Recognizing 3D objects by generating random actions
This paper presents a formal model of an active recognition system that can be programmed by learning. At each time step the system decides between producing an action to generate new data and stopping to issue the name of the object observed. The actions can be directed either towards the external...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 40 |
|---|---|
| container_issue | |
| container_start_page | 35 |
| container_title | |
| container_volume | |
| creator | Herbin, S. |
| description | This paper presents a formal model of an active recognition system that can be programmed by learning. At each time step the system decides between producing an action to generate new data and stopping to issue the name of the object observed. The actions can be directed either towards the external environment or towards the internal perceptual system of the agent. The decision strategy is based on a quantitative evaluation of the system learning experience. The problem studied is the recognition of chess pieces using a moving camera and a multiscale feature detector. The recognition is difficult because the objects are complex-neither polyhedral nor smooth-and rather similar between classes, especially in certain view configurations. The system uses the information obtained by observing internal state transitions when the camera is moved or when the feature detector scale is changed. A simulation of the agent and the environment is used for experimental measures of the model performances. |
| doi_str_mv | 10.1109/CVPR.1996.517050 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>proquest_6IE</sourceid><recordid>TN_cdi_ieee_primary_517050</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>517050</ieee_id><sourcerecordid>26351116</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-896552eed81346236a42b91e3a2fe30ae6257bce848cc2dddaeb46052561c80c3</originalsourceid><addsrcrecordid>eNpNkD1PwzAURS0-JKqSHTFlYkt5z45f7BEFCkiVQBWwRo7zGrlqkxKnQ_n1gMrAdIdzdIYrxBXCDBHsbfnxupyhtTTTWICGEzFBIJWRRXsqElsYMGiokNrC2T92IZIY1wCAlizk-USoJfu-7cJX6NpU3ad9vWY_xrQ-pC13PLjxFwyua_pt6vwY-i5eivOV20RO_nYq3ucPb-VTtnh5fC7vFlmQoMbMWNJaMjcGVU5SkctlbZGVkytW4JikLmrPJjfey6ZpHNc5gZaa0Bvwaipujt3d0H_uOY7VNkTPm43ruN_HSpLSiEg_4vVRDMxc7YawdcOhOl6jvgEkFVPg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype><pqid>26351116</pqid></control><display><type>conference_proceeding</type><title>Recognizing 3D objects by generating random actions</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Herbin, S.</creator><creatorcontrib>Herbin, S.</creatorcontrib><description>This paper presents a formal model of an active recognition system that can be programmed by learning. At each time step the system decides between producing an action to generate new data and stopping to issue the name of the object observed. The actions can be directed either towards the external environment or towards the internal perceptual system of the agent. The decision strategy is based on a quantitative evaluation of the system learning experience. The problem studied is the recognition of chess pieces using a moving camera and a multiscale feature detector. The recognition is difficult because the objects are complex-neither polyhedral nor smooth-and rather similar between classes, especially in certain view configurations. The system uses the information obtained by observing internal state transitions when the camera is moved or when the feature detector scale is changed. A simulation of the agent and the environment is used for experimental measures of the model performances.</description><identifier>ISSN: 1063-6919</identifier><identifier>ISBN: 9780818672590</identifier><identifier>ISBN: 0818672595</identifier><identifier>EISSN: 1063-6919</identifier><identifier>DOI: 10.1109/CVPR.1996.517050</identifier><language>eng</language><publisher>IEEE</publisher><subject>Autonomous agents ; Cameras ; Control systems ; Delay ; Differential equations ; Mobile robots ; Process control ; Random variables ; Robot vision systems ; Stochastic systems</subject><ispartof>PROC IEEE COMPUT SOC CONF COMPUT VISION PATTERN RECOGNIT, 1996, p.35-40</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/517050$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/517050$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Herbin, S.</creatorcontrib><title>Recognizing 3D objects by generating random actions</title><title>PROC IEEE COMPUT SOC CONF COMPUT VISION PATTERN RECOGNIT</title><addtitle>CVPR</addtitle><description>This paper presents a formal model of an active recognition system that can be programmed by learning. At each time step the system decides between producing an action to generate new data and stopping to issue the name of the object observed. The actions can be directed either towards the external environment or towards the internal perceptual system of the agent. The decision strategy is based on a quantitative evaluation of the system learning experience. The problem studied is the recognition of chess pieces using a moving camera and a multiscale feature detector. The recognition is difficult because the objects are complex-neither polyhedral nor smooth-and rather similar between classes, especially in certain view configurations. The system uses the information obtained by observing internal state transitions when the camera is moved or when the feature detector scale is changed. A simulation of the agent and the environment is used for experimental measures of the model performances.