A Real-Time Collision Detection and Avoidance Algorithm for Fingerspelling Animation

In sign languages, people use hand gestures, facial expressions, and body language to communicate with deaf and hearing people. While the use of avatars for sign languages has emerged as a promising tool, portraying animations of fingerspelling has proved surprisingly resistant to automation because of the collisions that arise from conventional interpolation of keyframes of individual manual letters. Previous methods have not been able to provide convincingly realistic fingerspelling due to the absence of effective collision avoidance in the underlying animation algorithms. This paper reports on the development and evaluation of a new collision avoidance algorithm that aids fingerspelling. Instead of analysing letter transitions, the algorithm capitalises on the transitions of individual fingers. The new strategy is efficient enough to support real-time fingerspelling while still maintaining a high level of predictive accuracy. Utilising this strategy in designing signing avatars is expected to improve current resources for anyone who wants to enhance their fingerspelling skills and comprehension. A new algorithm has been developed, trained on American Sign Language datasets, and tested on other one-handed systems of fingerspelling such as Arabic Sign Language (ArSL) and Langue des Signes Française (LSF). The new algorithm can be incorporated into a real-time avatar, making it suitable for use in fingerspelling learning and practice aids. The algorithm was designed to be independent of language. Future work will include testing the strategy’s generality when applying it to other one-handed manual alphabets.