Prayook Jatesiktat

Title: Prayook Jatesiktat: Advancing 3D Motion Capture and Keypoint Detection

Introduction

Prayook Jatesiktat is an inventor associated with Nanyang Technological University in Singapore. His patent work focuses on generating training data for keypoint detection and predicting the three-dimensional locations of virtual markers on subjects without physical markers.

Latest Patents

Jatesiktat is named on 1 patent: “Method and System for Generating a Training Dataset for Keypoint Detection, and Method and System for Predicting 3D Locations of Virtual Markers on a Marker-Less Subject.”

The invention combines an optical marker-based motion-capture system with video cameras that record synchronized image sequences. Markers placed on a subject’s bone landmarks are captured as three-dimensional trajectories. A computer projects those trajectories onto the images to determine marker locations, interpolates three-dimensional positions, and creates bounding boxes around the subject. The resulting dataset pairs images with marker locations and bounding boxes for training a keypoint-detection system. The patent also describes using a neural network trained on this dataset to predict the three-dimensional locations of virtual markers on a marker-less subject.

Career Highlights

Jatesiktat’s listed patent reflects work at the intersection of motion capture, computer vision, and machine learning. The approach aims to support three-dimensional pose estimation without requiring physical markers during later analysis.

Collaborations

The patent’s listed collaborators include Wei Tech Ang and Wee Sen Lim. Jatesiktat is associated with Nanyang Technological University.

Conclusion

Prayook Jatesiktat’s patent describes a data-generation and neural-network approach that connects marker-based motion capture with marker-less three-dimensional tracking.