Header

UZH-Logo

Maintenance Infos

DHP19: Dynamic Vision Sensor 3D Human Pose Dataset


Calabrese, Enrico; Taverni, Gemma; Awai Easthope, Christopher; Skriabine, Sophie; Corradi, Federico; Longinotti, Luca; Eng, Kynan; Delbruck, Tobi (2019). DHP19: Dynamic Vision Sensor 3D Human Pose Dataset. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA, 16 June 2019 - 20 June 2019.

Abstract

Human pose estimation has dramatically improved thanks to the continuous developments in deep learning. However, marker-free human pose estimation based on standard frame-based cameras is still slow and power hun- gry for real-time feedback interaction because of the huge number of operations necessary for large Convolutional Neural Network (CNN) inference. Event-based cameras such as the Dynamic Vision Sensor (DVS) quickly output sparse moving-edge information. Their sparse and rapid output is ideal for driving low-latency CNNs, thus poten- tially allowing real-time interaction for human pose estima- tors. Although the application of CNNs to standard frame- based cameras for human pose estimation is well estab- lished, their application to event-based cameras is still un- der study. This paper proposes a novel benchmark dataset of human body movements, the Dynamic Vision Sensor Hu- man Pose dataset (DHP19). It consists of recordings from 4 synchronized 346x260 pixel DVS cameras, for a set of 33 movements with 17 subjects. DHP19 also includes a 3D pose estimation model that achieves an average 3D pose estimation error of about 8 cm, despite the sparse and re- duced input data from the DVS.

Abstract

Human pose estimation has dramatically improved thanks to the continuous developments in deep learning. However, marker-free human pose estimation based on standard frame-based cameras is still slow and power hun- gry for real-time feedback interaction because of the huge number of operations necessary for large Convolutional Neural Network (CNN) inference. Event-based cameras such as the Dynamic Vision Sensor (DVS) quickly output sparse moving-edge information. Their sparse and rapid output is ideal for driving low-latency CNNs, thus poten- tially allowing real-time interaction for human pose estima- tors. Although the application of CNNs to standard frame- based cameras for human pose estimation is well estab- lished, their application to event-based cameras is still un- der study. This paper proposes a novel benchmark dataset of human body movements, the Dynamic Vision Sensor Hu- man Pose dataset (DHP19). It consists of recordings from 4 synchronized 346x260 pixel DVS cameras, for a set of 33 movements with 17 subjects. DHP19 also includes a 3D pose estimation model that achieves an average 3D pose estimation error of about 8 cm, despite the sparse and re- duced input data from the DVS.

Statistics

Citations

Dimensions.ai Metrics
1 citation in Web of Science®
7 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

64 downloads since deposited on 05 Dec 2019
54 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not_refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Physical Sciences > Computer Vision and Pattern Recognition
Physical Sciences > Electrical and Electronic Engineering
Language:English
Event End Date:20 June 2019
Deposited On:05 Dec 2019 09:41
Last Modified:29 Jul 2020 11:54
Publisher:CVF
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Publisher DOI:https://doi.org/10.1109/CVPRW.2019.00217
Official URL:http://openaccess.thecvf.com/content_CVPRW_2019/papers/EventVision/Calabrese_DHP19_Dynamic_Vision_Sensor_3D_Human_Pose_Dataset_CVPRW_2019_paper.pdf

Download

Green Open Access

Download PDF  'DHP19: Dynamic Vision Sensor 3D Human Pose Dataset'.
Preview
Content: Published Version
Filetype: PDF
Size: 1MB
View at publisher