Loading…
Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case
Printed circuit boards (PCBs) are essential components of electronic devices, and ensuring their quality is crucial in their production. However, the vast variety of components and PCBs manufactured by different companies makes it challenging to adapt to production lines with speed demands. To addre...
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 | 4471 |
container_issue | |
container_start_page | 4464 |
container_title | |
container_volume | |
creator | Shamsafar, Faranak Jaiswal, Sunil Kelkel, Benjamin Bodduna, Kireeti Illgner-Fehns, Klaus |
description | Printed circuit boards (PCBs) are essential components of electronic devices, and ensuring their quality is crucial in their production. However, the vast variety of components and PCBs manufactured by different companies makes it challenging to adapt to production lines with speed demands. To address this challenge, we present a multi-view object detection framework that offers a fast and precise solution. We introduce a novel multi-view dataset with semiautomatic ground-truth data, which results in significant labeling resource savings. Labeling PCB boards for object detection is a challenging task due to the high density of components and the small size of the objects, which makes it difficult to identify and label them accurately. By training an object detector model with multi-view data, we achieve improved performance over single-view images. To further enhance the accuracy, we develop a multi-view inference method that aggregates results from different viewpoints. Our experiments demonstrate a 15% improvement in mAP for detecting components that range in size from 0.5 to 27.0 mm. |
doi_str_mv | 10.1109/CVPRW59228.2023.00469 |
format | conference_proceeding |
fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10208794</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10208794</ieee_id><sourcerecordid>10208794</sourcerecordid><originalsourceid>FETCH-LOGICAL-i119t-8e813b80a991cd239406f159e698365980d8853dcf1f2a95111d1d8773c271d03</originalsourceid><addsrcrecordid>eNotjl1LwzAUQKMgOGb_gUL-QOe9SdPm-jY6PwoThzh9HLG5HZG2G2k38d870KfzcOBwhLhBmCEC3Zbvq9cPQ0rZmQKlZwBZTmcioYKsNqBBZaTPxURhDmlhML8UyTB8AQCCNYb0RKyXfOTotqHfyudDO4b0GPhbLtzoZLOLsur2cXdkLxc8cj2GXS9XHE-mc33Nd3Ley6r3h2GMwbVyPbAs3cBX4qJx7cDJP6di_XD_Vj6ly5fHqpwv04BIY2rZov604Iiw9kpTBnmDhjg__eeGLHhrjfZ1g41yZBDRo7dFoWtVoAc9Fdd_3cDMm30MnYs_GwQFtqBM_wK9qFEi</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case</title><source>IEEE Xplore All Conference Series</source><creator>Shamsafar, Faranak ; Jaiswal, Sunil ; Kelkel, Benjamin ; Bodduna, Kireeti ; Illgner-Fehns, Klaus</creator><creatorcontrib>Shamsafar, Faranak ; Jaiswal, Sunil ; Kelkel, Benjamin ; Bodduna, Kireeti ; Illgner-Fehns, Klaus</creatorcontrib><description>Printed circuit boards (PCBs) are essential components of electronic devices, and ensuring their quality is crucial in their production. However, the vast variety of components and PCBs manufactured by different companies makes it challenging to adapt to production lines with speed demands. To address this challenge, we present a multi-view object detection framework that offers a fast and precise solution. We introduce a novel multi-view dataset with semiautomatic ground-truth data, which results in significant labeling resource savings. Labeling PCB boards for object detection is a challenging task due to the high density of components and the small size of the objects, which makes it difficult to identify and label them accurately. By training an object detector model with multi-view data, we achieve improved performance over single-view images. To further enhance the accuracy, we develop a multi-view inference method that aggregates results from different viewpoints. Our experiments demonstrate a 15% improvement in mAP for detecting components that range in size from 0.5 to 27.0 mm.</description><identifier>EISSN: 2160-7516</identifier><identifier>EISBN: 9798350302493</identifier><identifier>DOI: 10.1109/CVPRW59228.2023.00469</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Detectors ; Manuals ; Object detection ; Pattern recognition ; Printed circuits ; Production ; Training</subject><ispartof>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, p.4464-4471</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/10208794$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10208794$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Shamsafar, Faranak</creatorcontrib><creatorcontrib>Jaiswal, Sunil</creatorcontrib><creatorcontrib>Kelkel, Benjamin</creatorcontrib><creatorcontrib>Bodduna, Kireeti</creatorcontrib><creatorcontrib>Illgner-Fehns, Klaus</creatorcontrib><title>Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case</title><title>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</title><addtitle>CVPRW</addtitle><description>Printed circuit boards (PCBs) are essential components of electronic devices, and ensuring their quality is crucial in their production. However, the vast variety of components and PCBs manufactured by different companies makes it challenging to adapt to production lines with speed demands. To address this challenge, we present a multi-view object detection framework that offers a fast and precise solution. We introduce a novel multi-view dataset with semiautomatic ground-truth data, which results in significant labeling resource savings. Labeling PCB boards for object detection is a challenging task due to the high density of components and the small size of the objects, which makes it difficult to identify and label them accurately. By training an object detector model with multi-view data, we achieve improved performance over single-view images. To further enhance the accuracy, we develop a multi-view inference method that aggregates results from different viewpoints. Our experiments demonstrate a 15% improvement in mAP for detecting components that range in size from 0.5 to 27.0 mm.