Distinguishing Refracted Features using Light Field Cameras with Application to Structure from Motion

Robots must reliably interact with refractive objects in many applications; however, refractive objects can cause many robotic vision algorithms to become unreliable or even fail, particularly feature-based matching applications, such as structure-from-motion. We propose a method to distinguish betw...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2018-05
Hauptverfasser: Tsai, Dorian, Dansereau, Donald G, Peynot, Thierry, Corke, Peter
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 Tsai, Dorian
Dansereau, Donald G
Peynot, Thierry
Corke, Peter
description Robots must reliably interact with refractive objects in many applications; however, refractive objects can cause many robotic vision algorithms to become unreliable or even fail, particularly feature-based matching applications, such as structure-from-motion. We propose a method to distinguish between refracted and Lambertian image features using a light field camera. Specifically, we propose to use textural cross-correlation to characterise apparent feature motion in a single light field, and compare this motion to its Lambertian equivalent based on 4D light field geometry. Our refracted feature distinguisher has a 34.3% higher rate of detection compared to state-of-the-art for light fields captured with large baselines relative to the refractive object. Our method also applies to light field cameras with much smaller baselines than previously considered, yielding up to 2 times better detection for 2D-refractive objects, such as a sphere, and up to 8 times better for 1D-refractive objects, such as a cylinder. For structure from motion, we demonstrate that rejecting refracted features using our distinguisher yields up to 42.4% lower reprojection error, and lower failure rate when the robot is approaching refractive objects. Our method lead to more robust robot vision in the presence of refractive objects.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2073556294</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2073556294</sourcerecordid><originalsourceid>FETCH-proquest_journals_20735562943</originalsourceid><addsrcrecordid>eNqNy0EKwjAQheEgCIp6hwHXhZiYqktRiwvdqHsJddpG2qZmJnh9LXgAV__ie28gxkrrRbJeKjUSM6KnlFKlK2WMHgvcO2LXltFR9Q1csAg2Z3xAhpZjQIJIPZxcWTFkDusH7GyDwRK8HVew7bra5Zadb4E9XDnEvD9CEXwDZ9_DVAwLWxPOfp2IeXa47Y5JF_wrIvH96WNov3RXcqWNSdVmqf9bfQCqxkck</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2073556294</pqid></control><display><type>article</type><title>Distinguishing Refracted Features using Light Field Cameras with Application to Structure from Motion</title><source>Free E- Journals</source><creator>Tsai, Dorian ; Dansereau, Donald G ; Peynot, Thierry ; Corke, Peter</creator><creatorcontrib>Tsai, Dorian ; Dansereau, Donald G ; Peynot, Thierry ; Corke, Peter</creatorcontrib><description>Robots must reliably interact with refractive objects in many applications; however, refractive objects can cause many robotic vision algorithms to become unreliable or even fail, particularly feature-based matching applications, such as structure-from-motion. We propose a method to distinguish between refracted and Lambertian image features using a light field camera. Specifically, we propose to use textural cross-correlation to characterise apparent feature motion in a single light field, and compare this motion to its Lambertian equivalent based on 4D light field geometry. Our refracted feature distinguisher has a 34.3% higher rate of detection compared to state-of-the-art for light fields captured with large baselines relative to the refractive object. Our method also applies to light field cameras with much smaller baselines than previously considered, yielding up to 2 times better detection for 2D-refractive objects, such as a sphere, and up to 8 times better for 1D-refractive objects, such as a cylinder. For structure from motion, we demonstrate that rejecting refracted features using our distinguisher yields up to 42.4% lower reprojection error, and lower failure rate when the robot is approaching refractive objects. Our method lead to more robust robot vision in the presence of refractive objects.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Cameras ; Chlorophyll ; Computer vision ; Cylinders ; Failure rates ; Field cameras ; Light ; Object recognition ; Robot dynamics</subject><ispartof>arXiv.org, 2018-05</ispartof><rights>2018. 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><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>776,780</link.rule.ids></links><search><creatorcontrib>Tsai, Dorian</creatorcontrib><creatorcontrib>Dansereau, Donald G</creatorcontrib><creatorcontrib>Peynot, Thierry</creatorcontrib><creatorcontrib>Corke, Peter</creatorcontrib><title>Distinguishing Refracted Features using Light Field Cameras with Application to Structure from Motion</title><title>arXiv.org</title><description>Robots must reliably interact with refractive objects in many applications; however, refractive objects can cause many robotic vision algorithms to become unreliable or even fail, particularly feature-based matching applications, such as structure-from-motion. We propose a method to distinguish between refracted and Lambertian image features using