Invariant descriptors for 3-D object recognition and pose
Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descri...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence 1991-10, Vol.13 (10), p.971-991 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 991 |
---|---|
container_issue | 10 |
container_start_page | 971 |
container_title | IEEE transactions on pattern analysis and machine intelligence |
container_volume | 13 |
creator | FORSYTH, D MUNDY, J. L ZISSERMAN, A COELHO, C HELLER, A ROTHWELL, C |
description | Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descriptors in 3-D model-based vision is demonstrated. First, a model-based vision system that recognizes curved plane objects irrespective of their pose is demonstrated. Curves are not reduced to polyhedral approximations but are handled as objects in their own right. Models are generated directly from image data. Once objects have been recognized, their pose can be computed, Invariant descriptors for 3-D object with plane faces are described. All these ideas are demonstrated using images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail. (I.E.) |
doi_str_mv | 10.1109/34.99233 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pasca</sourceid><recordid>TN_cdi_proquest_miscellaneous_25350652</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>25350652</sourcerecordid><originalsourceid>FETCH-LOGICAL-p213t-4968faa8151df002b8215415dd2837974d3ca50c0ada97c1389f20c5f4a7f3c93</originalsourceid><addsrcrecordid>eNotjctKAzEUQIMoOFbBT8hC3E1NcpOZZCn1VSi40fVwm4ekTJMxmQr-vQW7OpvDOYTccrbknJkHkEtjBMAZabgB04ICc04axjvRai30JbmqdccYl4pBQ8w6_WCJmGbqfLUlTnMulYZcKLRPNG933s60eJu_UpxjThSTo1Ou_ppcBByrvzlxQT5fnj9Wb-3m_XW9ety0k-Awt9J0OiBqrrgLjImtFlxJrpwTGnrTSwcWFbMMHZrectAmCGZVkNgHsAYW5P6_O5X8ffB1HvaxWj-OmHw-1EEoUKxT4ijenUSsFsdQMNlYh6nEPZbf4TiVSnTwBzrtVEQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>25350652</pqid></control><display><type>article</type><title>Invariant descriptors for 3-D object recognition and pose</title><source>IEEE Xplore</source><creator>FORSYTH, D ; MUNDY, J. L ; ZISSERMAN, A ; COELHO, C ; HELLER, A ; ROTHWELL, C</creator><creatorcontrib>FORSYTH, D ; MUNDY, J. L ; ZISSERMAN, A ; COELHO, C ; HELLER, A ; ROTHWELL, C</creatorcontrib><description>Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descriptors in 3-D model-based vision is demonstrated. First, a model-based vision system that recognizes curved plane objects irrespective of their pose is demonstrated. Curves are not reduced to polyhedral approximations but are handled as objects in their own right. Models are generated directly from image data. Once objects have been recognized, their pose can be computed, Invariant descriptors for 3-D object with plane faces are described. All these ideas are demonstrated using images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail. (I.E.)</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>DOI: 10.1109/34.99233</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE Computer Society</publisher><subject>Applied sciences ; Artificial intelligence ; Computer science; control theory; systems ; Exact sciences and technology</subject><ispartof>IEEE transactions on pattern analysis and machine intelligence, 1991-10, Vol.13 (10), p.971-991</ispartof><rights>1992 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=5414526$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>FORSYTH, D</creatorcontrib><creatorcontrib>MUNDY, J. L</creatorcontrib><creatorcontrib>ZISSERMAN, A</creatorcontrib><creatorcontrib>COELHO, C</creatorcontrib><creatorcontrib>HELLER, A</creatorcontrib><creatorcontrib>ROTHWELL, C</creatorcontrib><title>Invariant descriptors for 3-D object recognition and pose</title><title>IEEE transactions on pattern analysis and machine intelligence</title><description>Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descriptors in 3-D model-based vision is demonstrated. First, a model-based vision system that recognizes curved plane objects irrespective of their pose is demonstrated. Curves are not reduced to polyhedral approximations but are handled as objects in their own right. Models are generated directly from image data. Once objects have been recognized, their pose can be computed, Invariant descriptors for 3-D object with plane faces are described. All these ideas are demonstrated using images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail. (I.E.)