A new action recognition method by distinguishing ambiguous postures

A new action recognition method by distinguishing ambiguous postures

One of the most important aspects of promoting the intelligence of home service robots is to reliably recognize human actions and accurately understand human behaviors and intentions. In the task of action recognition, there are many common ambiguous postures, which affect the recognition accuracy....

Full description

Bibliographic Details
Main Authors: Zhiqiang Liu, Jianqin Yin, Jinping Li, Jun Wei, Zhiquan Feng
Format: Article
Language:English
Published: SAGE Publishing 2018-01-01
Series:International Journal of Advanced Robotic Systems
Online Access:https://doi.org/10.1177/1729881417749482
id doaj-977199b7a3c74364acba3cad502c49c6
record_format Article
spelling doaj-977199b7a3c74364acba3cad502c49c62020-11-25T03:38:22ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88142018-01-011510.1177/1729881417749482A new action recognition method by distinguishing ambiguous posturesZhiqiang Liu0Jianqin Yin1Jinping Li2Jun Wei3Zhiquan Feng4 Shandong Provincial Key Laboratory of Network Based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan, China Automation School, Beijing University of Posts and Telecommunications, Beijing, China Shandong Provincial Key Laboratory of Network Based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan, China Shandong Provincial Key Laboratory of Network Based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan, China Shandong Provincial Key Laboratory of Network Based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan, ChinaOne of the most important aspects of promoting the intelligence of home service robots is to reliably recognize human actions and accurately understand human behaviors and intentions. In the task of action recognition, there are many common ambiguous postures, which affect the recognition accuracy. To improve the reliability of the service provided by home service robots, this article presents a method of probabilistic soft-assignment recognition scheme based on Gaussian mixture models to recognize similar actions. First, we generate a representative posture dictionary based on the standard bag-of-words model; then, a Gaussian mixture model is introduced for the similar poses. Finally, combined with the Naive Bayesian principle, the method of weighted voting is used to recognize the action. The proposed scheme is verified by recognizing four types of daily actions, and the experimental results show its effectiveness.https://doi.org/10.1177/1729881417749482
collection DOAJ
language English
format Article
sources DOAJ
author Zhiqiang Liu
Jianqin Yin
Jinping Li
Jun Wei
Zhiquan Feng
spellingShingle Zhiqiang Liu
Jianqin Yin
Jinping Li
Jun Wei
Zhiquan Feng
A new action recognition method by distinguishing ambiguous postures
International Journal of Advanced Robotic Systems
author_facet Zhiqiang Liu
Jianqin Yin
Jinping Li
Jun Wei
Zhiquan Feng
author_sort Zhiqiang Liu
title A new action recognition method by distinguishing ambiguous postures
title_short A new action recognition method by distinguishing ambiguous postures
title_full A new action recognition method by distinguishing ambiguous postures
title_fullStr A new action recognition method by distinguishing ambiguous postures
title_full_unstemmed A new action recognition method by distinguishing ambiguous postures
title_sort new action recognition method by distinguishing ambiguous postures
publisher SAGE Publishing
series International Journal of Advanced Robotic Systems
issn 1729-8814
publishDate 2018-01-01
description One of the most important aspects of promoting the intelligence of home service robots is to reliably recognize human actions and accurately understand human behaviors and intentions. In the task of action recognition, there are many common ambiguous postures, which affect the recognition accuracy. To improve the reliability of the service provided by home service robots, this article presents a method of probabilistic soft-assignment recognition scheme based on Gaussian mixture models to recognize similar actions. First, we generate a representative posture dictionary based on the standard bag-of-words model; then, a Gaussian mixture model is introduced for the similar poses. Finally, combined with the Naive Bayesian principle, the method of weighted voting is used to recognize the action. The proposed scheme is verified by recognizing four types of daily actions, and the experimental results show its effectiveness.
url https://doi.org/10.1177/1729881417749482
work_keys_str_mv AT zhiqiangliu anewactionrecognitionmethodbydistinguishingambiguouspostures
AT jianqinyin anewactionrecognitionmethodbydistinguishingambiguouspostures
AT jinpingli anewactionrecognitionmethodbydistinguishingambiguouspostures
AT junwei anewactionrecognitionmethodbydistinguishingambiguouspostures
AT zhiquanfeng anewactionrecognitionmethodbydistinguishingambiguouspostures
AT zhiqiangliu newactionrecognitionmethodbydistinguishingambiguouspostures
AT jianqinyin newactionrecognitionmethodbydistinguishingambiguouspostures
AT jinpingli newactionrecognitionmethodbydistinguishingambiguouspostures
AT junwei newactionrecognitionmethodbydistinguishingambiguouspostures
AT zhiquanfeng newactionrecognitionmethodbydistinguishingambiguouspostures
_version_ 1724542531508633600

Similar Items