A real-time algorithm for human action recognition in RGB and thermal video

A real-time algorithm for human action recognition in RGB and thermal video

Monitoring the movement and actions of humans in video in real-time is an important task. We present a deep learning based algorithm for human action recognition for both RGB and thermal cameras. It is able to detect and track humans and recognize four basic actions (standing, walking, running, lyin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fassold, Hannes, Gutjahr, Karlheinz, Weber, Anna, Perko, Roland
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Fassold, Hannes
Gutjahr, Karlheinz
Weber, Anna
Perko, Roland
description Monitoring the movement and actions of humans in video in real-time is an important task. We present a deep learning based algorithm for human action recognition for both RGB and thermal cameras. It is able to detect and track humans and recognize four basic actions (standing, walking, running, lying) in real-time on a notebook with a NVIDIA GPU. For this, it combines state of the art components for object detection (Scaled YoloV4), optical flow (RAFT) and pose estimation (EvoSkeleton). Qualitative experiments on a set of tunnel videos show that the proposed algorithm works robustly for both RGB and thermal video.
doi_str_mv 10.48550/arxiv.2304.01567
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2304_01567</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2304_01567</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-aae0de7b53ec0bf2052a0b65574728434e890f1158ea8eee45c98275f01f63943</originalsourceid><addsrcrecordid>eNotz8FOwzAQBFBfekAtH8AJ_0CCHXtj51gqKIhKlVDv0SZZN5ZiG5lQwd8DgdPMYTTSY-xGilJbAHGH-dNfykoJXQoJtbliL1ueCadi9oE4TueU_TwG7lLm40fAyLGffYo_oz6do1-6j_x1f88xDnweKQec-MUPlDZs5XB6p-v_XLPT48Np91Qcjvvn3fZQYG1MgUhiINOBol50rhJQoehqAKNNZbXSZBvhpARLaIlIQ9_YyoAT0tWq0WrNbv9uF037ln3A_NX-qtpFpb4BLI9GxQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A real-time algorithm for human action recognition in RGB and thermal video</title><source>arXiv.org</source><creator>Fassold, Hannes ; Gutjahr, Karlheinz ; Weber, Anna ; Perko, Roland</creator><creatorcontrib>Fassold, Hannes ; Gutjahr, Karlheinz ; Weber, Anna ; Perko, Roland</creatorcontrib><description>Monitoring the movement and actions of humans in video in real-time is an important task. We present a deep learning based algorithm for human action recognition for both RGB and thermal cameras. It is able to detect and track humans and recognize four basic actions (standing, walking, running, lying) in real-time on a notebook with a NVIDIA GPU. For this, it combines state of the art components for object detection (Scaled YoloV4), optical flow (RAFT) and pose estimation (EvoSkeleton). Qualitative experiments on a set of tunnel videos show that the proposed algorithm works robustly for both RGB and thermal video.</description><identifier>DOI: 10.48550/arxiv.2304.01567</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2023-04</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,778,883</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2304.01567$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2304.01567$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Fassold, Hannes</creatorcontrib><creatorcontrib>Gutjahr, Karlheinz</creatorcontrib><creatorcontrib>Weber, Anna</creatorcontrib><creatorcontrib>Perko, Roland</creatorcontrib><title>A real-time algorithm for human action recognition in RGB and thermal video</title><description>Monitoring the movement and actions of humans in video in real-time is an important task. We present a deep learning based algorithm for human action recognition for both RGB and thermal cameras. It is able to detect and track humans and recognize four basic actions (standing, walking, running, lying) in real-time on a notebook with a NVIDIA GPU. For this, it combines state of the art components for object detection (Scaled YoloV4), optical flow (RAFT) and pose estimation (EvoSkeleton). Qualitative experiments on a set of tunnel videos show that the proposed algorithm works robustly for both RGB and thermal video.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8FOwzAQBFBfekAtH8AJ_0CCHXtj51gqKIhKlVDv0SZZN5ZiG5lQwd8DgdPMYTTSY-xGilJbAHGH-dNfykoJXQoJtbliL1ueCadi9oE4TueU_TwG7lLm40fAyLGffYo_oz6do1-6j_x1f88xDnweKQec-MUPlDZs5XB6p-v_XLPT48Np91Qcjvvn3fZQYG1MgUhiINOBol50rhJQoehqAKNNZbXSZBvhpARLaIlIQ9_YyoAT0tWq0WrNbv9uF037ln3A_NX-qtpFpb4BLI9GxQ</recordid><startdate>20230404</startdate><enddate>20230404</enddate><creator>Fassold, Hannes</creator><creator>Gutjahr, Karlheinz</creator><creator>Weber, Anna</creator><creator>Perko, Roland</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230404</creationdate><title>A real-time algorithm for human action recognition in RGB and thermal video</title><author>Fassold, Hannes ; Gutjahr, Karlheinz ; Weber, Anna ; Perko, Roland</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-aae0de7b53ec0bf2052a0b65574728434e890f1158ea8eee45c98275f01f63943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Fassold, Hannes</creatorcontrib><creatorcontrib>Gutjahr, Karlheinz</creatorcontrib><creatorcontrib>Weber, Anna</creatorcontrib><creatorcontrib>Perko, Roland</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fassold, Hannes</au><au>Gutjahr, Karlheinz</au><au>Weber, Anna</au><au>Perko, Roland</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A real-time algorithm for human action recognition in RGB and thermal video</atitle><date>2023-04-04</date><risdate>2023</risdate><abstract>Monitoring the movement and actions of humans in video in real-time is an important task. We present a deep learning based algorithm for human action recognition for both RGB and thermal cameras. It is able to detect and track humans and recognize four basic actions (standing, walking, running, lying) in real-time on a notebook with a NVIDIA GPU. For this, it combines state of the art components for object detection (Scaled YoloV4), optical flow (RAFT) and pose estimation (EvoSkeleton). Qualitative experiments on a set of tunnel videos show that the proposed algorithm works robustly for both RGB and thermal video.</abstract><doi>10.48550/arxiv.2304.01567</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2304.01567
ispartof
issn
language eng
recordid cdi_arxiv_primary_2304_01567
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title A real-time algorithm for human action recognition in RGB and thermal video
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T21%3A34%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20real-time%20algorithm%20for%20human%20action%20recognition%20in%20RGB%20and%20thermal%20video&rft.au=Fassold,%20Hannes&rft.date=2023-04-04&rft_id=info:doi/10.48550/arxiv.2304.01567&rft_dat=%3Carxiv_GOX%3E2304_01567%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true