Egocentric Dataset: Daily-Life Manipulation with RGB-D, EMG, and IMU

Lo6yu's Egocentric Multimodal Daily-Life RGB-D EMG IMU Dataset captures synchronized egocentric daily-life manipulation data. The dataset combines RGB-D video for scene context and hand motion with bilateral wrist EMG for muscle activation and wrist IMU signals. It was last updated on 2026-05 02 19:30:11.

Use Cases

• Train models for hand-object interaction recognition based on synchronized RGB-D and EMG data.
• Develop algorithms for contact region prediction based on depth and visual cues.
• Research muscle activation patterns for specific grasps and manipulations based on EMG signals.
• Fuse visual, depth, and physiological signals for holistic human activity understanding.

Strengths

• Synchronized capture of RGB-D video, EMG, and IMU provides a multimodal view of activities.
• Data captures a variety of hand-object interactions like grasping, lifting, pressing, pulling, and wiping.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count, file formats, and column-level documentation are absent.
• Data may reflect temporal or contextual bias inherent to the single-source collection method.

Provenance

Source

Lo6yu on Hugging Face.

Collection Method

Likely captured via wearable sensors for egocentric, first-person perspective recording.

Time Range

null

Freshness

Last updated 2026-05-02 19:30:11; freshness should be verified.

Geography

null