Motion capture of signs provides unique challenges in the field of multimodal data collection. The dense packaging of visual information requires high fidelity and high bandwidth of the captured data. Even though marker-based optical motion capture provides many desirable features such as high accuracy, global fitting, and the ability to record body and face simultaneously, it is not widely used to record finger motion, especially not for articulated and syntactic motion such as signs. Instead, most signing avatar projects use costly instrumented gloves, which require long calibration procedures. In this article, we evaluate the data quality obtained from optical motion capture of isolated signs from Swedish sign language with a large number of low-cost cameras. We also present a novel dual-sensor approach to combine the data with low-cost, five-sensor instrumented gloves to provide a recording method with low manual postprocessing. Finally, we evaluate the collected data and the dual-sensor approach as transferred to a highly stylized avatar. The application of the avatar is a game-based environment for training Key Word Signing (KWS) as augmented and alternative communication (AAC), intended for children with communication disabilities.

Passive optical motion capture is one of the predominant technologies for capturing high fidelity human motion, and is a workhorse in a large number of areas such as bio-mechanics, film and video games. While most state-of-the-art systems can automatically identify and track markers on the larger parts of the human body, the markers attached to the fingers and face provide unique challenges and usually require extensive manual cleanup. In this work we present a robust online method for identification and tracking of passive motion capture markers attached to non-rigid structures. The method is especially suited for large capture volumes and sparse marker sets. Once trained, our system can automatically initialize and track the markers, and the subject may exit and enter the capture volume at will. By using multiple assignment hypotheses and soft decisions, it can robustly recover from a difficult situation with many simultaneous occlusions and false observations (ghost markers). In three experiments, we evaluate the method for labeling a variety of marker configurations for finger and facial capture. We also compare the results with two of the most widely used motion capture platforms: Motion Analysis Cortex and Vicon Blade. The results show that our method is better at attaining correct marker labels and is especially beneficial for real-time applications.

Speech and gesture co-occur in spontaneous dialogue in a highly complex fashion. There is a large variability in the motion that people exhibit during a dialogue, and different kinds of motion occur during different states of the interaction. A wide range of multimodal interface applications, for example in the fields of virtual agents or social robots, can be envisioned where it is important to be able to automatically identify gestures that carry information and discriminate them from other types of motion. While it is easy for a human to distinguish and segment manual gestures from a flow of multimodal information, the same task is not trivial to perform for a machine. In this paper we present a method to automatically segment and label gestural units from a stream of 3D motion capture data. The gestural flow is modeled with a 2-level Hierarchical Hidden Markov Model (HHMM) where the sub-states correspond to gesture phases. The model is trained based on labels of complete gesture units and self-adaptive manipulators. The model is tested and validated on two datasets differing in genre and in method of capturing motion, and outperforms a state-of-the-art SVM classifier on a publicly available dataset.

In this paper we study the production and perception of speech in diverse conditions for the purposes of accurate, flexible and highly intelligible talking face animation. We recorded audio, video and facial motion capture data of a talker uttering a,set of 180 short sentences, under three conditions: normal speech (in quiet), Lombard speech (in noise), and whispering. We then produced an animated 3D avatar with similar shape and appearance as the original talker and used an error minimization procedure to drive the animated version of the talker in a way that matched the original performance as closely as possible. In a perceptual intelligibility study with degraded audio we then compared the animated talker against the real talker and the audio alone, in terms of audio-visual word recognition rate across the three different production conditions. We found that the visual intelligibility of the animated talker was on par with the real talker for the Lombard and whisper conditions. In addition we created two incongruent conditions where normal speech audio was paired with animated Lombard speech or whispering. When compared to the congruent normal speech condition, Lombard animation yields a significant increase in intelligibility, despite the AV-incongruence. In a separate evaluation, we gathered subjective opinions on the different animations, and found that some degree of incongruence was generally accepted.

Unlike their human counterparts, artificial agents such as robots and game characters may be deployed with a large variety of face and body configurations. Some have articulated bodies but lack facial features, and others may be talking heads ending at the neck. Generally, they have many fewer degrees of freedom than humans through which they must express themselves, and there will inevitably be a filtering effect when mapping human motion onto the agent. In this article, we investigate filtering effects on three types of embodiments: (a) an agent with a body but no facial features, (b) an agent with a head only, and (c) an agent with a body and a face. We performed a full performance capture of a mime actor enacting short interactions varying the non-verbal expression along five dimensions (e.g., level of frustration and level of certainty) for each of the three embodiments. We performed a crowd-sourced evaluation experiment comparing the video of the actor to the video of an animated robot for the different embodiments and dimensions. Our findings suggest that the face is especially important to pinpoint emotional reactions but is also most volatile to filtering effects. The body motion, on the other hand, had more diverse interpretations but tended to preserve the interpretation after mapping and thus proved to be more resilient to filtering.