Visualizing and annotating video and microsensor data from cross-country skiing using the autoactive research environment
INTRODUCTION: Wearable microsensors such as inertial movement sensors (IMUs) are revolutionizing the analysis of movement. It allows researchers to bring the lab to the field, resulting in more relevant data for the analysis of movements in sports. However, there has been a lack of tools to visualize and analyze the data. Especially, synchronizing video with recorded microsensor data, and easy annotations for machine learning purposes, have been challenging. To answer this challenge, SINTEF has developed an open-source AutoActive Research Environment (ARE) 1 consisting of an easy-to-use software with a graphical user interface, ActivityPresenter, to visualize, synchronize, annotate and organize data from sensors and cameras as well as supporting interactions with MATLAB and Python. We demonstrate this software suite by sharing a dataset to analyze and annotate sub-techniques in classical cross-country skiing as in [2]. The data and code are available at https://www.sintef.no/projectweb/autoactive/code-example/.
METHODS: We recorded data from IMUs mounted on the arm and chest and a video of classical cross-country skiing. The raw accelerometer and gyroscope data were processed in MATLAB with cycles detected and labeled as in [2]. The processed IMU data and cycle indications as well as sub-technique labels were synchronized with the video and written to an AutoActiveZip (aaz) file using the ARE MATLAB toolbox.
RESULTS: Processed data from the accelerometer on the chest is visualized in ActivityPresenter together with the cycle identification. Annotations are visible as DIA (diagonal) in the plot. Data and video can be played as a movie or stepped through frame-by-frame. Annotations can be added or modified by pre-selected keys.
DISCUSSION/CONCLUSION: The AutoActive Research Environment can ease the analysis and annotation of microsensor data synchronized with a video.
REFERENCES:
1 Albrektsen, S. et al., 2022. J Open Source Softw
2 Rindal, O.M.H. et al., 2017. Sensors
© Copyright 2023 9th International Congress on Science and Skiing, March 18 - 22, 2023, Saalbach-Hinterglemm, Austria. Published by University of Salzburg. All rights reserved.
| Subjects: | |
|---|---|
| Notations: | endurance sports technical and natural sciences |
| Tagging: | Datenanalyse |
| Published in: | 9th International Congress on Science and Skiing, March 18 - 22, 2023, Saalbach-Hinterglemm, Austria |
| Language: | English |
| Published: |
Salzburg
University of Salzburg
2023
|
| Online Access: | https://ski-science.org/fileadmin/user_upload/ICSS_2023_Book_of_Abstracts.pdf |
| Pages: | 46-47 |
| Document types: | congress proceedings |
| Level: | advanced |