Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition

Recently, infrared human action recognition has attracted increasing attention for it has many advantages over visible light, that is, being robust to illumination change and shadows. However, the infrared action data is limited until now, which degrades the performance of infrared action recognitio...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Liu, Zhaoyang Lu, Jing Li, Chao Yao, Yanzi Deng
Format: Article
Language:English
Published: Wiley 2018-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2018/5345241
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850165263398338560
author Yang Liu
Zhaoyang Lu
Jing Li
Chao Yao
Yanzi Deng
author_facet Yang Liu
Zhaoyang Lu
Jing Li
Chao Yao
Yanzi Deng
author_sort Yang Liu
collection DOAJ
description Recently, infrared human action recognition has attracted increasing attention for it has many advantages over visible light, that is, being robust to illumination change and shadows. However, the infrared action data is limited until now, which degrades the performance of infrared action recognition. Motivated by the idea of transfer learning, an infrared human action recognition framework using auxiliary data from visible light is proposed to solve the problem of limited infrared action data. In the proposed framework, we first construct a novel Cross-Dataset Feature Alignment and Generalization (CDFAG) framework to map the infrared data and visible light data into a common feature space, where Kernel Manifold Alignment (KEMA) and a dual aligned-to-generalized encoders (AGE) model are employed to represent the feature. Then, a support vector machine (SVM) is trained, using both the infrared data and visible light data, and can classify the features derived from infrared data. The proposed method is evaluated on InfAR, which is a publicly available infrared human action dataset. To build up auxiliary data, we set up a novel visible light action dataset XD145. Experimental results show that the proposed method can achieve state-of-the-art performance compared with several transfer learning and domain adaptation methods.
format Article
id doaj-art-eccdc2b9b6bf4e02933270435e3d3d96
institution OA Journals
issn 1076-2787
1099-0526
language English
publishDate 2018-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-eccdc2b9b6bf4e02933270435e3d3d962025-08-20T02:21:47ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/53452415345241Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action RecognitionYang Liu0Zhaoyang Lu1Jing Li2Chao Yao3Yanzi Deng4School of Telecommunications Engineering, Xidian University, No. 2 South Taibai Road, Xi’an, Shaanxi 710071, ChinaSchool of Telecommunications Engineering, Xidian University, No. 2 South Taibai Road, Xi’an, Shaanxi 710071, ChinaSchool of Telecommunications Engineering, Xidian University, No. 2 South Taibai Road, Xi’an, Shaanxi 710071, ChinaSchool of Automation, Northwestern Polytechnical University, No. 127, West Youyi Road, Xi’an, Shaanxi 710072, ChinaSchool of Telecommunications Engineering, Xidian University, No. 2 South Taibai Road, Xi’an, Shaanxi 710071, ChinaRecently, infrared human action recognition has attracted increasing attention for it has many advantages over visible light, that is, being robust to illumination change and shadows. However, the infrared action data is limited until now, which degrades the performance of infrared action recognition. Motivated by the idea of transfer learning, an infrared human action recognition framework using auxiliary data from visible light is proposed to solve the problem of limited infrared action data. In the proposed framework, we first construct a novel Cross-Dataset Feature Alignment and Generalization (CDFAG) framework to map the infrared data and visible light data into a common feature space, where Kernel Manifold Alignment (KEMA) and a dual aligned-to-generalized encoders (AGE) model are employed to represent the feature. Then, a support vector machine (SVM) is trained, using both the infrared data and visible light data, and can classify the features derived from infrared data. The proposed method is evaluated on InfAR, which is a publicly available infrared human action dataset. To build up auxiliary data, we set up a novel visible light action dataset XD145. Experimental results show that the proposed method can achieve state-of-the-art performance compared with several transfer learning and domain adaptation methods.http://dx.doi.org/10.1155/2018/5345241
spellingShingle Yang Liu
Zhaoyang Lu
Jing Li
Chao Yao
Yanzi Deng
Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
Complexity
title Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
title_full Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
title_fullStr Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
title_full_unstemmed Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
title_short Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition
title_sort transferable feature representation for visible to infrared cross dataset human action recognition
url http://dx.doi.org/10.1155/2018/5345241
work_keys_str_mv AT yangliu transferablefeaturerepresentationforvisibletoinfraredcrossdatasethumanactionrecognition
AT zhaoyanglu transferablefeaturerepresentationforvisibletoinfraredcrossdatasethumanactionrecognition
AT jingli transferablefeaturerepresentationforvisibletoinfraredcrossdatasethumanactionrecognition
AT chaoyao transferablefeaturerepresentationforvisibletoinfraredcrossdatasethumanactionrecognition
AT yanzideng transferablefeaturerepresentationforvisibletoinfraredcrossdatasethumanactionrecognition