Mining actionlet ensemble for action recognition with depth cameras
Human action recognition is an important yet challenging task. The recently developed commodity depth sensors open up new possibilities of dealing with this problem but also present some unique challenges. The depth maps captured by the depth cameras are very noisy and the 3D positions of the tracke...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/100602 http://hdl.handle.net/10220/17897 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-100602 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1006022020-03-07T13:24:50Z Mining actionlet ensemble for action recognition with depth cameras Wang, Jiang Liu, Zicheng Wu, Ying Yuan, Junsong School of Electrical and Electronic Engineering IEEE Conference on Computer Vision and Pattern Recognition (2012 : Providence, Rhode Island, US) DRNTU::Engineering::Electrical and electronic engineering Human action recognition is an important yet challenging task. The recently developed commodity depth sensors open up new possibilities of dealing with this problem but also present some unique challenges. The depth maps captured by the depth cameras are very noisy and the 3D positions of the tracked joints may be completely wrong if serious occlusions occur, which increases the intra-class variations in the actions. In this paper, an actionlet ensemble model is learnt to represent each action and to capture the intra-class variance. In addition, novel features that are suitable for depth data are proposed. They are robust to noise, invariant to translational and temporal misalignments, and capable of characterizing both the human motion and the human-object interactions. The proposed approach is evaluated on two challenging action recognition datasets captured by commodity depth cameras, and another dataset captured by a MoCap system. The experimental evaluations show that the proposed approach achieves superior performance to the state of the art algorithms. Accepted version 2013-11-29T03:20:19Z 2019-12-06T20:25:13Z 2013-11-29T03:20:19Z 2019-12-06T20:25:13Z 2012 2012 Conference Paper Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2012). Mining actionlet ensemble for action recognition with depth cameras. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 1290-1297. https://hdl.handle.net/10356/100602 http://hdl.handle.net/10220/17897 10.1109/CVPR.2012.6247813 en © 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/CVPR.2012.6247813]. This work was supported in part by National Science Foundation grant IIS-0347877,IIS-0916607,US Army Research Laboratory and the US Army Research Office under grant ARO W911NF-08-1-0504, and DARPA Award FA 8650-11-1-7149.This work is partially supported by Microsoft Research. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Electrical and electronic engineering |
spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering Wang, Jiang Liu, Zicheng Wu, Ying Yuan, Junsong Mining actionlet ensemble for action recognition with depth cameras |
description |
Human action recognition is an important yet challenging task. The recently developed commodity depth sensors open up new possibilities of dealing with this problem but also present some unique challenges. The depth maps captured by the depth cameras are very noisy and the 3D positions of the tracked joints may be completely wrong if serious occlusions occur, which increases the intra-class variations in the actions. In this paper, an actionlet ensemble model is learnt to represent each action and to capture the intra-class variance. In addition, novel features that are suitable for depth data are proposed. They are robust to noise, invariant to translational and temporal misalignments, and capable of characterizing both the human motion and the human-object interactions. The proposed approach is evaluated on two challenging action recognition datasets captured by commodity depth cameras, and another dataset captured by a MoCap system. The experimental evaluations show that the proposed approach achieves superior performance to the state of the art algorithms. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Wang, Jiang Liu, Zicheng Wu, Ying Yuan, Junsong |
format |
Conference or Workshop Item |
author |
Wang, Jiang Liu, Zicheng Wu, Ying Yuan, Junsong |
author_sort |
Wang, Jiang |
title |
Mining actionlet ensemble for action recognition with depth cameras |
title_short |
Mining actionlet ensemble for action recognition with depth cameras |
title_full |
Mining actionlet ensemble for action recognition with depth cameras |
title_fullStr |
Mining actionlet ensemble for action recognition with depth cameras |
title_full_unstemmed |
Mining actionlet ensemble for action recognition with depth cameras |
title_sort |
mining actionlet ensemble for action recognition with depth cameras |
publishDate |
2013 |
url |
https://hdl.handle.net/10356/100602 http://hdl.handle.net/10220/17897 |
_version_ |
1681035543885905920 |