DEPTH DATA-DRIVEN REAL-TIME ARTICULATED HAND POSE RECOGNITION
- DEPTH DATA-DRIVEN REAL-TIME ARTICULATED HAND POSE RECOGNITION
- 차영운; 임화섭; 성민혁; 안상철
- depth data; hand pose recognition
- Issue Date
- Lecture notes in computer science
- VOL 8888, 492-501
- This paper presents a fast but robust method to recognize articulated hand pose from single depth images in real-time. We tackle the main challenges in the hand pose recognition, which include the high degree of freedom and self-occlusion of articulated hand motion, using e cient retrieval of a large set of hand pose templates. The normalized orientation templates are used for encoding the depth images containing hand poses, and the locality sensitive hashing is used for nding the nearest neighbors in real time. Our approach does not su er from the common problems in the conventional tracking approaches such as model initialization and tracking drift, and qualitatively outperforms the existing hand pose estimation techniques.
- Appears in Collections:
- KIST Publication > Article
- Files in This Item:
There are no files associated with this item.
- RIS (EndNote)
- XLS (Excel)
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.