Towards Generating Virtual Movement from Textual Instructions A Case Study in Quality Assessment
This work addresses the challenge of validating generated movements for applications like health games and robotics, but it is incremental as it focuses on a preliminary quality assessment step.
The study tackled the problem of automatically generating body movements from textual instructions by recording five exercises performed by seven amateurs, finding that identical instructions led to different interpretations. They conducted a quality assessment using crowdsourcing, showing that RGB-based visualization achieved the best inter-rater agreement among annotators.
Many application areas ranging from serious games for health to learning by demonstration in robotics, could benefit from large body movement datasets extracted from textual instructions accompanied by images. The interpretation of instructions for the automatic generation of the corresponding motions (e.g. exercises) and the validation of these movements are difficult tasks. In this article we describe a first step towards achieving automated extraction. We have recorded five different exercises in random order with the help of seven amateur performers using a Kinect. During the recording, we found that the same exercise was interpreted differently by each human performer even though they were given identical textual instructions. We performed a quality assessment study based on that data using a crowdsourcing approach and tested the inter-rater agreement for different types of visualizations, where the RGBbased visualization showed the best agreement among the annotators.