Datasets
Standard Dataset
HANDMI4 (HAND Motion capture data for Industry 4.0)
- Citation Author(s):
-
MatteoMenolotto
University College Cork - Submitted by:
- Matteo Menolotto
- Last updated:
- Wed, 02/07/2024 - 05:39
- DOI:
- 10.21227/c6t8-ge47
- Data Format:
- License:
934 Views- Categories:
- Keywords:
Abstract
The dataset contains motion capture data of the human hand of 20 healthy subjects acquired using two different motion capture technology (wearable IMU and camera-based). This database provides an opportunity to expand the fields of research involving the hands or their range of mobility. Indeed, using this database to train AI's net to recognise gestures/tasks is an excellent beginning point for expanding the field of human-robot collaboration.
This work is licensed under the Creative Commons Attribution 4.0 International License. If you are using our database to evaluate your methods, please cite:
Inclusion criteria:
- More 18 years old.
- English speaking.
- Capacity to consent.
Exclusion criteria:
- Arm or hand injuries, or related musculoskeletal disorders.
Only the dominant hand of the subject was included.
Participant information:
Below there is a table containing all the demographic information of the participants.
| Subject | Hand | Sex | Age Range |
|---|---|---|---|
| 000 | R | M | 20-29 |
| 001 | R | F | 30-39 |
| 002 | L | F | 20-29 |
| 003 | R | F | 30-39 |
| 004 | R | M | 30-39 |
| 005 | R | F | 30-39 |
| 006 | R | F | 20-29 |
| 007 | R | M | 30-39 |
| 008 | R | M | 20-29 |
| 009 | R | M | 30-39 |
| 010 | R | M | 30-39 |
| 011 | R | M | 30-39 |
| 012 | L | M | 50-59 |
| 013 | R | F | 30-39 |
| 014 | R | M | 20-29 |
| 015 | R | M | 30-39 |
| 016 | R | F | 30-39 |
| 017 | R | M | 30-39 |
| 018 | R | F | 20-29 |
| 019 | R | M | 30-39 |
Motion Capture Technologies:
- IMU-based Data Glove - Tyndall Smart Glove (Tyndall National Institute, Ireland)
- Optitrack cameras - 10 PrimaX13 + 2 PrimeX41 camera system from Optitrack (NaturalPoint, Inc., OR, US)
File naming conventions:
The files are arranged in folders. Each folder corresponds to a study participant.
A coded file labelling system has been implemented that allows for unique identification of each datum.
The elements that compose each label are:
- 3-digit numeric participant identifier (ID)
- 3 letters which refer to the motion capture technology used (GLV or OPT)
- 3 letters which refer to task performed (TAX or IND),
- 2-digit numeric for the type of task (if the file refer to the taxonomy tasks, the number correspond with the Cutkosky taxonomy task)
- 2-digit numeric for the number of repetition (starting form 00).
For instance, in the label 000GLVTAX0201: 000 identifies the first participant, GLV stands for data glove, TAX refers to the Cutkosky's taxonomy, 02 refers to the second grasp of the Cutkosky's taxonomy, 01 means that this is the second repetition.
The complete list of abbreviations used for the labelling is shown in the following Table:
| Description | Label |
|---|---|
| IMU-based data glove | GLV |
| Optitrack cameras | OPT |
| Cutkosky taxonomy grasps | TAX |
| Industrial tasks | IND |
Documentation
| Attachment | Size |
|---|---|
 README.md | 1.96 KB |
