Camera System for Movement Analysis
Kamerový systém pro analýzu pohybu
Authors
Supervisors
Reviewers
Editors
Other contributors
Journal Title
Journal ISSN
Volume Title
Publisher
České vysoké učení technické v Praze
Czech Technical University in Prague
Czech Technical University in Prague
Date
Abstract
Cílem práce je vytvořit aplikaci v softwarovém prostředí MATLAB pro analýzu pohybu s využitím dvou kamer. Dvě synchronizované videosekvence jsou získány z dvou kamer s full HD rozlišením, kde jsou označeny anatomicky významné body modrými značkami. Videosekvence se zpracovávají off-line s využitím metod počítačového vidění, zpracování obrazu a rozpoznávání obrazu. Aplikace se skládá z modulárního systému, který obsahuje barevnou kalibraci, kalibraci kamery, detekci značek, stereo kalibraci, 3D rekonstrukci a analýzu pohybu. Barevná kalibrace provádí převod (vícenásobná lineární regrese, lineární a Hermitova interpolace) z nekalibrovaného obrazu do RGB standardu. Detekce značek určí souřadnice značek použitím metod predikováním oblastí, multispektrálním prahováním, iterativním prahováním, prahováním metodou nejmenší chyby, Houghovy transformace, učením bez učitele s EM algoritmem a K-means. Kalibrace kamery, stereo kalibrace a 3D rekonstrukce slouží k získání vnitřních a vnějších parametrů kamery pro projekci z 2D do 3D prostoru. Analýza pohybu poskytuje základní charakteristiky pohybu.
The goal of this work is to create an application for 3D motion analysis by using two cameras in the MATLAB software environment. Two synchronized video sequences are obtained from the two cameras with high definition (full HD) resolution, in which anatomically significant points have been labeled by blue markers. These video sequences are used for off-line processing by the means of computer vision, image processing and pattern recognition. The application consists of a modular system, which contains color calibration, camera calibration, marker detection, stereo calibration, 3D reconstruction and motion analysis. Color calibration transforms (using multiple linear regression, linear and Hermite interpolating) the uncalibrated image to the RGB standard. Marker detection detects the coordinates of the markers using methods such as region prediction, multispectral thresholding, iterative thresholding, minimum error thresholding, Hough transform, unsupervised learning with Expectation-Maximization algorithm and K-means. Camera calibration, stereo calibration and 3D reconstruction result in obtaining the intrinsic and extrinsic camera parameters for the projection from 2D to 3D space. Motion analysis provides the basic characteristics of motion.
The goal of this work is to create an application for 3D motion analysis by using two cameras in the MATLAB software environment. Two synchronized video sequences are obtained from the two cameras with high definition (full HD) resolution, in which anatomically significant points have been labeled by blue markers. These video sequences are used for off-line processing by the means of computer vision, image processing and pattern recognition. The application consists of a modular system, which contains color calibration, camera calibration, marker detection, stereo calibration, 3D reconstruction and motion analysis. Color calibration transforms (using multiple linear regression, linear and Hermite interpolating) the uncalibrated image to the RGB standard. Marker detection detects the coordinates of the markers using methods such as region prediction, multispectral thresholding, iterative thresholding, minimum error thresholding, Hough transform, unsupervised learning with Expectation-Maximization algorithm and K-means. Camera calibration, stereo calibration and 3D reconstruction result in obtaining the intrinsic and extrinsic camera parameters for the projection from 2D to 3D space. Motion analysis provides the basic characteristics of motion.