Loading…
A Novel Deep Convolutional Neural Network Pooling Algorithm for Small floating objects detection
The problem of floating debris in rivers and oceans is growing. To clean floating objects on the water more effectively, IoT-based unmanned boats were chosen for autonomous cleaning. However, the strong light reflections of riverside objects on the water surface pose challenges for vision-based obje...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 176 |
| container_issue | |
| container_start_page | 175 |
| container_title | |
| container_volume | |
| creator | Shen, Jun-Yu Lu, Cheng-Kai Lim, Lam Ghai |
| description | The problem of floating debris in rivers and oceans is growing. To clean floating objects on the water more effectively, IoT-based unmanned boats were chosen for autonomous cleaning. However, the strong light reflections of riverside objects on the water surface pose challenges for vision-based object detection systems to detect small targets. By modifying the pooling module in Spatial Pyramid Pooling and using the TS-YOLO structure to retain the original spatial pyramid advantage, we improve the accuracy of floating litter for detecting objects on rivers. In the experimental results, our proposed method was tested on Pascal VOC, FLOW, and WIDER FACE, which showed good detection capability on mAP with 2.86%, 1%, and 2.28% improvement over the original YOLOv4. |
| doi_str_mv | 10.1109/ICCE-Taiwan58799.2023.10226754 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10226754</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10226754</ieee_id><sourcerecordid>10226754</sourcerecordid><originalsourceid>FETCH-LOGICAL-i119t-a291955e9a709f3cb30cbe305ef33905dcf87176413a8cd27e9dc10acf0a3303</originalsourceid><addsrcrecordid>eNo10E1PAjEUheFqYiJB_oGLrtwN3rZTOndJRhQSgiayx9K5xcEyJTMF4r8Xv1bP4iTv4jB2J2AoBOD9rCwn2dLWJ9vowiAOJUg1FCDlyOj8gg3QYKE0KJkLk1-yntRGZ4Us8ms26LotACiBAAJ77G3MF_FIgT8Q7XkZm2MMh1THxga-oEP7QzrF9oO_xBjqZsPHYRPbOr3vuI8tf93ZELgP0abvMa635FLHK0pnz50bduVt6GjwZ58tHyfLcprNn59m5Xie1UJgyqxEgVoTWgPolVsrcGtSoMkrhaAr5wsjzCgXyhaukoawcgKs82CVAtVnt7_ZmohW-7be2fZz9f-J-gKWIlmg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A Novel Deep Convolutional Neural Network Pooling Algorithm for Small floating objects detection</title><source>IEEE Xplore All Conference Series</source><creator>Shen, Jun-Yu ; Lu, Cheng-Kai ; Lim, Lam Ghai</creator><creatorcontrib>Shen, Jun-Yu ; Lu, Cheng-Kai ; Lim, Lam Ghai</creatorcontrib><description>The problem of floating debris in rivers and oceans is growing. To clean floating objects on the water more effectively, IoT-based unmanned boats were chosen for autonomous cleaning. However, the strong light reflections of riverside objects on the water surface pose challenges for vision-based object detection systems to detect small targets. By modifying the pooling module in Spatial Pyramid Pooling and using the TS-YOLO structure to retain the original spatial pyramid advantage, we improve the accuracy of floating litter for detecting objects on rivers. In the experimental results, our proposed method was tested on Pascal VOC, FLOW, and WIDER FACE, which showed good detection capability on mAP with 2.86%, 1%, and 2.28% improvement over the original YOLOv4.</description><identifier>EISSN: 2575-8284</identifier><identifier>EISBN: 9798350324174</identifier><identifier>DOI: 10.1109/ICCE-Taiwan58799.2023.10226754</identifier><language>eng</language><publisher>IEEE</publisher><subject>Boats ; Feature extraction ; neural network ; Object detection ; pooling ; Reflection ; Rivers ; Sea surface ; spatial pyramid pooling ; Surface cleaning ; YOLO</subject><ispartof>2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan), 2023, p.175-176</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10226754$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10226754$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Shen, Jun-Yu</creatorcontrib><creatorcontrib>Lu, Cheng-Kai</creatorcontrib><creatorcontrib>Lim, Lam Ghai</creatorcontrib><title>A Novel Deep Convolutional Neural Network Pooling Algorithm for Small floating objects detection</title><title>2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)</title><addtitle>ICCE-Taiwan</addtitle><description>The problem of floating debris in rivers and oceans is growing. To clean floating objects on the water more effectively, IoT-based unmanned boats were chosen for autonomous cleaning. However, the strong light reflections of riverside objects on the water surface pose challenges for vision-based object detection systems to detect small targets. By modifying the pooling module in Spatial Pyramid Pooling and using the TS-YOLO structure to retain the original spatial pyramid advantage, we improve the accuracy of floating litter for detecting objects on rivers. In the experimental results, our proposed method was tested on Pascal VOC, FLOW, and WIDER FACE, which showed good detection capability on mAP with 2.86%, 1%, and 2.28% improvement over the original YOLOv4.