Regression-Based Landmark Detection on Dynamic Human Models

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 724
  • Download : 0
Detecting anatomical landmarks on various human models with dynamic poses remains an important and challenging problem in computer graphics research. We present a novel framework that consists of two-level regressors for finding correlations between human shapes and landmark positions in both body part and holistic scales. To this end, we first develop pose invariant coordinates of landmarks that represent both local and global shape features by using the pose invariant local shape descriptors and their spatial relationships. Our body part-level regression deals with the shape features from only those body parts that correspond to a certain landmark. In order to do this, we develop a method that identifies such body parts per landmark, by using geometric shape dictionary obtained through the bag of features method. Our method is nearly automatic, as it requires human assistance only once to differentiate the left and right sides. The method also shows the prediction accuracy comparable to or better than those of existing methods, with a test data set containing a large variation of human shapes and poses.
Publisher
WILEY-BLACKWELL
Issue Date
2017-10
Language
English
Article Type
Article; Proceedings Paper
Keywords

CANONICAL CORRELATION-ANALYSIS; 3D SHAPE RETRIEVAL; BAG-OF-FEATURES; RECOGNITION

Citation

COMPUTER GRAPHICS FORUM, v.36, no.7, pp.73 - 82

ISSN
0167-7055
DOI
10.1111/cgf.13273
URI
http://hdl.handle.net/10203/226831
Appears in Collection
GCT-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0