One of the unique advantages of Theia3D is its ability to perform automatic, multi-person tracking by identifying each unique individual within a recording. If a person is sufficiently visible in three or more camera views, they will be tracked. This can be useful in several different scenarios, including for data collections where person-to-person interactions are being studied, for in-person group assessments, and for situations in which there are multiple people in the field of view simultaneously, such as a practitioner, research participant, or other individuals.

However, it is important to note that there are some technical considerations when using multi-person tracking mode in Theia3D. With these technical limitations in mind, we’ve prepared some best practices for collecting data that involves multiple people in the same capture volume.

People in the Capture Volume

Theia3D automatically tracks all people visible in three or more cameras in a recording. When using multi-person tracking in your data collection, we recommend keeping non-essential people out of the capture volume as much as possible. Having many people in a capture volume increases the possibility of body segments being occluded by others, which will decrease the accuracy of the tracking. For data collections aimed at research participants, it's often ideal to minimize the number of people in the capture volume, especially if the person of interest needs to be tracked accurately. In some scenarios, such as biomechanical research on team dynamics or occupational movement studies, it is beneficial to have multiple people in the capture volume simultaneously. In these cases, we recommend keeping the number of research participants in the volume to what is necessary for the research task.

Interaction and Recovery Research

Multi-person tracking can be particularly valuable when studying interactions between research participants, such as in sport science research on team dynamics, paired task performance, or occupational biomechanics studies. When individuals are in close proximity or physically interacting, there is an increased risk of occlusion of body segments, which can temporarily reduce tracking accuracy. In these scenarios, maximizing camera coverage from multiple angles is especially important to ensure reliable tracking of all individuals throughout the data collection.

Data Considerations

When conducting data collection with multiple people, consider reviewing the data from each person independently after collection to ensure that tracking quality meets your research requirements. A useful workflow is to use Theia3D’s built-in person identification features to assign meaningful labels to each tracked individual before exporting data for downstream analysis.

Contact us to discuss best practices for multi-person tracking in your specific research context.