</description><subject>Autonomous agents</subject><subject>Cameras</subject><subject>Control systems</subject><subject>Delay</subject><subject>Differential equations</subject><subject>Mobile robots</subject><subject>Process control</subject><subject>Random variables</subject><subject>Robot vision systems</subject><subject>Stochastic systems</subject><issn>1063-6919</issn><issn>1063-6919</issn><isbn>9780818672590</isbn><isbn>0818672595</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1996</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpNkD1PwzAURS0-JKqSHTFlYkt5z45f7BEFCkiVQBWwRo7zGrlqkxKnQ_n1gMrAdIdzdIYrxBXCDBHsbfnxupyhtTTTWICGEzFBIJWRRXsqElsYMGiokNrC2T92IZIY1wCAlizk-USoJfu-7cJX6NpU3ad9vWY_xrQ-pC13PLjxFwyua_pt6vwY-i5eivOV20RO_nYq3ucPb-VTtnh5fC7vFlmQoMbMWNJaMjcGVU5SkctlbZGVkytW4JikLmrPJjfey6ZpHNc5gZaa0Bvwaipujt3d0H_uOY7VNkTPm43ruN_HSpLSiEg_4vVRDMxc7YawdcOhOl6jvgEkFVPg</recordid><startdate>1996</startdate><enddate>1996</enddate><creator>Herbin, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>1996</creationdate><title>Recognizing 3D objects by generating random actions</title><author>Herbin, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-896552eed81346236a42b91e3a2fe30ae6257bce848cc2dddaeb46052561c80c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1996</creationdate><topic>Autonomous agents</topic><topic>Cameras</topic><topic>Control systems</topic><topic>Delay</topic><topic>Differential equations</topic><topic>Mobile robots</topic><topic>Process control</topic><topic>Random variables</topic><topic>Robot vision systems</topic><topic>Stochastic systems</topic><toplevel>online_resources</toplevel><creatorcontrib>Herbin, S.</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/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology 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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Herbin, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Recognizing 3D objects by generating random actions</atitle><btitle>PROC IEEE COMPUT SOC CONF COMPUT VISION PATTERN RECOGNIT</btitle><stitle>CVPR</stitle><date>1996</date><risdate>1996</risdate><spage>35</spage><epage>40</epage><pages>35-40</pages><issn>1063-6919</issn><eissn>1063-6919</eissn><isbn>9780818672590</isbn><isbn>0818672595</isbn><abstract>This paper presents a formal model of an active recognition system that can be programmed by learning. At each time step the system decides between producing an action to generate new data and stopping to issue the name of the object observed. The actions can be directed either towards the external environment or towards the internal perceptual system of the agent. The decision strategy is based on a quantitative evaluation of the system learning experience. The problem studied is the recognition of chess pieces using a moving camera and a multiscale feature detector. The recognition is difficult because the objects are complex-neither polyhedral nor smooth-and rather similar between classes, especially in certain view configurations. The system uses the information obtained by observing internal state transitions when the camera is moved or when the feature detector scale is changed. A simulation of the agent and the environment is used for experimental measures of the model performances.</abstract><pub>IEEE</pub><doi>10.1109/CVPR.1996.517050</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1063-6919 |
| ispartof | PROC IEEE COMPUT SOC CONF COMPUT VISION PATTERN RECOGNIT, 1996, p.35-40 |
| issn | 1063-6919 1063-6919 |
| language | eng |
| recordid | cdi_ieee_primary_517050 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Autonomous agents Cameras Control systems Delay Differential equations Mobile robots Process control Random variables Robot vision systems Stochastic systems |
| title | Recognizing 3D objects by generating random actions |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T15%3A07%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Recognizing%203D%20objects%20by%20generating%20random%20actions&rft.btitle=PROC%20IEEE%20COMPUT%20SOC%20CONF%20COMPUT%20VISION%20PATTERN%20RECOGNIT&rft.au=Herbin,%20S.&rft.date=1996&rft.spage=35&rft.epage=40&rft.pages=35-40&rft.issn=1063-6919&rft.eissn=1063-6919&rft.isbn=9780818672590&rft.isbn_list=0818672595&rft_id=info:doi/10.1109/CVPR.1996.517050&rft_dat=%3Cproquest_6IE%3E26351116%3C/proquest_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=26351116&rft_id=info:pmid/&rft_ieee_id=517050&rfr_iscdi=true |