EdgeYOLO: An Edge-Real-Time Object Detector

This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-02
Hauptverfasser: Liu, Shihan, Zha, Junlin, Sun, Jian, Li, Zhuo, Wang, Gang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Liu, Shihan
Zha, Junlin
Sun, Jian
Li, Zhuo
Wang, Gang
description This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Inspired by FCOS, a lighter and more efficient decoupled head is proposed, and its inference speed can be improved with little loss of precision. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia Jetson AGX Xavier. We also designed lighter models with less parameters for edge computing devices with lower computing power, which also show better performances. Our source code, hyper-parameters and model weights are all available at https://github.com/LSH9832/edgeyolo.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2777166618</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2777166618</sourcerecordid><originalsourceid>FETCH-proquest_journals_27771666183</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdk1JT4309_G3UnDMUwBxdINSE3N0QzJzUxX8k7JSk0sUXFJLgFR-EQ8Da1piTnEqL5TmZlB2cw1x9tAtKMovLE0tLonPyi8tygNKxRuZm5sbmpmZGVoYE6cKAIWdL6o</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2777166618</pqid></control><display><type>article</type><title>EdgeYOLO: An Edge-Real-Time Object Detector</title><source>Free E- Journals</source><creator>Liu, Shihan ; Zha, Junlin ; Sun, Jian ; Li, Zhuo ; Wang, Gang</creator><creatorcontrib>Liu, Shihan ; Zha, Junlin ; Sun, Jian ; Li, Zhuo ; Wang, Gang</creatorcontrib><description>This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Inspired by FCOS, a lighter and more efficient decoupled head is proposed, and its inference speed can be improved with little loss of precision. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, and it meets real-time requirements (FPS&gt;=30) on edge-computing device Nvidia Jetson AGX Xavier. We also designed lighter models with less parameters for edge computing devices with lower computing power, which also show better performances. Our source code, hyper-parameters and model weights are all available at https://github.com/LSH9832/edgeyolo.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Accuracy ; Datasets ; Edge computing ; Mathematical models ; Object recognition ; Parameters ; Real time ; Source code</subject><ispartof>arXiv.org, 2023-02</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>776,780</link.rule.ids></links><search><creatorcontrib>Liu, Shihan</creatorcontrib><creatorcontrib>Zha, Junlin</creatorcontrib><creatorcontrib>Sun, Jian</creatorcontrib><creatorcontrib>Li, Zhuo</creatorcontrib><creatorcontrib>Wang, Gang</creatorcontrib><title>EdgeYOLO: An Edge-Real-Time Object Detector</title><title>arXiv.org</title><description>This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Inspired by FCOS, a lighter and more efficient decoupled head is proposed, and its inference speed can be improved with little loss of precision. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, and it meets real-time requirements (FPS&gt;=30) on edge-computing device Nvidia Jetson AGX Xavier. We also designed lighter models with less parameters for edge computing devices with lower computing power, which also show better performances. Our source code, hyper-parameters and model weights are all available at https://github.com/LSH9832/edgeyolo.</description><subject>Accuracy</subject><subject>Datasets</subject><subject>Edge computing</subject><subject>Mathematical models</subject><subject>Object recognition</subject><subject>Parameters</subject><subject>Real time</subject><subject>Source code</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQdk1JT4309_G3UnDMUwBxdINSE3N0QzJzUxX8k7JSk0sUXFJLgFR-EQ8Da1piTnEqL5TmZlB2cw1x9tAtKMovLE0tLonPyi8tygNKxRuZm5sbmpmZGVoYE6cKAIWdL6o</recordid><startdate>20230215</startdate><enddate>20230215</enddate><creator>Liu, Shihan</creator><creator>Zha, Junlin</creator><creator>Sun, Jian</creator><creator>Li, Zhuo</creator><creator>Wang, Gang</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20230215</creationdate><title>EdgeYOLO: An Edge-Real-Time Object Detector</title><author>Liu, Shihan ; Zha, Junlin ; Sun, Jian ; Li, Zhuo ; Wang, Gang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27771666183</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Datasets</topic><topic>Edge computing</topic><topic>Mathematical models</topic><topic>Object recognition</topic><topic>Parameters</topic><topic>Real time</topic><topic>Source code</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Shihan</creatorcontrib><creatorcontrib>Zha, Junlin</creatorcontrib><creatorcontrib>Sun, Jian</creatorcontrib><creatorcontrib>Li, Zhuo</creatorcontrib><creatorcontrib>Wang, Gang</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Shihan</au><au>Zha, Junlin</au><au>Sun, Jian</au><au>Li, Zhuo</au><au>Wang, Gang</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>EdgeYOLO: An Edge-Real-Time Object Detector</atitle><jtitle>arXiv.org</jtitle><date>2023-02-15</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework, which can be implemented in real time on edge computing platforms. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Inspired by FCOS, a lighter and more efficient decoupled head is proposed, and its inference speed can be improved with little loss of precision. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS COCO2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone2019-DET dataset, and it meets real-time requirements (FPS&gt;=30) on edge-computing device Nvidia Jetson AGX Xavier. We also designed lighter models with less parameters for edge computing devices with lower computing power, which also show better performances. Our source code, hyper-parameters and model weights are all available at https://github.com/LSH9832/edgeyolo.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2777166618
source Free E- Journals
subjects Accuracy
Datasets
Edge computing
Mathematical models
Object recognition
Parameters
Real time
Source code
title EdgeYOLO: An Edge-Real-Time Object Detector
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T16%3A18%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=EdgeYOLO:%20An%20Edge-Real-Time%20Object%20Detector&rft.jtitle=arXiv.org&rft.au=Liu,%20Shihan&rft.date=2023-02-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2777166618%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2777166618&rft_id=info:pmid/&rfr_iscdi=true