Survey on Computer Vision Techniques for Internet-of-Things Devices

Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deplo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-08
Hauptverfasser: Kaur, Ishmeet, Jadhav, Adwaita Janardhan
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 Kaur, Ishmeet
Jadhav, Adwaita Janardhan
description Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deploy on small battery-powered Internet-of-Things (IoT) devices with limited computing resources. Deployment of DNNs on Internet-of-Things devices, such as traffic cameras, can improve public safety by enabling applications such as automatic accident detection and emergency response.Through this paper, we survey the recent advances in low-power and energy-efficient DNN implementations that improve the deployability of DNNs without significantly sacrificing accuracy. In general, these techniques either reduce the memory requirements, the number of arithmetic operations, or both. The techniques can be divided into three major categories: neural network compression, network architecture search and design, and compiler and graph optimizations. In this paper, we survey both low-power techniques for both convolutional and transformer DNNs, and summarize the advantages, disadvantages, and open research problems.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2847577649</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2847577649</sourcerecordid><originalsourceid>FETCH-proquest_journals_28475776493</originalsourceid><addsrcrecordid>eNqNi9EKgjAYRkcQJOU7DLoe2DadXa-irpNuReRfTmqz_U7o7TPoAbo6fJzvLEjChdixUnK-Iilin2UZLxTPc5EQfY1hgjf1jmr_HOIIgd4s2nlX0HbOviIgNT7Qi5udg5F5w6rOujvSA0y2BdyQpWkeCOmPa7I9HSt9ZkPw33ysex-Dm1XNS6lypQq5F_-9PgbPOlg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2847577649</pqid></control><display><type>article</type><title>Survey on Computer Vision Techniques for Internet-of-Things Devices</title><source>Free E- Journals</source><creator>Kaur, Ishmeet ; Jadhav, Adwaita Janardhan</creator><creatorcontrib>Kaur, Ishmeet ; Jadhav, Adwaita Janardhan</creatorcontrib><description>Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deploy on small battery-powered Internet-of-Things (IoT) devices with limited computing resources. Deployment of DNNs on Internet-of-Things devices, such as traffic cameras, can improve public safety by enabling applications such as automatic accident detection and emergency response.Through this paper, we survey the recent advances in low-power and energy-efficient DNN implementations that improve the deployability of DNNs without significantly sacrificing accuracy. In general, these techniques either reduce the memory requirements, the number of arithmetic operations, or both. The techniques can be divided into three major categories: neural network compression, network architecture search and design, and compiler and graph optimizations. In this paper, we survey both low-power techniques for both convolutional and transformer DNNs, and summarize the advantages, disadvantages, and open research problems.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Accident detection ; Artificial neural networks ; Computer architecture ; Computer vision ; Design optimization ; Emergency response ; Internet of Things ; Neural networks ; Power management ; Public safety ; State of the art</subject><ispartof>arXiv.org, 2023-08</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>780,784</link.rule.ids></links><search><creatorcontrib>Kaur, Ishmeet</creatorcontrib><creatorcontrib>Jadhav, Adwaita Janardhan</creatorcontrib><title>Survey on Computer Vision Techniques for Internet-of-Things Devices</title><title>arXiv.org</title><description>Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deploy on small battery-powered Internet-of-Things (IoT) devices with limited computing resources. Deployment of DNNs on Internet-of-Things devices, such as traffic cameras, can improve public safety by enabling applications such as automatic accident detection and emergency response.Through this paper, we survey the recent advances in low-power and energy-efficient DNN implementations that improve the deployability of DNNs without significantly sacrificing accuracy. In general, these techniques either reduce the memory requirements, the number of arithmetic operations, or both. The techniques can be divided into three major categories: neural network compression, network architecture search and design, and compiler and graph optimizations. In this paper, we survey both low-power techniques for both convolutional and transformer DNNs, and summarize the advantages, disadvantages, and open research problems.</description><subject>Accident detection</subject><subject>Artificial neural networks</subject><subject>Computer architecture</subject><subject>Computer vision</subject><subject>Design optimization</subject><subject>Emergency response</subject><subject>Internet of Things</subject><subject>Neural networks</subject><subject>Power management</subject><subject>Public safety</subject><subject>State of the art</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>eNqNi9EKgjAYRkcQJOU7DLoe2DadXa-irpNuReRfTmqz_U7o7TPoAbo6fJzvLEjChdixUnK-Iilin2UZLxTPc5EQfY1hgjf1jmr_HOIIgd4s2nlX0HbOviIgNT7Qi5udg5F5w6rOujvSA0y2BdyQpWkeCOmPa7I9HSt9ZkPw33ysex-Dm1XNS6lypQq5F_-9PgbPOlg</recordid><startdate>20230802</startdate><enddate>20230802</enddate><creator>Kaur, Ishmeet</creator><creator>Jadhav, Adwaita Janardhan</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>PTHSS</scope></search><sort><creationdate>20230802</creationdate><title>Survey on Computer Vision Techniques for Internet-of-Things Devices</title><author>Kaur, Ishmeet ; Jadhav, Adwaita Janardhan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28475776493</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accident detection</topic><topic>Artificial neural networks</topic><topic>Computer architecture</topic><topic>Computer vision</topic><topic>Design optimization</topic><topic>Emergency response</topic><topic>Internet of Things</topic><topic>Neural networks</topic><topic>Power management</topic><topic>Public safety</topic><topic>State of the art</topic><toplevel>online_resources</toplevel><creatorcontrib>Kaur, Ishmeet</creatorcontrib><creatorcontrib>Jadhav, Adwaita Janardhan</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 (ProQuest)</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>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kaur, Ishmeet</au><au>Jadhav, Adwaita Janardhan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Survey on Computer Vision Techniques for Internet-of-Things Devices</atitle><jtitle>arXiv.org</jtitle><date>2023-08-02</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Deep neural networks (DNNs) are state-of-the-art techniques for solving most computer vision problems. DNNs require billions of parameters and operations to achieve state-of-the-art results. This requirement makes DNNs extremely compute, memory, and energy-hungry, and consequently difficult to deploy on small battery-powered Internet-of-Things (IoT) devices with limited computing resources. Deployment of DNNs on Internet-of-Things devices, such as traffic cameras, can improve public safety by enabling applications such as automatic accident detection and emergency response.Through this paper, we survey the recent advances in low-power and energy-efficient DNN implementations that improve the deployability of DNNs without significantly sacrificing accuracy. In general, these techniques either reduce the memory requirements, the number of arithmetic operations, or both. The techniques can be divided into three major categories: neural network compression, network architecture search and design, and compiler and graph optimizations. In this paper, we survey both low-power techniques for both convolutional and transformer DNNs, and summarize the advantages, disadvantages, and open research problems.</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, 2023-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2847577649
source Free E- Journals
subjects Accident detection
Artificial neural networks
Computer architecture
Computer vision
Design optimization
Emergency response
Internet of Things
Neural networks
Power management
Public safety
State of the art
title Survey on Computer Vision Techniques for Internet-of-Things Devices
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T07%3A46%3A46IST&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=Survey%20on%20Computer%20Vision%20Techniques%20for%20Internet-of-Things%20Devices&rft.jtitle=arXiv.org&rft.au=Kaur,%20Ishmeet&rft.date=2023-08-02&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2847577649%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2847577649&rft_id=info:pmid/&rfr_iscdi=true