</description><subject>Detectors</subject><subject>Manuals</subject><subject>Object detection</subject><subject>Pattern recognition</subject><subject>Printed circuits</subject><subject>Production</subject><subject>Training</subject><issn>2160-7516</issn><isbn>9798350302493</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjl1LwzAUQKMgOGb_gUL-QOe9SdPm-jY6PwoThzh9HLG5HZG2G2k38d870KfzcOBwhLhBmCEC3Zbvq9cPQ0rZmQKlZwBZTmcioYKsNqBBZaTPxURhDmlhML8UyTB8AQCCNYb0RKyXfOTotqHfyudDO4b0GPhbLtzoZLOLsur2cXdkLxc8cj2GXS9XHE-mc33Nd3Ley6r3h2GMwbVyPbAs3cBX4qJx7cDJP6di_XD_Vj6ly5fHqpwv04BIY2rZov604Iiw9kpTBnmDhjg__eeGLHhrjfZ1g41yZBDRo7dFoWtVoAc9Fdd_3cDMm30MnYs_GwQFtqBM_wK9qFEi</recordid><startdate>202306</startdate><enddate>202306</enddate><creator>Shamsafar, Faranak</creator><creator>Jaiswal, Sunil</creator><creator>Kelkel, Benjamin</creator><creator>Bodduna, Kireeti</creator><creator>Illgner-Fehns, Klaus</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>202306</creationdate><title>Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case</title><author>Shamsafar, Faranak ; Jaiswal, Sunil ; Kelkel, Benjamin ; Bodduna, Kireeti ; Illgner-Fehns, Klaus</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i119t-8e813b80a991cd239406f159e698365980d8853dcf1f2a95111d1d8773c271d03</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Detectors</topic><topic>Manuals</topic><topic>Object detection</topic><topic>Pattern recognition</topic><topic>Printed circuits</topic><topic>Production</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Shamsafar, Faranak</creatorcontrib><creatorcontrib>Jaiswal, Sunil</creatorcontrib><creatorcontrib>Kelkel, Benjamin</creatorcontrib><creatorcontrib>Bodduna, Kireeti</creatorcontrib><creatorcontrib>Illgner-Fehns, Klaus</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 Electronic Library Online</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>Shamsafar, Faranak</au><au>Jaiswal, Sunil</au><au>Kelkel, Benjamin</au><au>Bodduna, Kireeti</au><au>Illgner-Fehns, Klaus</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case</atitle><btitle>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</btitle><stitle>CVPRW</stitle><date>2023-06</date><risdate>2023</risdate><spage>4464</spage><epage>4471</epage><pages>4464-4471</pages><eissn>2160-7516</eissn><eisbn>9798350302493</eisbn><coden>IEEPAD</coden><abstract>Printed circuit boards (PCBs) are essential components of electronic devices, and ensuring their quality is crucial in their production. However, the vast variety of components and PCBs manufactured by different companies makes it challenging to adapt to production lines with speed demands. To address this challenge, we present a multi-view object detection framework that offers a fast and precise solution. We introduce a novel multi-view dataset with semiautomatic ground-truth data, which results in significant labeling resource savings. Labeling PCB boards for object detection is a challenging task due to the high density of components and the small size of the objects, which makes it difficult to identify and label them accurately. By training an object detector model with multi-view data, we achieve improved performance over single-view images. To further enhance the accuracy, we develop a multi-view inference method that aggregates results from different viewpoints. Our experiments demonstrate a 15% improvement in mAP for detecting components that range in size from 0.5 to 27.0 mm.</abstract><pub>IEEE</pub><doi>10.1109/CVPRW59228.2023.00469</doi><tpages>8</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | EISSN: 2160-7516 |
ispartof | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023, p.4464-4471 |
issn | 2160-7516 |
language | eng |
recordid | cdi_ieee_primary_10208794 |
source | IEEE Xplore All Conference Series |
subjects | Detectors Manuals Object detection Pattern recognition Printed circuits Production Training |
title | Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T09%3A02%3A31IST&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=Leveraging%20Multi-view%20Data%20for%20Improved%20Detection%20Performance:%20An%20Industrial%20Use%20Case&rft.btitle=2023%20IEEE/CVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20(CVPRW)&rft.au=Shamsafar,%20Faranak&rft.date=2023-06&rft.spage=4464&rft.epage=4471&rft.pages=4464-4471&rft.eissn=2160-7516&rft.coden=IEEPAD&rft_id=info:doi/10.1109/CVPRW59228.2023.00469&rft.eisbn=9798350302493&rft_dat=%3Cieee_CHZPO%3E10208794%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i119t-8e813b80a991cd239406f159e698365980d8853dcf1f2a95111d1d8773c271d03%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=10208794&rfr_iscdi=true |