Edge Intelligence Empowered Vehicle Detection and Image Segmentation for Autonomous Vehicles
Edge intelligence (EI) migrates data and artificial intelligence (AI) to the "edge" of a network, enhancing the high-bandwidth and low-latency of wireless data transmission with the multiplier effect of 5G and AI, greatly improving the edges' processing speed. Through integrating EI a...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on intelligent transportation systems 2023-11, Vol.24 (11), p.1-12 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 12 |
|---|---|
| container_issue | 11 |
| container_start_page | 1 |
| container_title | IEEE transactions on intelligent transportation systems |
| container_volume | 24 |
| creator | Chen, Chen Wang, Chenyu Liu, Bin He, Ci Cong, Li Wan, Shaohua |
| description | Edge intelligence (EI) migrates data and artificial intelligence (AI) to the "edge" of a network, enhancing the high-bandwidth and low-latency of wireless data transmission with the multiplier effect of 5G and AI, greatly improving the edges' processing speed. Through integrating EI and computer vision technology, video surveillance systems in ITS can improve the processing capability of traffic information, which improves traffic efficiency and ensures traffic safety. Accordingly, first, we propose an edge intelligence-based improved-YOLOv4 vehicle detection algorithm, introducing an efficient channel attention (ECA) mechanism and a high-resolution network (HRNet) to enhance vehicle detection ability. Second, an edge intelligence-based improved DeepLabv3+ image segmentation algorithm is proposed, replacing the original backbone network with MobileNetv2 and using the softpool method, thus reducing the network size while improving the segmentation accuracy. Experimental results show that our proposed model has a higher average precision (AP) and can improve vehicle detection accuracy from 82.03% to 86.22%. The mean intersection over union (mIOU) of the image segmentation model improves from 73.32% to 75.63%. |
| doi_str_mv | 10.1109/TITS.2022.3232153 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2884899204</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10007064</ieee_id><sourcerecordid>2884899204</sourcerecordid><originalsourceid>FETCH-LOGICAL-c294t-6afef5868c8917bee7ef4849cd04b84a10a12fcf8ca2dbeb9f4699ae7cba421c3</originalsourceid><addsrcrecordid>eNpNkNFKwzAUhoMoOKcPIHhR8LozSdM2uRxz08LAi02vhJCmJ7OjbWaSIr69rZvg1Tn8_N858CF0S_CMECwetsV2M6OY0llCE0rS5AxNSJryGGOSnY87ZbHAKb5EV97vh5SlhEzQ-7LaQVR0AZqm3kGnIVq2B_sFDqroDT5q3UD0CAF0qG0Xqa6KilYNyAZ2LXRB_cbGumjeB9vZ1vb-j_PX6MKoxsPNaU7R62q5XTzH65enYjFfx5oKFuJMGTApz7jmguQlQA6GcSZ0hVnJmSJYEWq04VrRqoRSGJYJoSDXpWKU6GSK7o93D85-9uCD3NvedcNLSTlnXAiK2dAix5Z21nsHRh5c3Sr3LQmWo0Q5SpSjRHmSODB3R6YGgH99jHOcseQHR5Rvbw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2884899204</pqid></control><display><type>article</type><title>Edge Intelligence Empowered Vehicle Detection and Image Segmentation for Autonomous Vehicles</title><source>IEEE Electronic Library (IEL)</source><creator>Chen, Chen ; Wang, Chenyu ; Liu, Bin ; He, Ci ; Cong, Li ; Wan, Shaohua</creator><creatorcontrib>Chen, Chen ; Wang, Chenyu ; Liu, Bin ; He, Ci ; Cong, Li ; Wan, Shaohua</creatorcontrib><description>Edge intelligence (EI) migrates data and artificial intelligence (AI) to the "edge" of a network, enhancing the high-bandwidth and low-latency of wireless data transmission with the multiplier effect of 5G and AI, greatly improving the edges' processing speed. Through integrating EI and computer vision technology, video surveillance systems in ITS can improve the processing capability of traffic information, which improves traffic efficiency and ensures traffic safety. Accordingly, first, we propose an edge intelligence-based improved-YOLOv4 vehicle detection algorithm, introducing an efficient channel attention (ECA) mechanism and a high-resolution network (HRNet) to enhance vehicle detection ability. Second, an edge intelligence-based improved DeepLabv3+ image segmentation algorithm is proposed, replacing the original backbone network with MobileNetv2 and using the softpool method, thus reducing the network size while improving the segmentation accuracy. Experimental results show that our proposed model has a higher average precision (AP) and can improve vehicle detection accuracy from 82.03% to 86.22%. The mean intersection over union (mIOU) of the image segmentation model improves from 73.32% to 75.63%.