Validation of deep learning-based markerless 3D pose estimation

Abstract

Deep learning-based approaches to markerless 3D pose estimation are being adopted by researchers in psychology and neuroscience at an unprecedented rate. Yet many of these tools remain unvalidated. Here, we report on the validation of one increasingly popular tool (DeepLabCut) against simultaneous measurements obtained from a reference measurement system (Fastrak) with well-known performance characteristics. Our results confirm close (mm range) agreement between the two, indicating that under specific circumstances deep learning-based approaches can match more traditional motion tracking methods. Although more work needs to be done to determine their specific performance characteristics and limitations, this study should help build confidence within the research community using these new tools.

Masked-Piper: Masking personal identities in visual recordings while preserving multimodal information

“…Thus, further iterations of the masking tool will need to be developed to mask multiple persons in one video. Finally, any automated computer vision-based tracking may be insufficiently precise 3 depending on your research questions (but see [7,17] for comparisons of video-based tracking versus device-based trackers). Fortunately, researchers can easily verify the quality of the videos and tracking performance produced by Masked-Piper.…”