VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications
Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications. We propose a set of methods, which we colle...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2019-11 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| 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 | Wu, Chyuan-Tyng Isikdogan, Leo F Rao, Sushma Nayak, Bhavin Gerasimow, Timo Sutic, Aleksandar Ain-kedem, Liron Gilad, Michael |
| description | Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications. We propose a set of methods, which we collectively call VisionISP, to repurpose the ISP for machine consumption. VisionISP significantly reduces data transmission needs by reducing the bit-depth and resolution while preserving the relevant information. The blocks in VisionISP are simple, content-aware, and trainable. Experimental results show that VisionISP boosts the performance of a subsequent computer vision system trained to detect objects in an autonomous driving setting. The results demonstrate the potential and the practicality of VisionISP for computer vision applications. |
| doi_str_mv | 10.48550/arxiv.1911.05931 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1911_05931</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2314659525</sourcerecordid><originalsourceid>FETCH-LOGICAL-a525-f48a85d56ddb60b49bac4aee36a1f172f78341ca19535218788c4bbf98c16d233</originalsourceid><addsrcrecordid>eNotz99LwzAQB_AgCI65P8AnAz635vKjTX0bRV1h4NiGryVt05mxNjFpRf976-bDcffwveM-CN0BibkUgjwq_22-YsgAYiIyBldoRhmDSHJKb9AihCMhhCYpFYLN0PbdBGP7Yrd5wlvtRu9sMP0BDx8aF506aLwzh16d8MbbWodgPW6nym3nxkF7fFnHS-dOplbDNIdbdN2qU9CL_z5H-5fnfb6K1m-vRb5cR0pQEbVcKikakTRNlZCKZ5WqudKaJQpaSGmbSsahVpAJJijIVMqaV1WbyRqSZhLN0f3l7BlcOm865X_KP3h5hk-Jh0vCefs56jCURzv6CRNKyoAnIpseYb81hVtT</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2314659525</pqid></control><display><type>article</type><title>VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Wu, Chyuan-Tyng ; Isikdogan, Leo F ; Rao, Sushma ; Nayak, Bhavin ; Gerasimow, Timo ; Sutic, Aleksandar ; Ain-kedem, Liron ; Gilad, Michael</creator><creatorcontrib>Wu, Chyuan-Tyng ; Isikdogan, Leo F ; Rao, Sushma ; Nayak, Bhavin ; Gerasimow, Timo ; Sutic, Aleksandar ; Ain-kedem, Liron ; Gilad, Michael</creatorcontrib><description>Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications. We propose a set of methods, which we collectively call VisionISP, to repurpose the ISP for machine consumption. VisionISP significantly reduces data transmission needs by reducing the bit-depth and resolution while preserving the relevant information. The blocks in VisionISP are simple, content-aware, and trainable. Experimental results show that VisionISP boosts the performance of a subsequent computer vision system trained to detect objects in an autonomous driving setting. The results demonstrate the potential and the practicality of VisionISP for computer vision applications.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1911.05931</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer vision ; Data transmission ; Image quality ; Microprocessors ; Object recognition ; Signal processing ; Vision systems</subject><ispartof>arXiv.org, 2019-11</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.1911.05931$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1109/ICIP.2019.8803607$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Wu, Chyuan-Tyng</creatorcontrib><creatorcontrib>Isikdogan, Leo F</creatorcontrib><creatorcontrib>Rao, Sushma</creatorcontrib><creatorcontrib>Nayak, Bhavin</creatorcontrib><creatorcontrib>Gerasimow, Timo</creatorcontrib><creatorcontrib>Sutic, Aleksandar</creatorcontrib><creatorcontrib>Ain-kedem, Liron</creatorcontrib><creatorcontrib>Gilad, Michael</creatorcontrib><title>VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications</title><title>arXiv.org</title><description>Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications. We propose a set of methods, which we collectively call VisionISP, to repurpose the ISP for machine consumption. VisionISP significantly reduces data transmission needs by reducing the bit-depth and resolution while preserving the relevant information. The blocks in VisionISP are simple, content-aware, and trainable. Experimental results show that VisionISP boosts the performance of a subsequent computer vision system trained to detect objects in an autonomous driving setting. The results demonstrate the potential and the practicality of VisionISP for computer vision applications.