Multimodal Gait Data from 17 Participants Across Indoor and Outdoor Environments

17 healthy participants (7 females, 10 males, aged 19–34) performed walking activities across diverse indoor and outdoor terrains. The dataset includes motion data from 7 inertial sensors, foot pressure from 96-point force sensors, and visual data from 3 front-facing cameras, all annotated with 16 locomotion state classes. Collected by Chen Wang and shared under a CC-BY-4.0 license, this 16.9 GB dataset was last updated on 2026-05-31.

Use Cases

• Train locomotion state recognition models based on annotated 16-class lower-limb state labels.
• Develop gait phase classification algorithms based on annotated gait phase data for both legs.
• Analyze center of pressure dynamics based on annotated coordinates for both feet.
• Fuse inertial, pressure, and visual data for multimodal activity analysis in real-world environments.

Strengths

• Data from 17 participants with detailed demographics (age, height, weight) provided.
• Multimodal collection includes 7 inertial sensors, 96-point foot pressure data, and 3 cameras.
• Fully annotated with 16 locomotion state classes, gait phases, and center of pressure coordinates.
• Covers diverse real-world indoor and outdoor environments, not just laboratory settings.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for large-scale model training.
• Data may reflect bias inherent to the participant pool (19–34 year olds, specific height/weight range).

Provenance

Source

Chen Wang

Collection Method

Collected from 17 healthy participants performing walking activities across indoor and outdoor environments using wearable sensors and cameras.

Freshness

Last updated 2026-05-31 06:28:51; freshness should be verified.