LaRED: A large RGB-D extensible hand gesture dataset

Yuan Sheng Hsiao; Jordi Sanchez-Riera; Tekoing Lim; Kai Lung Hua; Wen-Huang Cheng

doi:10.1145/2557642.2563669

LaRED: A large RGB-D extensible hand gesture dataset

Yuan Sheng Hsiao, Jordi Sanchez-Riera, Tekoing Lim, Kai Lung Hua, Wen-Huang Cheng

Institute of Electronics

Research output: Contribution to conference › Paper › peer-review

26 Scopus citations

Abstract

We present the LaRED, a Large RGB-D Extensible hand gesture Dataset, recorded with an Intel's newly-developed short range depth camera. This dataset is unique and differs from the existing ones in several aspects. Firstly, the large volume of data recorded: 243, 000 tuples where each tuple is composed of a color image, a depth image, and a mask of the hand region. Secondly, the number of different classes provided: a total of 81 classes (27 gestures in 3 different rotations). Thirdly, the extensibility of dataset: the software used to record and inspect the dataset is also available, giving the possibility for future users to increase the number of data as well as the number of gestures. Finally, in this paper, some experiments are presented to characterize the dataset and establish a baseline as the start point to develop more complex recognition algorithms. The LaRED dataset is publicly available at: http://mclab.citi.sinica.edu.tw/dataset/lared/lared.html.

Original language	English
Pages	53-58
Number of pages	6
DOIs	https://doi.org/10.1145/2557642.2563669
State	Published - 1 Jan 2014
Event	5th ACM Multimedia Systems Conference, MMSys 2014 - Singapore, Singapore Duration: 19 Mar 2014 → 21 Mar 2014

Conference

Conference	5th ACM Multimedia Systems Conference, MMSys 2014
Country/Territory	Singapore
City	Singapore
Period	19/03/14 → 21/03/14

Keywords

Dataset
Depth data
Hand gestures
RGB images

Access to Document

10.1145/2557642.2563669

Cite this

@conference{dcbffeafd5744cb591c3538b6fd3eeb6,

title = "LaRED: A large RGB-D extensible hand gesture dataset",

abstract = "We present the LaRED, a Large RGB-D Extensible hand gesture Dataset, recorded with an Intel's newly-developed short range depth camera. This dataset is unique and differs from the existing ones in several aspects. Firstly, the large volume of data recorded: 243, 000 tuples where each tuple is composed of a color image, a depth image, and a mask of the hand region. Secondly, the number of different classes provided: a total of 81 classes (27 gestures in 3 different rotations). Thirdly, the extensibility of dataset: the software used to record and inspect the dataset is also available, giving the possibility for future users to increase the number of data as well as the number of gestures. Finally, in this paper, some experiments are presented to characterize the dataset and establish a baseline as the start point to develop more complex recognition algorithms. The LaRED dataset is publicly available at: http://mclab.citi.sinica.edu.tw/dataset/lared/lared.html.",

keywords = "Dataset, Depth data, Hand gestures, RGB images",

author = "Hsiao, {Yuan Sheng} and Jordi Sanchez-Riera and Tekoing Lim and Hua, {Kai Lung} and Wen-Huang Cheng",

year = "2014",

month = jan,

day = "1",

doi = "10.1145/2557642.2563669",

language = "English",

pages = "53--58",

note = "5th ACM Multimedia Systems Conference, MMSys 2014 ; Conference date: 19-03-2014 Through 21-03-2014",

}

TY - CONF

T1 - LaRED

T2 - 5th ACM Multimedia Systems Conference, MMSys 2014

AU - Hsiao, Yuan Sheng

AU - Sanchez-Riera, Jordi

AU - Lim, Tekoing

AU - Hua, Kai Lung

AU - Cheng, Wen-Huang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - We present the LaRED, a Large RGB-D Extensible hand gesture Dataset, recorded with an Intel's newly-developed short range depth camera. This dataset is unique and differs from the existing ones in several aspects. Firstly, the large volume of data recorded: 243, 000 tuples where each tuple is composed of a color image, a depth image, and a mask of the hand region. Secondly, the number of different classes provided: a total of 81 classes (27 gestures in 3 different rotations). Thirdly, the extensibility of dataset: the software used to record and inspect the dataset is also available, giving the possibility for future users to increase the number of data as well as the number of gestures. Finally, in this paper, some experiments are presented to characterize the dataset and establish a baseline as the start point to develop more complex recognition algorithms. The LaRED dataset is publicly available at: http://mclab.citi.sinica.edu.tw/dataset/lared/lared.html.

AB - We present the LaRED, a Large RGB-D Extensible hand gesture Dataset, recorded with an Intel's newly-developed short range depth camera. This dataset is unique and differs from the existing ones in several aspects. Firstly, the large volume of data recorded: 243, 000 tuples where each tuple is composed of a color image, a depth image, and a mask of the hand region. Secondly, the number of different classes provided: a total of 81 classes (27 gestures in 3 different rotations). Thirdly, the extensibility of dataset: the software used to record and inspect the dataset is also available, giving the possibility for future users to increase the number of data as well as the number of gestures. Finally, in this paper, some experiments are presented to characterize the dataset and establish a baseline as the start point to develop more complex recognition algorithms. The LaRED dataset is publicly available at: http://mclab.citi.sinica.edu.tw/dataset/lared/lared.html.

KW - Dataset

KW - Depth data

KW - Hand gestures

KW - RGB images

UR - http://www.scopus.com/inward/record.url?scp=84898931593&partnerID=8YFLogxK

U2 - 10.1145/2557642.2563669

DO - 10.1145/2557642.2563669

M3 - Paper

AN - SCOPUS:84898931593

SP - 53

EP - 58

Y2 - 19 March 2014 through 21 March 2014

ER -

LaRED: A large RGB-D extensible hand gesture dataset

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this