Dataset profile

UTD-MHAD

UTD-MHAD contains actions captured with Kinect and wearable inertial sensing. It is not healthcare-specific, but includes movement classes such as sit-to-stand, stand-to-sit, lunges, and squats relevant to movement understanding.

Source institutionUniversity of Texas at Dallas
Activities of Daily LivingRehabilitation

Overview

UTD-MHAD contains actions captured with Kinect and wearable inertial sensing. It is not healthcare-specific, but includes movement classes such as sit-to-stand, stand-to-sit, lunges, and squats relevant to movement understanding.

What's included

  • RGB and depth videos
  • Skeleton joint positions
  • Wearable inertial signals

Tasks / activities

sit to standstand to sitlungesquatgesturessports actions

Modalities

RGBDepthPoseKinematicsAnnotations

Collection methodology

Eight subjects repeated defined actions while a Kinect sensor and wearable inertial sensor recorded synchronized modalities.

Potential applications

  • Human activity recognition
  • Movement transition modeling
  • Skeleton and inertial fusion
  • Rehabilitation-adjacent action benchmarks

Access & licensing

This is a third-party public/research dataset. We do not own or distribute this dataset. Access and usage are governed by the original publisher's terms.

Access and use are governed by the original UTD-MHAD publisher terms.

Limitations / opportunities for custom data

Custom healthcare collection can add care tasks, professional roles, assisted mobility, and richer environmental context.

Need data beyond this benchmark?

We design custom healthcare and caregiving collections around the tasks, experts, environments, and modalities your model requires.

Request Similar Data