RGB-D Data-Based Action Recognition: A Review
Classification of human actions is an ongoing research problem in computer vision. This review is aimed to scope current literature on data fusion and action recognition techniques and to identify gaps and future research direction. Success in producing cost-effective and portable vision-based senso...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/12/4246 |
_version_ | 1797529355010703360 |
---|---|
author | Muhammad Bilal Shaikh Douglas Chai |
author_facet | Muhammad Bilal Shaikh Douglas Chai |
author_sort | Muhammad Bilal Shaikh |
collection | DOAJ |
description | Classification of human actions is an ongoing research problem in computer vision. This review is aimed to scope current literature on data fusion and action recognition techniques and to identify gaps and future research direction. Success in producing cost-effective and portable vision-based sensors has dramatically increased the number and size of datasets. The increase in the number of action recognition datasets intersects with advances in deep learning architectures and computational support, both of which offer significant research opportunities. Naturally, each action-data modality—such as RGB, depth, skeleton, and infrared (IR)—has distinct characteristics; therefore, it is important to exploit the value of each modality for better action recognition. In this paper, we focus solely on data fusion and recognition techniques in the context of vision with an RGB-D perspective. We conclude by discussing research challenges, emerging trends, and possible future research directions. |
first_indexed | 2024-03-10T10:12:39Z |
format | Article |
id | doaj.art-61d896c9a9f04ca4b0f5c74d86a5f4b0 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T10:12:39Z |
publishDate | 2021-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-61d896c9a9f04ca4b0f5c74d86a5f4b02023-11-22T01:04:57ZengMDPI AGSensors1424-82202021-06-012112424610.3390/s21124246RGB-D Data-Based Action Recognition: A ReviewMuhammad Bilal Shaikh0Douglas Chai1School of Engineering, Edith Cowan University, Perth, WA 6027, AustraliaSchool of Engineering, Edith Cowan University, Perth, WA 6027, AustraliaClassification of human actions is an ongoing research problem in computer vision. This review is aimed to scope current literature on data fusion and action recognition techniques and to identify gaps and future research direction. Success in producing cost-effective and portable vision-based sensors has dramatically increased the number and size of datasets. The increase in the number of action recognition datasets intersects with advances in deep learning architectures and computational support, both of which offer significant research opportunities. Naturally, each action-data modality—such as RGB, depth, skeleton, and infrared (IR)—has distinct characteristics; therefore, it is important to exploit the value of each modality for better action recognition. In this paper, we focus solely on data fusion and recognition techniques in the context of vision with an RGB-D perspective. We conclude by discussing research challenges, emerging trends, and possible future research directions.https://www.mdpi.com/1424-8220/21/12/4246action recognitiondeep learningdata fusionRGB-D |
spellingShingle | Muhammad Bilal Shaikh Douglas Chai RGB-D Data-Based Action Recognition: A Review Sensors action recognition deep learning data fusion RGB-D |
title | RGB-D Data-Based Action Recognition: A Review |
title_full | RGB-D Data-Based Action Recognition: A Review |
title_fullStr | RGB-D Data-Based Action Recognition: A Review |
title_full_unstemmed | RGB-D Data-Based Action Recognition: A Review |
title_short | RGB-D Data-Based Action Recognition: A Review |
title_sort | rgb d data based action recognition a review |
topic | action recognition deep learning data fusion RGB-D |
url | https://www.mdpi.com/1424-8220/21/12/4246 |
work_keys_str_mv | AT muhammadbilalshaikh rgbddatabasedactionrecognitionareview AT douglaschai rgbddatabasedactionrecognitionareview |