Perceptible Lightweight Zero-Mean Normalized Cross-Correlation for Infrared Template Matching
Infrared template matching is an essential technology that enables reliable and accurate object detection, recognition, and tracking in complex environments. Perceptible Lightweight Zero-mean normalized cross-correlation (ZNCC) Template Matching (PLZ-TM) has been proposed as a tool for matching infr...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2024, Vol.12, p.164777-164791 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 164791 |
|---|---|
| container_issue | |
| container_start_page | 164777 |
| container_title | IEEE access |
| container_volume | 12 |
| creator | Lee, Seungeon Kim, Donyung Park, Inho Kim, Geonjong Kim, Sungho |
| description | Infrared template matching is an essential technology that enables reliable and accurate object detection, recognition, and tracking in complex environments. Perceptible Lightweight Zero-mean normalized cross-correlation (ZNCC) Template Matching (PLZ-TM) has been proposed as a tool for matching infrared images obtained from cameras with different fields of view. Aligning such images is challenging because of the involved differences in thermal distributions, focus discrepancies, background elements, and distortions. The first stage of PLZ-TM involves extracting feature maps from the search and template images using a deep learning network. This deep learning network is designed with a Convolutional Neural Network (CNN) architecture that omits pooling layers, thereby minimizing information loss during extraction. The subsequent stage involves matching the feature maps. The matching method utilizes a lightweight ZNCC (ZNCC) module that employs average pooling for training. The deep learning network is trained to optimize the distribution of the output heatmap and the probability at the correct location of the template image. PLZ-TM delivers excellent performance achieving a processing time of only 3.3 ms in matching a 640\times 480 search image with a 192\times 144 template image. Moreover, it attains a matching accuracy of 96% on a dataset obtained from infrared cameras with different fields of view. |
| doi_str_mv | 10.1109/ACCESS.2024.3492206 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_10747364</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10747364</ieee_id><doaj_id>oai_doaj_org_article_dccb51aaa7504e2ea2f549542548c7d0</doaj_id><sourcerecordid>3127777629</sourcerecordid><originalsourceid>FETCH-LOGICAL-c289t-7cb872c1e664749f889559722bb1d1d3f1e90deaa74818e5825b593966dc86a13</originalsourceid><addsrcrecordid>eNpNUdtKw0AQDaKgaL9AHwI-p-798ijBS6FewPoiyLLZTOqWNFs3KaJf79aIOA-zw9k5Z4Y5WXaK0RRjpC8uy_Lq6WlKEGFTyjQhSOxlRwQLXVBOxf6_-jCb9P0KpVAJ4vIoe32E6GAz-KqFfO6Xb8MH7HL-AjEUd2C7_D7EtW39F9R5GUPfF2WIEVo7-NDlTYj5rGuijel7AetNwiG_s4N7893yJDtobNvD5Pc9zp6vrxblbTF_uJmVl_PCEaWHQrpKSeIwCMEk041SmnMtCakqXOOaNhg0qsFayRRWwBXhFddUC1E7JSymx9ls1K2DXZlN9GsbP02w3vwAIS6NjYN3LZjauYpjm7Q4YkDAkoYzzRnhTDlZo6R1PmptYnjfQj-YVdjGLq1vKCYyhSA6ddGxy-1OEqH5m4qR2dliRlvMzhbza0tinY0sDwD_GJJJKhj9BuWAiLM</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3127777629</pqid></control><display><type>article</type><title>Perceptible Lightweight Zero-Mean Normalized Cross-Correlation for Infrared Template Matching</title><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>IEEE Xplore Open Access Journals</source><creator>Lee, Seungeon ; Kim, Donyung ; Park, Inho ; Kim, Geonjong ; Kim, Sungho</creator><creatorcontrib>Lee, Seungeon ; Kim, Donyung ; Park, Inho ; Kim, Geonjong ; Kim, Sungho</creatorcontrib><description><![CDATA[Infrared template matching is an essential technology that enables reliable and accurate object detection, recognition, and tracking in complex environments. Perceptible Lightweight Zero-mean normalized cross-correlation (ZNCC) Template Matching (PLZ-TM) has been proposed as a tool for matching infrared images obtained from cameras with different fields of view. Aligning such images is challenging because of the involved differences in thermal distributions, focus discrepancies, background elements, and distortions. The first stage of PLZ-TM involves extracting feature maps from the search and template images using a deep learning network. This deep learning network is designed with a Convolutional Neural Network (CNN) architecture that omits pooling layers, thereby minimizing information loss during extraction. The subsequent stage involves matching the feature maps. The matching method utilizes a lightweight ZNCC (ZNCC) module that employs average pooling for training. The deep learning network is trained to optimize the distribution of the output heatmap and the probability at the correct location of the template image. PLZ-TM delivers excellent performance achieving a processing time of only 3.3 ms in matching a <inline-formula> <tex-math notation="LaTeX">640\times 480 </tex-math></inline-formula> search image with a <inline-formula> <tex-math notation="LaTeX">192\times 144 </tex-math></inline-formula> template image. Moreover, it attains a matching accuracy of 96% on a dataset obtained from infrared cameras with different fields of view.]]