</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computer science; control theory; systems</subject><subject>Exact sciences and technology</subject><issn>0162-8828</issn><issn>1939-3539</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1991</creationdate><recordtype>article</recordtype><recordid>eNotjctKAzEUQIMoOFbBT8hC3E1NcpOZZCn1VSi40fVwm4ekTJMxmQr-vQW7OpvDOYTccrbknJkHkEtjBMAZabgB04ICc04axjvRai30JbmqdccYl4pBQ8w6_WCJmGbqfLUlTnMulYZcKLRPNG933s60eJu_UpxjThSTo1Ou_ppcBByrvzlxQT5fnj9Wb-3m_XW9ety0k-Awt9J0OiBqrrgLjImtFlxJrpwTGnrTSwcWFbMMHZrectAmCGZVkNgHsAYW5P6_O5X8ffB1HvaxWj-OmHw-1EEoUKxT4ijenUSsFsdQMNlYh6nEPZbf4TiVSnTwBzrtVEQ</recordid><startdate>19911001</startdate><enddate>19911001</enddate><creator>FORSYTH, D</creator><creator>MUNDY, J. L</creator><creator>ZISSERMAN, A</creator><creator>COELHO, C</creator><creator>HELLER, A</creator><creator>ROTHWELL, C</creator><general>IEEE Computer Society</general><scope>IQODW</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>19911001</creationdate><title>Invariant descriptors for 3-D object recognition and pose</title><author>FORSYTH, D ; MUNDY, J. L ; ZISSERMAN, A ; COELHO, C ; HELLER, A ; ROTHWELL, C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p213t-4968faa8151df002b8215415dd2837974d3ca50c0ada97c1389f20c5f4a7f3c93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1991</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computer science; control theory; systems</topic><topic>Exact sciences and technology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>FORSYTH, D</creatorcontrib><creatorcontrib>MUNDY, J. L</creatorcontrib><creatorcontrib>ZISSERMAN, A</creatorcontrib><creatorcontrib>COELHO, C</creatorcontrib><creatorcontrib>HELLER, A</creatorcontrib><creatorcontrib>ROTHWELL, C</creatorcontrib><collection>Pascal-Francis</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>FORSYTH, D</au><au>MUNDY, J. L</au><au>ZISSERMAN, A</au><au>COELHO, C</au><au>HELLER, A</au><au>ROTHWELL, C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Invariant descriptors for 3-D object recognition and pose</atitle><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle><date>1991-10-01</date><risdate>1991</risdate><volume>13</volume><issue>10</issue><spage>971</spage><epage>991</epage><pages>971-991</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><coden>ITPIDJ</coden><abstract>Invariant descriptors are shape descriptors that are unaffected by object pose, by perspective projection, or by the intrinsic parameters of the camera. These descriptors can be constructed using the methods of invariant theory, which are briefly surveyed. A range of applications of invariant descriptors in 3-D model-based vision is demonstrated. First, a model-based vision system that recognizes curved plane objects irrespective of their pose is demonstrated. Curves are not reduced to polyhedral approximations but are handled as objects in their own right. Models are generated directly from image data. Once objects have been recognized, their pose can be computed, Invariant descriptors for 3-D object with plane faces are described. All these ideas are demonstrated using images of real scenes. The stability of a range of invariant descriptors to measurement error is treated in detail. (I.E.)</abstract><cop>Los Alamitos, CA</cop><pub>IEEE Computer Society</pub><doi>10.1109/34.99233</doi><tpages>21</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0162-8828 |
ispartof | IEEE transactions on pattern analysis and machine intelligence, 1991-10, Vol.13 (10), p.971-991 |
issn | 0162-8828 1939-3539 |
language | eng |
recordid | cdi_proquest_miscellaneous_25350652 |
source | IEEE Xplore |
subjects | Applied sciences Artificial intelligence Computer science control theory systems Exact sciences and technology |
title | Invariant descriptors for 3-D object recognition and pose |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T07%3A01%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pasca&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Invariant%20descriptors%20for%203-D%20object%20recognition%20and%20pose&rft.jtitle=IEEE%20transactions%20on%20pattern%20analysis%20and%20machine%20intelligence&rft.au=FORSYTH,%20D&rft.date=1991-10-01&rft.volume=13&rft.issue=10&rft.spage=971&rft.epage=991&rft.pages=971-991&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/34.99233&rft_dat=%3Cproquest_pasca%3E25350652%3C/proquest_pasca%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=25350652&rft_id=info:pmid/&rfr_iscdi=true |