Search

We propose an environment for assisting in the transfer of motor skills by supporting nonverbal communication with wearable haptic technology. The proposed setting comprises a human expert and several learners, all endowed with wearable devices. Learners benefit from the automated feedback obtained via wearable technology regarding a desired move relevant to a specific motor skill. Similarly, the expert benefits from automated means to provide instructions to the learner as well as from monitoring data provided by wearable devices. We focus on tactile communication as the basis for this interaction, thus supporting users who are not able to rely on other senses that are relevant to most motor skill-related tasks, such as sight and hearing. We discuss leader-follower dance as a motor skill context in order to instantiate and validate critical components of our skill transfer environment, using accelerometers and gyroscopes as the basis for sensing movements. In this particular scenario, our approach focuses on the haptic communication elements needed to perform a leader-follower dance, assessing movements by the learners in response to the intent of the expert. In order to validate our approach, we have prototyped and conducted experiments with the three critical components of our environment that enables tactile communication between experts and learners. Our development is informed by user research conducted with expert dance teachers, through which we gathered expert dance moves that resulted in a reference database that makes up one of the components that are critical to demonstrate the potential of our proposed environment. We also implemented a tactile encoder that is used to send movement instructions to learners through the sense of touch, as well as an autonomous classifier that uses the reference database as input. Overall, our results provide a roadmap for building an environment for skill transfer using nonverbal communication based on haptic wearable devices. [ABSTRACT FROM AUTHOR]

In computer graphics, various processing operations are applied to 3D triangle meshes and these processes often involve distortions, which affect the visual quality of surface geometry. In this context, perceptual quality assessment of 3D triangle meshes has become a crucial issue. In this paper, we propose a new objective quality metric for assessing the visual difference between a reference mesh and a corresponding distorted mesh. Our analysis indicates that the overall quality of a distorted mesh is sensitive to the distortion distribution. The proposed metric is based on a spatial pooling strategy and statistical descriptors of the distortion distribution. We generate a perceptual distortion map for vertices in the reference mesh while taking into account the visual masking effect of the human visual system. The proposed metric extracts statistical descriptors from the distortion map as the feature vector to represent the overall mesh quality. With the feature vector as input, we adopt a support vector regression model to predict the mesh quality score.We validate the performance of our method with three publicly available databases, and the comparison with state-of-the-art metrics demonstrates the superiority of our method. Experimental results show that our proposed method achieves a high correlation between objective assessment and subjective scores. [ABSTRACT FROM AUTHOR]