SenseCap: Synchronized Data Collection with Microsoft Kinect2 and LeapMotion

Julian F.P. Kooij

doi:10.1145/2964284.2973805

SenseCap: Synchronized Data Collection with Microsoft Kinect2 and LeapMotion

Pattern Recognition and Bioinformatics

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

5 Citations (Scopus)

Abstract

We present a new recording tool to capture synchronized video and skeletal data streams from cheap sensors such as the Microsoft Kinect2, and LeapMotion. While other recording tools act as virtual playback devices for testing on-line real-time applications, we target multi-media data collection for off-line processing. Images are encoded in common video formats, and skeletal data as flat text tables. This approach enables long duration recordings (e.g. over 30 minutes), and supports post-hoc mapping of the Kinect2 depth video to the color space if needed. By using common file formats, the data can be played back and analyzed on any other computer, without requiring sensor specific SDKs to be installed. The project is released under a 3-clause BSD license, and consists of an extensible C++11 framework, with support for the official Microsoft Kinect 2 and LeapMotion APIs to record, a command-line interface, and a Matlab GUI to initiate, inspect, and load Kinect2 recordings.

Original language	English
Title of host publication	Proceedings of the 2016 ACM on Multimedia Conference, MM '16
Editors	A. Hanjalic, C. Snoek, M. Worring, D. Bulterman, B. Huet, A. Kelliher, Y. Kompatsiaris, J. Li
Place of Publication	New York, NY
Publisher	Association for Computing Machinery (ACM)
Pages	1218-1221
ISBN (Print)	978-1-4503-3603-1
DOIs	https://doi.org/10.1145/2964284.2973805
Publication status	Published - 15 Oct 2016
Event	MM'16 the ACM Multimedia Conference: 24th ACM Multimedia Conference - Amsterdam, Netherlands Duration: 15 Oct 2016 → 19 Oct 2016

Conference

Conference	MM'16 the ACM Multimedia Conference
Country/Territory	Netherlands
City	Amsterdam
Period	15/10/16 → 19/10/16

Access to Document

10.1145/2964284.2973805

Cite this

@inproceedings{6eb3cc332ea0483da32ac4e8ac134a5b,

title = "SenseCap: Synchronized Data Collection with Microsoft Kinect2 and LeapMotion",

abstract = "We present a new recording tool to capture synchronized video and skeletal data streams from cheap sensors such as the Microsoft Kinect2, and LeapMotion. While other recording tools act as virtual playback devices for testing on-line real-time applications, we target multi-media data collection for off-line processing. Images are encoded in common video formats, and skeletal data as flat text tables. This approach enables long duration recordings (e.g. over 30 minutes), and supports post-hoc mapping of the Kinect2 depth video to the color space if needed. By using common file formats, the data can be played back and analyzed on any other computer, without requiring sensor specific SDKs to be installed. The project is released under a 3-clause BSD license, and consists of an extensible C++11 framework, with support for the official Microsoft Kinect 2 and LeapMotion APIs to record, a command-line interface, and a Matlab GUI to initiate, inspect, and load Kinect2 recordings.",

author = "Kooij, {Julian F.P.}",

year = "2016",

month = oct,

day = "15",

doi = "10.1145/2964284.2973805",

language = "English",

isbn = "978-1-4503-3603-1",

pages = "1218--1221",

editor = "A. Hanjalic and C. Snoek and M. Worring and D. Bulterman and B. Huet and A. Kelliher and Y. Kompatsiaris and J. Li",

booktitle = "Proceedings of the 2016 ACM on Multimedia Conference, MM '16",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "MM'16 the ACM Multimedia Conference : 24th ACM Multimedia Conference ; Conference date: 15-10-2016 Through 19-10-2016",

}

Kooij, JFP 2016, SenseCap: Synchronized Data Collection with Microsoft Kinect2 and LeapMotion. in A Hanjalic, C Snoek, M Worring, D Bulterman, B Huet, A Kelliher, Y Kompatsiaris & J Li (eds), Proceedings of the 2016 ACM on Multimedia Conference, MM '16. Association for Computing Machinery (ACM), New York, NY, pp. 1218-1221, MM'16 the ACM Multimedia Conference, Amsterdam, Netherlands, 15/10/16. https://doi.org/10.1145/2964284.2973805

SenseCap: Synchronized Data Collection with Microsoft Kinect2 and LeapMotion. / Kooij, Julian F.P.
Proceedings of the 2016 ACM on Multimedia Conference, MM '16. ed. / A. Hanjalic; C. Snoek; M. Worring; D. Bulterman; B. Huet; A. Kelliher; Y. Kompatsiaris; J. Li. New York, NY: Association for Computing Machinery (ACM), 2016. p. 1218-1221.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - SenseCap

T2 - MM'16 the ACM Multimedia Conference

AU - Kooij, Julian F.P.

PY - 2016/10/15

Y1 - 2016/10/15

N2 - We present a new recording tool to capture synchronized video and skeletal data streams from cheap sensors such as the Microsoft Kinect2, and LeapMotion. While other recording tools act as virtual playback devices for testing on-line real-time applications, we target multi-media data collection for off-line processing. Images are encoded in common video formats, and skeletal data as flat text tables. This approach enables long duration recordings (e.g. over 30 minutes), and supports post-hoc mapping of the Kinect2 depth video to the color space if needed. By using common file formats, the data can be played back and analyzed on any other computer, without requiring sensor specific SDKs to be installed. The project is released under a 3-clause BSD license, and consists of an extensible C++11 framework, with support for the official Microsoft Kinect 2 and LeapMotion APIs to record, a command-line interface, and a Matlab GUI to initiate, inspect, and load Kinect2 recordings.

AB - We present a new recording tool to capture synchronized video and skeletal data streams from cheap sensors such as the Microsoft Kinect2, and LeapMotion. While other recording tools act as virtual playback devices for testing on-line real-time applications, we target multi-media data collection for off-line processing. Images are encoded in common video formats, and skeletal data as flat text tables. This approach enables long duration recordings (e.g. over 30 minutes), and supports post-hoc mapping of the Kinect2 depth video to the color space if needed. By using common file formats, the data can be played back and analyzed on any other computer, without requiring sensor specific SDKs to be installed. The project is released under a 3-clause BSD license, and consists of an extensible C++11 framework, with support for the official Microsoft Kinect 2 and LeapMotion APIs to record, a command-line interface, and a Matlab GUI to initiate, inspect, and load Kinect2 recordings.

U2 - 10.1145/2964284.2973805

DO - 10.1145/2964284.2973805

M3 - Conference contribution

SN - 978-1-4503-3603-1

SP - 1218

EP - 1221

BT - Proceedings of the 2016 ACM on Multimedia Conference, MM '16

A2 - Hanjalic, A.

A2 - Snoek, C.

A2 - Worring, M.

A2 - Bulterman, D.

A2 - Huet, B.

A2 - Kelliher, A.

A2 - Kompatsiaris, Y.

A2 - Li, J.

PB - Association for Computing Machinery (ACM)

CY - New York, NY

Y2 - 15 October 2016 through 19 October 2016

ER -

SenseCap: Synchronized Data Collection with Microsoft Kinect2 and LeapMotion

Abstract

Conference

Access to Document

Fingerprint

Cite this