></description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2024.3492206</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Accuracy ; Artificial neural networks ; Brightness ; Cameras ; convolutional neural network ; Convolutional neural networks ; Cross correlation ; Deep learning ; Feature extraction ; Feature maps ; Image matching ; infrared ; Infrared cameras ; Infrared imagery ; Infrared imaging ; Infrared tracking ; Lightweight ; Machine learning ; Object recognition ; Object tracking ; real-time ; Real-time systems ; Template matching ; Training ; Weight reduction ; zero-mean normalized cross correlation</subject><ispartof>IEEE access, 2024, Vol.12, p.164777-164791</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c289t-7cb872c1e664749f889559722bb1d1d3f1e90deaa74818e5825b593966dc86a13</cites><orcidid>0000-0002-5401-2459 ; 0009-0009-9693-2358 ; 0000-0003-0193-6700</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10747364$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,860,2096,4010,27610,27900,27901,27902,54908</link.rule.ids></links><search><creatorcontrib>Lee, Seungeon</creatorcontrib><creatorcontrib>Kim, Donyung</creatorcontrib><creatorcontrib>Park, Inho</creatorcontrib><creatorcontrib>Kim, Geonjong</creatorcontrib><creatorcontrib>Kim, Sungho</creatorcontrib><title>Perceptible Lightweight Zero-Mean Normalized Cross-Correlation for Infrared Template Matching</title><title>IEEE access</title><addtitle>Access</addtitle><description><![CDATA[Infrared template matching is an essential technology that enables reliable and accurate object detection, recognition, and tracking in complex environments. Perceptible Lightweight Zero-mean normalized cross-correlation (ZNCC) Template Matching (PLZ-TM) has been proposed as a tool for matching infrared images obtained from cameras with different fields of view. Aligning such images is challenging because of the involved differences in thermal distributions, focus discrepancies, background elements, and distortions. The first stage of PLZ-TM involves extracting feature maps from the search and template images using a deep learning network. This deep learning network is designed with a Convolutional Neural Network (CNN) architecture that omits pooling layers, thereby minimizing information loss during extraction. The subsequent stage involves matching the feature maps. The matching method utilizes a lightweight ZNCC (ZNCC) module that employs average pooling for training. The deep learning network is trained to optimize the distribution of the output heatmap and the probability at the correct location of the template image. PLZ-TM delivers excellent performance achieving a processing time of only 3.3 ms in matching a <inline-formula> <tex-math notation="LaTeX">640\times 480 </tex-math></inline-formula> search image with a <inline-formula> <tex-math notation="LaTeX">192\times 144 </tex-math></inline-formula> template image. Moreover, it attains a matching accuracy of 96% on a dataset obtained from infrared cameras with different fields of view.]]></description><subject>Accuracy</subject><subject>Artificial neural networks</subject><subject>Brightness</subject><subject>Cameras</subject><subject>convolutional neural network</subject><subject>Convolutional neural networks</subject><subject>Cross correlation</subject><subject>Deep learning</subject><subject>Feature extraction</subject><subject>Feature maps</subject><subject>Image matching</subject><subject>infrared</subject><subject>Infrared cameras</subject><subject>Infrared imagery</subject><subject>Infrared imaging</subject><subject>Infrared tracking</subject><subject>Lightweight</subject><subject>Machine learning</subject><subject>Object recognition</subject><subject>Object tracking</subject><subject>real-time</subject><subject>Real-time systems</subject><subject>Template matching</subject><subject>Training</subject><subject>Weight reduction</subject><subject>zero-mean normalized cross correlation</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUdtKw0AQDaKgaL9AHwI-p-798ijBS6FewPoiyLLZTOqWNFs3KaJf79aIOA-zw9k5Z4Y5WXaK0RRjpC8uy_Lq6WlKEGFTyjQhSOxlRwQLXVBOxf6_-jCb9P0KpVAJ4vIoe32E6GAz-KqFfO6Xb8MH7HL-AjEUd2C7_D7EtW39F9R5GUPfF2WIEVo7-NDlTYj5rGuijel7AetNwiG_s4N7893yJDtobNvD5Pc9zp6vrxblbTF_uJmVl_PCEaWHQrpKSeIwCMEk041SmnMtCakqXOOaNhg0qsFayRRWwBXhFddUC1E7JSymx9ls1K2DXZlN9GsbP02w3vwAIS6NjYN3LZjauYpjm7Q4YkDAkoYzzRnhTDlZo6R1PmptYnjfQj-YVdjGLq1vKCYyhSA6ddGxy-1OEqH5m4qR2dliRlvMzhbza0tinY0sDwD_GJJJKhj9BuWAiLM</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Lee, Seungeon</creator><creator>Kim, Donyung</creator><creator>Park, Inho</creator><creator>Kim, Geonjong</creator><creator>Kim, Sungho</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-5401-2459</orcidid><orcidid>https://orcid.org/0009-0009-9693-2358</orcidid><orcidid>https://orcid.org/0000-0003-0193-6700</orcidid></search><sort><creationdate>2024</creationdate><title>Perceptible Lightweight Zero-Mean Normalized Cross-Correlation for Infrared Template Matching</title><author>Lee, Seungeon ; Kim, Donyung ; Park, Inho ; Kim, Geonjong ; Kim, Sungho</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c289t-7cb872c1e664749f889559722bb1d1d3f1e90deaa74818e5825b593966dc86a13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Artificial neural networks</topic><topic>Brightness</topic><topic>Cameras</topic><topic>convolutional neural network</topic><topic>Convolutional neural networks</topic><topic>Cross correlation</topic><topic>Deep learning</topic><topic>Feature extraction</topic><topic>Feature maps</topic><topic>Image matching</topic><topic>infrared</topic><topic>Infrared cameras</topic><topic>Infrared imagery</topic><topic>Infrared imaging</topic><topic>Infrared tracking</topic><topic>Lightweight</topic><topic>Machine learning</topic><topic>Object recognition</topic><topic>Object tracking</topic><topic>real-time</topic><topic>Real-time systems</topic><topic>Template matching</topic><topic>Training</topic><topic>Weight reduction</topic><topic>zero-mean normalized cross correlation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lee, Seungeon</creatorcontrib><creatorcontrib>Kim, Donyung</creatorcontrib><creatorcontrib>Park, Inho</creatorcontrib><creatorcontrib>Kim, Geonjong</creatorcontrib><creatorcontrib>Kim, Sungho</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Xplore Open Access Journals</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>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lee, Seungeon</au><au>Kim, Donyung</au><au>Park, Inho</au><au>Kim, Geonjong</au><au>Kim, Sungho</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Perceptible Lightweight Zero-Mean Normalized Cross-Correlation for Infrared Template Matching</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2024</date><risdate>2024</risdate><volume>12</volume><spage>164777</spage><epage>164791</epage><pages>164777-164791</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract><![CDATA[Infrared template matching is an essential technology that enables reliable and accurate object detection, recognition, and tracking in complex environments. Perceptible Lightweight Zero-mean normalized cross-correlation (ZNCC) Template Matching (PLZ-TM) has been proposed as a tool for matching infrared images obtained from cameras with different fields of view. Aligning such images is challenging because of the involved differences in thermal distributions, focus discrepancies, background elements, and distortions. The first stage of PLZ-TM involves extracting feature maps from the search and template images using a deep learning network. This deep learning network is designed with a Convolutional Neural Network (CNN) architecture that omits pooling layers, thereby minimizing information loss during extraction. The subsequent stage involves matching the feature maps. The matching method utilizes a lightweight ZNCC (ZNCC) module that employs average pooling for training. The deep learning network is trained to optimize the distribution of the output heatmap and the probability at the correct location of the template image. PLZ-TM delivers excellent performance achieving a processing time of only 3.3 ms in matching a <inline-formula> <tex-math notation="LaTeX">640\times 480 </tex-math></inline-formula> search image with a <inline-formula> <tex-math notation="LaTeX">192\times 144 </tex-math></inline-formula> template image. Moreover, it attains a matching accuracy of 96% on a dataset obtained from infrared cameras with different fields of view.]]></abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2024.3492206</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-5401-2459</orcidid><orcidid>https://orcid.org/0009-0009-9693-2358</orcidid><orcidid>https://orcid.org/0000-0003-0193-6700</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2024, Vol.12, p.164777-164791 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_ieee_primary_10747364 |
| source | DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; IEEE Xplore Open Access Journals |
| subjects | Accuracy Artificial neural networks Brightness Cameras convolutional neural network Convolutional neural networks Cross correlation Deep learning Feature extraction Feature maps Image matching infrared Infrared cameras Infrared imagery Infrared imaging Infrared tracking Lightweight Machine learning Object recognition Object tracking real-time Real-time systems Template matching Training Weight reduction zero-mean normalized cross correlation |
| title | Perceptible Lightweight Zero-Mean Normalized Cross-Correlation for Infrared Template Matching |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T10%3A26%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Perceptible%20Lightweight%20Zero-Mean%20Normalized%20Cross-Correlation%20for%20Infrared%20Template%20Matching&rft.jtitle=IEEE%20access&rft.au=Lee,%20Seungeon&rft.date=2024&rft.volume=12&rft.spage=164777&rft.epage=164791&rft.pages=164777-164791&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2024.3492206&rft_dat=%3Cproquest_ieee_%3E3127777629%3C/proquest_ieee_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3127777629&rft_id=info:pmid/&rft_ieee_id=10747364&rft_doaj_id=oai_doaj_org_article_dccb51aaa7504e2ea2f549542548c7d0&rfr_iscdi=true |