Premium
Perceptual 3D pose distance estimation by boosting relational geometric features
Author(s) -
Chen Cheng,
Zhuang Yueting,
Xiao Jun,
Liang Zhang
Publication year - 2009
Publication title -
computer animation and virtual worlds
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.225
H-Index - 49
eISSN - 1546-427X
pISSN - 1546-4261
DOI - 10.1002/cav.297
Subject(s) - artificial intelligence , computer science , pose , similarity (geometry) , boosting (machine learning) , pattern recognition (psychology) , perception , adaboost , computer vision , feature (linguistics) , set (abstract data type) , image (mathematics) , classifier (uml) , linguistics , philosophy , neuroscience , biology , programming language
Traditional pose similarity functions based on joint coordinates or rotations often do not conform to human perception. We propose a new perceptual pose distance: Relational Geometric Distance that accumulates the differences over a set of features that reflects the geometric relations between different body parts. An extensive relational geometric feature pool that contains a large number of potential features is defined, and the features effective for pose similarity estimation are selected using a set of labeled data by Adaboost. The extensive feature pool guarantees that a wide diversity of features is considered, and the boosting ensures that the selected features are optimized when used jointly. Finally, the selected features form a pose distance function that can be used for novel poses. Experiments show that our method outperforms others in emulating human perception in pose similarity. Our method can also adapt to specific motion types and capture the features that are important for pose similarity of a certain motion type. Copyright © 2009 John Wiley & Sons, Ltd.