopes of correcting and improving synchronized swimmers ability to do figures. Extracted feature through image processing techniques plays an important role in understanding the synchronized swimmers body kinematics. A member of the synchroswan team performed three types of figures synchronized swimming. These are Porpoise, Neptunus and Ballerina. In gathering data, two cameras were used to video capture the swimmers movements. One was stationed at a calculated distance above the water, and the other camera was placed underwater directly above other camera. Image processing was done not in real time under the Matlab environment. Threshold limits were empirically extracted base from skin color region and it serve as a tool to feature extract the foreground from the background. Centroid of each column or row data was measured producing a segmental outline of the body. This is analogous to a stick figure representation of the swimmer. Toe-ankle segment, ankle-knee segment, kneehip segment and hip-shoulder segment were the anatomical segments that were observed. Centroid measurements were done only at the figure transitions indicated by the FINA Manual for Synchronized Swimming. From the centroid values, two points were extracted per segment to be used in angle calculation. The calculated angle, angular velocity and angular acceleration of each body segments were used to analyze the swimmers motion. Systematic error and random errors were also considered and noted. Angle information became an indicative factor of whether the sychro swimmer did hit a specific figure transition or not. These collected data are essential in analyzing the synchro swimmers performance.
format text
author Ong, Prane Mariel B.
author_facet Ong, Prane Mariel B.
author_sort Ong, Prane Mariel B.
title Vision-based feature extraction and analysis of a synchronized swimmer
title_short Vision-based feature extraction and analysis of a synchronized swimmer
title_full Vision-based feature extraction and analysis of a synchronized swimmer
title_fullStr Vision-based feature extraction and analysis of a synchronized swimmer
title_full_unstemmed Vision-based feature extraction and analysis of a synchronized swimmer
title_sort vision-based feature extraction and analysis of a synchronized swimmer
publisher Animo Repository
publishDate 2009
url https://animorepository.dlsu.edu.ph/etd_masteral/3812
https://animorepository.dlsu.edu.ph/context/etd_masteral/article/10650/viewcontent/CDTG004663_P.pdf
_version_ 1789971896150786048