SensorPositionComparison - Stride Segmentation#

Further Links:

A challenge for stride segmentation on long @lab gait tests of healthy participants.

General Information#

Dataset

The Sensor Position Comparison 2019 dataset [1] (usage example, download) contains 4x10m, 2x20m and a long walk (5 min) gait tests of 14 participants. The 4x10m and 2x20m tests are performed at 3 different speeds (slow, normal, fast). However, for this challenge, we consider all tests together as a single recording. This recording also contains potential walking and shuffling of the participants in between the tests. The dataset uses sensors at 6 different positions of each foot. However, for this challenge only the instep sensors are used.

Sensor System

The instep sensors are NilsPod IMU sensors (204.8 Hz). The two sensors are synchronized with each other and the motion capture system with sub-sample accuracy.

Reference System

The stride borders within the raw IMU data was labeled manually by an expert using the stride definition by [2].

Implementation Recommendations#

For each participant, we only have a single recording that contains all tests. This recording also contains all walking and movement between the tests. Before each test, the participant was also jumping 3 times in place as a marker for the start of the test. Further, some participants had to do some tests twice, because they did not follow the instructions. All of this is included in the recording and all strides are labeled.

This means the algorithms should search for all strides (straight and turns) in the recording independent of everything.

References#

[1]

Küderle, Arne, Nils Roth, Jovana Zlatanovic, Markus Zrenner, Bjoern Eskofier, and Felix Kluge. “The Placement of Foot-Mounted IMU Sensors Does Affect the Accuracy of Spatial Parameters during Regular Walking.” PLOS ONE 17, no. 6 (June 9, 2022): e0269567. https://doi.org/10.1371/journal.pone.0269567.

[2]

Barth, Jens, Cäcilia Oberndorfer, Cristian Pasluosta, Samuel Schülein, Heiko Gassner, Samuel Reinfelder, Patrick Kugler, et al. “Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data.” Sensors (Switzerland) 15, no. 3 (March 17, 2015): 6419-40. https://doi.org/10.3390/s150306419.