a light field camera. Specifically, we propose to use textural cross-correlation to characterise apparent feature motion in a single light field, and compare this motion to its Lambertian equivalent based on 4D light field geometry. Our refracted feature distinguisher has a 34.3% higher rate of detection compared to state-of-the-art for light fields captured with large baselines relative to the refractive object. Our method also applies to light field cameras with much smaller baselines than previously considered, yielding up to 2 times better detection for 2D-refractive objects, such as a sphere, and up to 8 times better for 1D-refractive objects, such as a cylinder. For structure from motion, we demonstrate that rejecting refracted features using our distinguisher yields up to 42.4% lower reprojection error, and lower failure rate when the robot is approaching refractive objects. Our method lead to more robust robot vision in the presence of refractive objects.</description><subject>Algorithms</subject><subject>Cameras</subject><subject>Chlorophyll</subject><subject>Computer vision</subject><subject>Cylinders</subject><subject>Failure rates</subject><subject>Field cameras</subject><subject>Light</subject><subject>Object recognition</subject><subject>Robot dynamics</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNy0EKwjAQheEgCIp6hwHXhZiYqktRiwvdqHsJddpG2qZmJnh9LXgAV__ie28gxkrrRbJeKjUSM6KnlFKlK2WMHgvcO2LXltFR9Q1csAg2Z3xAhpZjQIJIPZxcWTFkDusH7GyDwRK8HVew7bra5Zadb4E9XDnEvD9CEXwDZ9_DVAwLWxPOfp2IeXa47Y5JF_wrIvH96WNov3RXcqWNSdVmqf9bfQCqxkck</recordid><startdate>20180531</startdate><enddate>20180531</enddate><creator>Tsai, Dorian</creator><creator>Dansereau, Donald G</creator><creator>Peynot, Thierry</creator><creator>Corke, Peter</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></search><sort><creationdate>20180531</creationdate><title>Distinguishing Refracted Features using Light Field Cameras with Application to Structure from Motion</title><author>Tsai, Dorian ; Dansereau, Donald G ; Peynot, Thierry ; Corke, Peter</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20735562943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Algorithms</topic><topic>Cameras</topic><topic>Chlorophyll</topic><topic>Computer vision</topic><topic>Cylinders</topic><topic>Failure rates</topic><topic>Field cameras</topic><topic>Light</topic><topic>Object recognition</topic><topic>Robot dynamics</topic><toplevel>online_resources</toplevel><creatorcontrib>Tsai, Dorian</creatorcontrib><creatorcontrib>Dansereau, Donald G</creatorcontrib><creatorcontrib>Peynot, Thierry</creatorcontrib><creatorcontrib>Corke, Peter</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; 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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tsai, Dorian</au><au>Dansereau, Donald G</au><au>Peynot, Thierry</au><au>Corke, Peter</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Distinguishing Refracted Features using Light Field Cameras with Application to Structure from Motion</atitle><jtitle>arXiv.org</jtitle><date>2018-05-31</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Robots must reliably interact with refractive objects in many applications; however, refractive objects can cause many robotic vision algorithms to become unreliable or even fail, particularly feature-based matching applications, such as structure-from-motion. We propose a method to distinguish between refracted and Lambertian image features using a light field camera. Specifically, we propose to use textural cross-correlation to characterise apparent feature motion in a single light field, and compare this motion to its Lambertian equivalent based on 4D light field geometry. Our refracted feature distinguisher has a 34.3% higher rate of detection compared to state-of-the-art for light fields captured with large baselines relative to the refractive object. Our method also applies to light field cameras with much smaller baselines than previously considered, yielding up to 2 times better detection for 2D-refractive objects, such as a sphere, and up to 8 times better for 1D-refractive objects, such as a cylinder. For structure from motion, we demonstrate that rejecting refracted features using our distinguisher yields up to 42.4% lower reprojection error, and lower failure rate when the robot is approaching refractive objects. Our method lead to more robust robot vision in the presence of refractive objects.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2018-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2073556294
source Free E- Journals
subjects Algorithms
Cameras
Chlorophyll
Computer vision
Cylinders
Failure rates
Field cameras
Light
Object recognition
Robot dynamics
title Distinguishing Refracted Features using Light Field Cameras with Application to Structure from Motion
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T16%3A08%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Distinguishing%20Refracted%20Features%20using%20Light%20Field%20Cameras%20with%20Application%20to%20Structure%20from%20Motion&rft.jtitle=arXiv.org&rft.au=Tsai,%20Dorian&rft.date=2018-05-31&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2073556294%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2073556294&rft_id=info:pmid/&rfr_iscdi=true