Character‐Object Interaction Retrieval using the Interaction Bisector Surface

• Published in: Computer graphics forum Vol. 36; no. 2; pp. 119 - 129
• Main Authors: Zhao, X., Choi, M.G., Komura, T.
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.05.2017
• Subjects: Body parts; Categories and Subject Descriptors (according to ACM CCS); Classification; Computer graphics; I.3.7 [Computer Graphics]: Three‐Dimensional Graphics and Realism—Animation; Image retrieval; Motion planning; Object recognition; Robot dynamics; Robotics
• ISSN: 0167-7055; 1467-8659
• DOI: 10.1111/cgf.13112

In this paper, we propose a novel approach for the classification and retrieval of interactions between human characters and objects. We propose to use the interaction bisector surface (IBS) between the body and the object as a feature of the interaction. We define a multi‐resolution representation of the body structure, and compute a correspondence matrix hierarchy that describes which parts of the character's skeleton take part in the composition of the IBS and how much they contribute to the interaction. Key‐frames of the interactions are extracted based on the evolution of the IBS and used to align the query interaction with the interaction in the database. Through the experimental results, we show that our approach outperforms existing techniques in motion classification and retrieval, which implies that the contextual information plays a significant role for scene and interaction description. Our method also shows better performance than other techniques that use features based on the spatial relations between the body parts, or the body parts and the object. Our method can be applied for character motion synthesis and robot motion planning.