Pose capturing and evaluation in a VR environment

Name: Karn Kiattikunrat

LCSH: Kasetsart University -- Theses. M.Eng. (Artificial Intelligence and Internet of Things) 2023

Classification :.LCCS: TA1637

LCSH: Kasetsart University. -- Department of Electrical Engineering -- Theses

LCSH: Image processing

LCSH: Virtual reality

LCSH: Pattern recognition systems

Abstract: This proposed method contributes to the existing body of knowledge and lays a strong foundation for future advancements in the field of VR-based pose analysis and interaction. As the technology continues to evolve, it is expected that further improvements and innovations will emerge, further enhancing the capabilities and applications of pose capturing and evaluation in VR environments. In this study, we introduce an innovative method for evaluating and comparing human postures by harnessing the power of optical motion capture and virtual reality (VR) technologies. Our cutting-edge pose matching algorithm enables users to refine their performance by providing real-time feedback on their postural alignment with a template pose. Capitalizing on the high accuracy and low latency of optical motion capture systems, our approach records detailed posture information, including time stamps, frame indices, and the orientation and position of multiple body joints in Cartesian coordinates. The algorithm computes a similarity score between the user's pose and the template by calculating a normalized loss function based on their 3D posture data. We seamlessly integrate the evaluation model into a VR environment tailored for posture imitation exercises. The template pose is pre-recorded, and the user's pose is dynamically synchronized with the physical world, visualized as an interactive 3D humanoid model within the virtual space. As users mimic the displayed postures and movements, the system generates instantaneous feedback on the similarity score, empowering them to refine their technique and enhance their performance, all within a safe and immersive virtual setting. As a result, we have developed a versatile VR application that successfully compares the similarity of postures and provides users with valuable feedback to improve their skills. The application demonstrates the efficacy of our pose matching algorithm and serves as a foundation for further development and expansion into various domains, including sports training, rehabilitation, and performance arts.

Kasetsart University. Office of the University Library

Address: Bangkok

Email: tdckulib@ku.ac.th

Name: Chowarit Mitsantisuk

Role: Thesis Advisor

Name: Shoichi Hasegawa

Role: Thesis CO-Advisor

Created: 2023

Modified: 2025-07-23

Issued: 2025-07-23

วิทยานิพนธ์/Thesis

application/pdf

URL: https://www.lib.ku.ac.th/KUthesis/2566/karn-kia-all.pdf

CallNumber: TA1637 .K38

eng

DegreeName: Master of Engineering

Level: Master's Degree

Descipline: Artificial Intelligence and Internet of Things

Grantor: Kasetsart University

©copyrights Kasetsart University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	karn-kia-all.pdf	2.35 MB

ใช้เวลา

0.01966 วินาที