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer vision</subject><subject>Data transmission</subject><subject>Image quality</subject><subject>Microprocessors</subject><subject>Object recognition</subject><subject>Signal processing</subject><subject>Vision systems</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotz99LwzAQB_AgCI65P8AnAz635vKjTX0bRV1h4NiGryVt05mxNjFpRf976-bDcffwveM-CN0BibkUgjwq_22-YsgAYiIyBldoRhmDSHJKb9AihCMhhCYpFYLN0PbdBGP7Yrd5wlvtRu9sMP0BDx8aF506aLwzh16d8MbbWodgPW6nym3nxkF7fFnHS-dOplbDNIdbdN2qU9CL_z5H-5fnfb6K1m-vRb5cR0pQEbVcKikakTRNlZCKZ5WqudKaJQpaSGmbSsahVpAJJijIVMqaV1WbyRqSZhLN0f3l7BlcOm865X_KP3h5hk-Jh0vCefs56jCURzv6CRNKyoAnIpseYb81hVtT</recordid><startdate>20191114</startdate><enddate>20191114</enddate><creator>Wu, Chyuan-Tyng</creator><creator>Isikdogan, Leo F</creator><creator>Rao, Sushma</creator><creator>Nayak, Bhavin</creator><creator>Gerasimow, Timo</creator><creator>Sutic, Aleksandar</creator><creator>Ain-kedem, Liron</creator><creator>Gilad, Michael</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>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20191114</creationdate><title>VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications</title><author>Wu, Chyuan-Tyng ; Isikdogan, Leo F ; Rao, Sushma ; Nayak, Bhavin ; Gerasimow, Timo ; Sutic, Aleksandar ; Ain-kedem, Liron ; Gilad, Michael</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a525-f48a85d56ddb60b49bac4aee36a1f172f78341ca19535218788c4bbf98c16d233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer vision</topic><topic>Data transmission</topic><topic>Image quality</topic><topic>Microprocessors</topic><topic>Object recognition</topic><topic>Signal processing</topic><topic>Vision systems</topic><toplevel>online_resources</toplevel><creatorcontrib>Wu, Chyuan-Tyng</creatorcontrib><creatorcontrib>Isikdogan, Leo F</creatorcontrib><creatorcontrib>Rao, Sushma</creatorcontrib><creatorcontrib>Nayak, Bhavin</creatorcontrib><creatorcontrib>Gerasimow, Timo</creatorcontrib><creatorcontrib>Sutic, Aleksandar</creatorcontrib><creatorcontrib>Ain-kedem, Liron</creatorcontrib><creatorcontrib>Gilad, Michael</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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</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>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wu, Chyuan-Tyng</au><au>Isikdogan, Leo F</au><au>Rao, Sushma</au><au>Nayak, Bhavin</au><au>Gerasimow, Timo</au><au>Sutic, Aleksandar</au><au>Ain-kedem, Liron</au><au>Gilad, Michael</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications</atitle><jtitle>arXiv.org</jtitle><date>2019-11-14</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Traditional image signal processors (ISPs) are primarily designed and optimized to improve the image quality perceived by humans. However, optimal perceptual image quality does not always translate into optimal performance for computer vision applications. We propose a set of methods, which we collectively call VisionISP, to repurpose the ISP for machine consumption. VisionISP significantly reduces data transmission needs by reducing the bit-depth and resolution while preserving the relevant information. The blocks in VisionISP are simple, content-aware, and trainable. Experimental results show that VisionISP boosts the performance of a subsequent computer vision system trained to detect objects in an autonomous driving setting. The results demonstrate the potential and the practicality of VisionISP for computer vision applications.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1911.05931</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2019-11 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_1911_05931 |
| source | arXiv.org; Free E- Journals |
| subjects | Computer Science - Computer Vision and Pattern Recognition Computer vision Data transmission Image quality Microprocessors Object recognition Signal processing Vision systems |
| title | VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T18%3A12%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=VisionISP:%20Repurposing%20the%20Image%20Signal%20Processor%20for%20Computer%20Vision%20Applications&rft.jtitle=arXiv.org&rft.au=Wu,%20Chyuan-Tyng&rft.date=2019-11-14&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1911.05931&rft_dat=%3Cproquest_arxiv%3E2314659525%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2314659525&rft_id=info:pmid/&rfr_iscdi=true |