Detailed Information
Cited 0 time in 
Cited 0 time in 
Cited 0 time in
Metadata Downloads
단계적 딥러닝 네트워크 학습 방법을 통한 3차원 관절 좌표 추정Deep Learning Network Two-Stage Learning Method for 3D Pose Estimation
- Other Titles
- Deep Learning Network Two-Stage Learning Method for 3D Pose Estimation
- Issue Date
- Nov-2019
- Publisher
- 대한전자공학회
- Citation
- 2019년 대한전자공학회 추계학술대회 논문집, pp.431 - 435
- Indexed
- OTHER
- Journal Title
- 2019년 대한전자공학회 추계학술대회 논문집
- Start Page
- 431
- End Page
- 435
- Abstract
- 3D pose estimation is a study of estimating human 3D joints from a single image, and it is widely used in industrial fields and applications. The performance of 3D pose estimation has dramatically improved with the deep learning. However, the lack of 3D data has always been a constant problem. To solve this issue, we propose multi-stage learning method that uses both 2D and 3D datasets. We achieved 92.0% accuracy with Human3.6M dataset and obtained natural 3D pose results on outdoor images.
- Files in This Item
- Go to Link
- Appears in
Collections - COLLEGE OF COMPUTING > SCHOOL OF COMPUTER SCIENCE > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.