Human Grasp Dataset for Human Robot Handovers
| Main Authors: | Scheikl, Paul Maria, Kunz, Christian, Meißner, Pascal, Kröger, Torsten, Reischl, Markus |
|---|---|
| Format: | info dataset eJournal |
| Bahasa: | eng |
| Terbitan: |
, 2019
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/2578811 |
Daftar Isi:
- The dataset consists of 278.400 RGB images of size (299, 299). The images are sorted into the folders: Angles 30°, 45°, and 60° Lights From_Behind, From_Front, and Full_Lighting Objects Duplo_Block, Highlighter, Plastic_Pear, Table_Tennis_Racket, and Wood_Block Persons Person_1 to Person_10 Other Default_Configuration, Clutter, and Other_Grasps_And_Interactions Each folder contains 11.600 images that have a label in their file name. l=1 for grasp and l=0 for not grasp.