</description><subject>Boats</subject><subject>Feature extraction</subject><subject>neural network</subject><subject>Object detection</subject><subject>pooling</subject><subject>Reflection</subject><subject>Rivers</subject><subject>Sea surface</subject><subject>spatial pyramid pooling</subject><subject>Surface cleaning</subject><subject>YOLO</subject><issn>2575-8284</issn><isbn>9798350324174</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo10E1PAjEUheFqYiJB_oGLrtwN3rZTOndJRhQSgiayx9K5xcEyJTMF4r8Xv1bP4iTv4jB2J2AoBOD9rCwn2dLWJ9vowiAOJUg1FCDlyOj8gg3QYKE0KJkLk1-yntRGZ4Us8ms26LotACiBAAJ77G3MF_FIgT8Q7XkZm2MMh1THxga-oEP7QzrF9oO_xBjqZsPHYRPbOr3vuI8tf93ZELgP0abvMa635FLHK0pnz50bduVt6GjwZ58tHyfLcprNn59m5Xie1UJgyqxEgVoTWgPolVsrcGtSoMkrhaAr5wsjzCgXyhaukoawcgKs82CVAtVnt7_ZmohW-7be2fZz9f-J-gKWIlmg</recordid><startdate>20230717</startdate><enddate>20230717</enddate><creator>Shen, Jun-Yu</creator><creator>Lu, Cheng-Kai</creator><creator>Lim, Lam Ghai</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20230717</creationdate><title>A Novel Deep Convolutional Neural Network Pooling Algorithm for Small floating objects detection</title><author>Shen, Jun-Yu ; Lu, Cheng-Kai ; Lim, Lam Ghai</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i119t-a291955e9a709f3cb30cbe305ef33905dcf87176413a8cd27e9dc10acf0a3303</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Boats</topic><topic>Feature extraction</topic><topic>neural network</topic><topic>Object detection</topic><topic>pooling</topic><topic>Reflection</topic><topic>Rivers</topic><topic>Sea surface</topic><topic>spatial pyramid pooling</topic><topic>Surface cleaning</topic><topic>YOLO</topic><toplevel>online_resources</toplevel><creatorcontrib>Shen, Jun-Yu</creatorcontrib><creatorcontrib>Lu, Cheng-Kai</creatorcontrib><creatorcontrib>Lim, Lam Ghai</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Shen, Jun-Yu</au><au>Lu, Cheng-Kai</au><au>Lim, Lam Ghai</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A Novel Deep Convolutional Neural Network Pooling Algorithm for Small floating objects detection</atitle><btitle>2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)</btitle><stitle>ICCE-Taiwan</stitle><date>2023-07-17</date><risdate>2023</risdate><spage>175</spage><epage>176</epage><pages>175-176</pages><eissn>2575-8284</eissn><eisbn>9798350324174</eisbn><abstract>The problem of floating debris in rivers and oceans is growing. To clean floating objects on the water more effectively, IoT-based unmanned boats were chosen for autonomous cleaning. However, the strong light reflections of riverside objects on the water surface pose challenges for vision-based object detection systems to detect small targets. By modifying the pooling module in Spatial Pyramid Pooling and using the TS-YOLO structure to retain the original spatial pyramid advantage, we improve the accuracy of floating litter for detecting objects on rivers. In the experimental results, our proposed method was tested on Pascal VOC, FLOW, and WIDER FACE, which showed good detection capability on mAP with 2.86%, 1%, and 2.28% improvement over the original YOLOv4.</abstract><pub>IEEE</pub><doi>10.1109/ICCE-Taiwan58799.2023.10226754</doi><tpages>2</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2575-8284 |
| ispartof | 2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan), 2023, p.175-176 |
| issn | 2575-8284 |
| language | eng |
| recordid | cdi_ieee_primary_10226754 |
| source | IEEE Xplore All Conference Series |
| subjects | Boats Feature extraction neural network Object detection pooling Reflection Rivers Sea surface spatial pyramid pooling Surface cleaning YOLO |
| title | A Novel Deep Convolutional Neural Network Pooling Algorithm for Small floating objects detection |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T14%3A22%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20Novel%20Deep%20Convolutional%20Neural%20Network%20Pooling%20Algorithm%20for%20Small%20floating%20objects%20detection&rft.btitle=2023%20International%20Conference%20on%20Consumer%20Electronics%20-%20Taiwan%20(ICCE-Taiwan)&rft.au=Shen,%20Jun-Yu&rft.date=2023-07-17&rft.spage=175&rft.epage=176&rft.pages=175-176&rft.eissn=2575-8284&rft_id=info:doi/10.1109/ICCE-Taiwan58799.2023.10226754&rft.eisbn=9798350324174&rft_dat=%3Cieee_CHZPO%3E10226754%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i119t-a291955e9a709f3cb30cbe305ef33905dcf87176413a8cd27e9dc10acf0a3303%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10226754&rfr_iscdi=true |