抄録
We propose the DeepPose-based pose estimation system that is flexible with the change of bounding-box range for top-view images. Our purpose is to link person detection system and pose estimation system. We introduce Bounding-box Curriculum Learning (BCL) and Recurrent Pose Estimation (RPE). BCL is a learning technique of CNN inspired from Curriculum Learning. RPE is a recurrent process of pose estimation that fixes the bounding-box range in response to the estimated results. We show the effect of proposed methods compared to normal learned CNN-based pose estimator on our original top-view dataset.
本文言語 | English |
---|---|
ホスト出版物のタイトル | 2016 IEEE 5th Global Conference on Consumer Electronics, GCCE 2016 |
出版社 | Institute of Electrical and Electronics Engineers Inc. |
ISBN(電子版) | 9781509023332 |
DOI | |
出版ステータス | Published - 2016 12月 27 |
イベント | 5th IEEE Global Conference on Consumer Electronics, GCCE 2016 - Kyoto, Japan 継続期間: 2016 10月 11 → 2016 10月 14 |
Other
Other | 5th IEEE Global Conference on Consumer Electronics, GCCE 2016 |
---|---|
国/地域 | Japan |
City | Kyoto |
Period | 16/10/11 → 16/10/14 |
ASJC Scopus subject areas
- 信号処理
- 電子工学および電気工学
- コンピュータ サイエンスの応用
- ハードウェアとアーキテクチャ
- 器械工学