¡¡Chinese Journal of Computers   Full Text
  TitleA New Method for Motion Retargeting for the Hand Gesture
  AuthorsGE Chun-Bao1),2) CHEN Yi-Qiang2) YIN Bao-Cai1) GAO Wen2) YANG Chang-Shui2)
  Address1)(Multimedia and Intelligent Software Technology Beijing Municipal Key Laboratory, Beijing University of Technology, Beijing 100022)
2)(Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100080)
  Abstract &
Abstract Existed motion retargeting algorithms mostly focused on the motion between the character and the environment and seldom considered the interaction among the segments of a character, especially for the hand gesture. In this paper a new method for motion retargeting for the hand gesture is proposed. Realistic and natural animations with similar meanings to the original can be produced through the way. First many sensitive points are defined on the human body, and key sensitive points and secondary sensitive points are selected through analyzing the importance of the sensitive points. Then a novel method based on the relative position of the original sensitive points is proposed to compute the target sensitive point position. Finally an adapted IK solver is utilized to realize the retargeting problem. Experimental results show that the proposed method dramatically improves the recognition rate of the Chinese sign language synthesis system about 30%.

keywords character animation; motion retargeting; key sensitive point; IK; Chinese Sign Language

background The project ¡°Multi-functional Perceptual Technology¡± is mainly engaged in the research of comprehensive advanced human-computer interface technology which integrates speech, gesture, feeling, and an important means for pervading computing technologies into the human society. This work is part of this project. It focuses on the research of the Chinese sign language synthesis system. It is a system using computer technology that translates text into animation of the virtual human in order to help hearing impaired people study sign language. For pursuing more harmonious interaction between human and the machine and applying it for more fields (for example, TV news broadcasting, internet, communication and film) they build many virtual human models for the users¡¯ choice. The task is to produce animations for different virtual human models with different sizes and proportions that express the same meanings and can be readily understood by members of the deaf population. Existed algorithms mostly focused on motion between the character and the environment and seldom considered interaction among the segments of a character. The authors has made studies on such fields and propose a new method which solved the retargeting problems for the hand gesture.