Exploring Sub-skeleton Trajectories for Interpretable Recognition of Sign Language
J Gudmundsson, MP Seybold, J Pfeifer - International Conference on …, 2022 - Springer
J Gudmundsson, MP Seybold, J Pfeifer
International Conference on Database Systems for Advanced Applications, 2022•SpringerRecent advances in tracking sensors and pose estimation software enable smart systems to
use trajectories of skeleton joint locations for supervised learning. We study the problem of
accurately recognizing sign language words, which is key to narrowing the communication
gap between hard and non-hard of hearing people. Our method explores a geometric
feature space that we call 'sub-skeleton'aspects of movement. We assess similarity of feature
space trajectories using natural, speed invariant distance measures, which enables clear …
use trajectories of skeleton joint locations for supervised learning. We study the problem of
accurately recognizing sign language words, which is key to narrowing the communication
gap between hard and non-hard of hearing people. Our method explores a geometric
feature space that we call 'sub-skeleton'aspects of movement. We assess similarity of feature
space trajectories using natural, speed invariant distance measures, which enables clear …
Abstract
Recent advances in tracking sensors and pose estimation software enable smart systems to use trajectories of skeleton joint locations for supervised learning. We study the problem of accurately recognizing sign language words, which is key to narrowing the communication gap between hard and non-hard of hearing people.
Our method explores a geometric feature space that we call ‘sub-skeleton’ aspects of movement. We assess similarity of feature space trajectories using natural, speed invariant distance measures, which enables clear and insightful nearest neighbor classification. The simplicity and scalability of our basic method allows for immediate application in different data domains with little to no parameter tuning.
We demonstrate the effectiveness of our basic method, and a boosted variation, with experiments on data from different application domains and tracking technologies. Surprisingly, our simple methods improve sign recognition over recent, state-of-the-art approaches.
Springer