This inventor holds 1 USPTO granted patent. Top assignee: Seiko Epson Corporation. Active years: 2021.
Company Filing History:
Years Active: 2021
Title: Juhan Bae: Innovator in Object Detection Algorithms
Introduction
Juhan Bae is a notable inventor based in North York, Canada. He has made significant contributions to the field of computer vision, particularly in the development of methods for training object detection algorithms. His innovative approach utilizes synthetic images to enhance the performance of these algorithms.
Latest Patents
Juhan Bae holds a patent for "Methods and systems for training an object detection algorithm using synthetic images." This patent describes a non-transitory computer-readable medium that embodies instructions for processors to perform a method. The method includes selecting a 3D model corresponding to an object and generating domain-adapted images of the 3D model at various poses. It also involves acquiring 2D projections of 3D points on a bounding box defined around the 3D model and training an algorithm model to learn correspondences between the generated images and the corresponding 2D projections. This innovative method is crucial for improving the accuracy and efficiency of object detection systems.
Career Highlights
Juhan Bae is currently employed at Seiko Epson Corporation, where he continues to work on advancements in technology related to imaging and object detection. His expertise in this area has positioned him as a valuable asset to his team and the company.
Collaborations
Throughout his career, Juhan has collaborated with talented individuals such as Dibyendu Mukherjee and Bowen Chen. These collaborations have fostered a creative environment that encourages innovation and the sharing of ideas.
Conclusion
Juhan Bae is a prominent figure in the field of object detection algorithms, with a focus on utilizing synthetic images for training purposes. His contributions through patents and collaborations highlight his commitment to advancing technology in this area.