</description><identifier>ISSN: 1524-9050</identifier><identifier>EISSN: 1558-0016</identifier><identifier>DOI: 10.1109/TITS.2022.3232153</identifier><identifier>CODEN: ITISFG</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Artificial intelligence ; attention mechanism ; Computer networks ; Computer vision ; Convolution ; Data transmission ; edge intelligence ; Image edge detection ; Image enhancement ; Image segmentation ; Network latency ; Object detection ; power constraint network ; Real-time systems ; Surveillance systems ; Task analysis ; Traffic information ; Vehicle detection</subject><ispartof>IEEE transactions on intelligent transportation systems, 2023-11, Vol.24 (11), p.1-12</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c294t-6afef5868c8917bee7ef4849cd04b84a10a12fcf8ca2dbeb9f4699ae7cba421c3</citedby><cites>FETCH-LOGICAL-c294t-6afef5868c8917bee7ef4849cd04b84a10a12fcf8ca2dbeb9f4699ae7cba421c3</cites><orcidid>0000-0002-4971-5029 ; 0000-0001-7013-9081 ; 0000-0002-2877-1291</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10007064$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10007064$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chen, Chen</creatorcontrib><creatorcontrib>Wang, Chenyu</creatorcontrib><creatorcontrib>Liu, Bin</creatorcontrib><creatorcontrib>He, Ci</creatorcontrib><creatorcontrib>Cong, Li</creatorcontrib><creatorcontrib>Wan, Shaohua</creatorcontrib><title>Edge Intelligence Empowered Vehicle Detection and Image Segmentation for Autonomous Vehicles</title><title>IEEE transactions on intelligent transportation systems</title><addtitle>TITS</addtitle><description>Edge intelligence (EI) migrates data and artificial intelligence (AI) to the "edge" of a network, enhancing the high-bandwidth and low-latency of wireless data transmission with the multiplier effect of 5G and AI, greatly improving the edges' processing speed. Through integrating EI and computer vision technology, video surveillance systems in ITS can improve the processing capability of traffic information, which improves traffic efficiency and ensures traffic safety. Accordingly, first, we propose an edge intelligence-based improved-YOLOv4 vehicle detection algorithm, introducing an efficient channel attention (ECA) mechanism and a high-resolution network (HRNet) to enhance vehicle detection ability. Second, an edge intelligence-based improved DeepLabv3+ image segmentation algorithm is proposed, replacing the original backbone network with MobileNetv2 and using the softpool method, thus reducing the network size while improving the segmentation accuracy. Experimental results show that our proposed model has a higher average precision (AP) and can improve vehicle detection accuracy from 82.03% to 86.22%. The mean intersection over union (mIOU) of the image segmentation model improves from 73.32% to 75.63%.</description><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>attention mechanism</subject><subject>Computer networks</subject><subject>Computer vision</subject><subject>Convolution</subject><subject>Data transmission</subject><subject>edge intelligence</subject><subject>Image edge detection</subject><subject>Image enhancement</subject><subject>Image segmentation</subject><subject>Network latency</subject><subject>Object detection</subject><subject>power constraint network</subject><subject>Real-time systems</subject><subject>Surveillance systems</subject><subject>Task analysis</subject><subject>Traffic information</subject><subject>Vehicle detection</subject><issn>1524-9050</issn><issn>1558-0016</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkNFKwzAUhoMoOKcPIHhR8LozSdM2uRxz08LAi02vhJCmJ7OjbWaSIr69rZvg1Tn8_N858CF0S_CMECwetsV2M6OY0llCE0rS5AxNSJryGGOSnY87ZbHAKb5EV97vh5SlhEzQ-7LaQVR0AZqm3kGnIVq2B_sFDqroDT5q3UD0CAF0qG0Xqa6KilYNyAZ2LXRB_cbGumjeB9vZ1vb-j_PX6MKoxsPNaU7R62q5XTzH65enYjFfx5oKFuJMGTApz7jmguQlQA6GcSZ0hVnJmSJYEWq04VrRqoRSGJYJoSDXpWKU6GSK7o93D85-9uCD3NvedcNLSTlnXAiK2dAix5Z21nsHRh5c3Sr3LQmWo0Q5SpSjRHmSODB3R6YGgH99jHOcseQHR5Rvbw</recordid><startdate>20231101</startdate><enddate>20231101</enddate><creator>Chen, Chen</creator><creator>Wang, Chenyu</creator><creator>Liu, Bin</creator><creator>He, Ci</creator><creator>Cong, Li</creator><creator>Wan, Shaohua</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-4971-5029</orcidid><orcidid>https://orcid.org/0000-0001-7013-9081</orcidid><orcidid>https://orcid.org/0000-0002-2877-1291</orcidid></search><sort><creationdate>20231101</creationdate><title>Edge Intelligence Empowered Vehicle Detection and Image Segmentation for Autonomous Vehicles</title><author>Chen, Chen ; Wang, Chenyu ; Liu, Bin ; He, Ci ; Cong, Li ; Wan, Shaohua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c294t-6afef5868c8917bee7ef4849cd04b84a10a12fcf8ca2dbeb9f4699ae7cba421c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>attention mechanism</topic><topic>Computer networks</topic><topic>Computer vision</topic><topic>Convolution</topic><topic>Data transmission</topic><topic>edge intelligence</topic><topic>Image edge detection</topic><topic>Image enhancement</topic><topic>Image segmentation</topic><topic>Network latency</topic><topic>Object detection</topic><topic>power constraint network</topic><topic>Real-time systems</topic><topic>Surveillance systems</topic><topic>Task analysis</topic><topic>Traffic information</topic><topic>Vehicle detection</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Chen</creatorcontrib><creatorcontrib>Wang, Chenyu</creatorcontrib><creatorcontrib>Liu, Bin</creatorcontrib><creatorcontrib>He, Ci</creatorcontrib><creatorcontrib>Cong, Li</creatorcontrib><creatorcontrib>Wan, Shaohua</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on intelligent transportation systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Chen</au><au>Wang, Chenyu</au><au>Liu, Bin</au><au>He, Ci</au><au>Cong, Li</au><au>Wan, Shaohua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Edge Intelligence Empowered Vehicle Detection and Image Segmentation for Autonomous Vehicles</atitle><jtitle>IEEE transactions on intelligent transportation systems</jtitle><stitle>TITS</stitle><date>2023-11-01</date><risdate>2023</risdate><volume>24</volume><issue>11</issue><spage>1</spage><epage>12</epage><pages>1-12</pages><issn>1524-9050</issn><eissn>1558-0016</eissn><coden>ITISFG</coden><abstract>Edge intelligence (EI) migrates data and artificial intelligence (AI) to the "edge" of a network, enhancing the high-bandwidth and low-latency of wireless data transmission with the multiplier effect of 5G and AI, greatly improving the edges' processing speed. Through integrating EI and computer vision technology, video surveillance systems in ITS can improve the processing capability of traffic information, which improves traffic efficiency and ensures traffic safety. Accordingly, first, we propose an edge intelligence-based improved-YOLOv4 vehicle detection algorithm, introducing an efficient channel attention (ECA) mechanism and a high-resolution network (HRNet) to enhance vehicle detection ability. Second, an edge intelligence-based improved DeepLabv3+ image segmentation algorithm is proposed, replacing the original backbone network with MobileNetv2 and using the softpool method, thus reducing the network size while improving the segmentation accuracy. Experimental results show that our proposed model has a higher average precision (AP) and can improve vehicle detection accuracy from 82.03% to 86.22%. The mean intersection over union (mIOU) of the image segmentation model improves from 73.32% to 75.63%.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TITS.2022.3232153</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-4971-5029</orcidid><orcidid>https://orcid.org/0000-0001-7013-9081</orcidid><orcidid>https://orcid.org/0000-0002-2877-1291</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1524-9050 |
| ispartof | IEEE transactions on intelligent transportation systems, 2023-11, Vol.24 (11), p.1-12 |
| issn | 1524-9050 1558-0016 |
| language | eng |
| recordid | cdi_proquest_journals_2884899204 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Artificial intelligence attention mechanism Computer networks Computer vision Convolution Data transmission edge intelligence Image edge detection Image enhancement Image segmentation Network latency Object detection power constraint network Real-time systems Surveillance systems Task analysis Traffic information Vehicle detection |
| title | Edge Intelligence Empowered Vehicle Detection and Image Segmentation for Autonomous Vehicles |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T22%3A12%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Edge%20Intelligence%20Empowered%20Vehicle%20Detection%20and%20Image%20Segmentation%20for%20Autonomous%20Vehicles&rft.jtitle=IEEE%20transactions%20on%20intelligent%20transportation%20systems&rft.au=Chen,%20Chen&rft.date=2023-11-01&rft.volume=24&rft.issue=11&rft.spage=1&rft.epage=12&rft.pages=1-12&rft.issn=1524-9050&rft.eissn=1558-0016&rft.coden=ITISFG&rft_id=info:doi/10.1109/TITS.2022.3232153&rft_dat=%3Cproquest_RIE%3E2884899204%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2884899204&rft_id=info:pmid/&rft_ieee_id=10007064&rfr_iscdi=true |