LaRED

Hsiao, Yuan-Sheng; Sanchez-Riera, Jordi; Lim, Theam Soon; Hua, Kai-Lung; Cheng, Wen-Huang

doi:10.1145/2557642.2563669

Cited by 22 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, most datasets contain color images where the hands are the only object present in them (with both simple and cluttered backgrounds), making them suitable for CNN models or segmentation techniques such as the ones in [2] , [3] . Multi-modal datasets are also available, such as the one presented in [4] , [5] , [6] , [7] where static gestures have been collected in the form of RGB and Depth frames spatially and temporally aligned. The drawback of these datasets is that only one gesture per image is shown and the hand is very close to the camera, making this dataset not suitable for Object Detector models that aim to detect gestures in big images also picturing cluttered environments.…”

Section: Data Descriptionmentioning

confidence: 99%

HANDS: an RGB-D dataset of static hand-gestures for human-robot interaction

et al. 2021

View full text Add to dashboard Cite

The HANDS dataset has been created for human-robot interaction research, and it is composed of spatially and temporally aligned RGB and Depth frames. It contains 12 static single-hand gestures performed with both the right-hand and the left-hand, and 3 static two-hands gestures for a total of 29 unique classes. Five actors (two females and three males) have been acquired performing the gestures, each of them adopting a different background and light conditions. For each actor, 150 RGB frames and their corresponding 150 Depth frames per gesture have been collected, for a total of 2400 RGB frames and 2400 Depth frames per actor. Data has been collected using a Kinect v2 camera intrinsically calibrated to spatially align RGB data to Depth data. The temporal alignment has been performed offline using MATLAB, aligning frames with a maximum temporal distance of 66 ms. This dataset has been used in [1] and it is freely available at http://dx.doi.org/10.17632/ndrczc35bt.1 .

show abstract