Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search
The goal of our work is object categorization in real-world scenes. That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity to a learned object category. For use in a real-world system, it is important that this includes the ability to recognize...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 153 |
|---|---|
| container_issue | |
| container_start_page | 145 |
| container_title | |
| container_volume | |
| creator | Leibe, Bastian Schiele, Bernt |
| description | The goal of our work is object categorization in real-world scenes. That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity to a learned object category. For use in a real-world system, it is important that this includes the ability to recognize objects at multiple scales.
In this paper, we present an approach to multi-scale object categorization using scale-invariant interest points and a scale-adaptive Mean-Shift search. The approach builds on the method from [12], which has been demonstrated to achieve excellent results for the single-scale case, and extends it to multiple scales. We present an experimental comparison of the influence of different interest point operators and quantitatively show the method’s robustness to large scale changes. |
| doi_str_mv | 10.1007/978-3-540-28649-3_18 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>pascalfrancis_sprin</sourceid><recordid>TN_cdi_pascalfrancis_primary_16177111</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>16177111</sourcerecordid><originalsourceid>FETCH-LOGICAL-c279t-69056e05c29d4be341323b53d5449fbf8f7b4a44c8e983f3fa087b1730ea5f7d3</originalsourceid><addsrcrecordid>eNpFkE1PAjEQhutXIkH-gYe9eKy2ne62PRKiSIJyQM7N7G4LRdwl2w2J_noLmDiXSZ73zWTyEHLP2SNnTD0ZpSnQXDIqdCENBcv1BRklDAmeGFySAS84pwDSXP1nwshcXJMBAyaoURJuySjGLUsjuNagB-R9WeHO0VlzwC5g02eLcuuqPptg79ZtF36wD22TrWJo1hlm5_a4xn0fDi57c9jQ5Sb4Pls67KrNHbnxuItu9LeHZPXy_DF5pfPFdDYZz2kllOlpYVheOJZXwtSydCA5CChzqHMpjS-99qqUKGWlndHgwSPTquQKmMPcqxqG5OF8d48xveQ7bKoQ7b4LX9h92yRDKc556olzL6aoWbvOlm37GS1n9ijXJlMWbHJlTyLtUS78AgvUZos</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search</title><source>Springer Books</source><creator>Leibe, Bastian ; Schiele, Bernt</creator><contributor>Bülthoff, Heinrich H. ; Rasmussen, Carl Edward ; Schölkopf, Bernhard ; Giese, Martin A.</contributor><creatorcontrib>Leibe, Bastian ; Schiele, Bernt ; Bülthoff, Heinrich H. ; Rasmussen, Carl Edward ; Schölkopf, Bernhard ; Giese, Martin A.</creatorcontrib><description>The goal of our work is object categorization in real-world scenes. That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity to a learned object category. For use in a real-world system, it is important that this includes the ability to recognize objects at multiple scales.
In this paper, we present an approach to multi-scale object categorization using scale-invariant interest points and a scale-adaptive Mean-Shift search. The approach builds on the method from [12], which has been demonstrated to achieve excellent results for the single-scale case, and extends it to multiple scales. We present an experimental comparison of the influence of different interest point operators and quantitatively show the method’s robustness to large scale changes.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 9783540229452</identifier><identifier>ISBN: 3540229450</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540286493</identifier><identifier>EISBN: 3540286497</identifier><identifier>DOI: 10.1007/978-3-540-28649-3_18</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>Applied sciences ; Artificial intelligence ; Computer science; control theory; systems ; Equal Error Rate ; Exact sciences and technology ; Interest Point ; Interest Point Detector ; Learning and adaptive systems ; Object Categorization ; Object Detection</subject><ispartof>Lecture notes in computer science, 2004, p.145-153</ispartof><rights>Springer-Verlag Berlin Heidelberg 2004</rights><rights>2004 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c279t-69056e05c29d4be341323b53d5449fbf8f7b4a44c8e983f3fa087b1730ea5f7d3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/978-3-540-28649-3_18$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/978-3-540-28649-3_18$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,779,780,784,789,790,793,4050,4051,27925,38255,41442,42511</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=16177111$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Bülthoff, Heinrich H.</contributor><contributor>Rasmussen, Carl Edward</contributor><contributor>Schölkopf, Bernhard</contributor><contributor>Giese, Martin A.</contributor><creatorcontrib>Leibe, Bastian</creatorcontrib><creatorcontrib>Schiele, Bernt</creatorcontrib><title>Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search</title><title>Lecture notes in computer science</title><description>The goal of our work is object categorization in real-world scenes. That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity to a learned object category. For use in a real-world system, it is important that this includes the ability to recognize objects at multiple scales.
In this paper, we present an approach to multi-scale object categorization using scale-invariant interest points and a scale-adaptive Mean-Shift search. The approach builds on the method from [12], which has been demonstrated to achieve excellent results for the single-scale case, and extends it to multiple scales. We present an experimental comparison of the influence of different interest point operators and quantitatively show the method’s robustness to large scale changes.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computer science; control theory; systems</subject><subject>Equal Error Rate</subject><subject>Exact sciences and technology</subject><subject>Interest Point</subject><subject>Interest Point Detector</subject><subject>Learning and adaptive systems</subject><subject>Object Categorization</subject><subject>Object Detection</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>9783540229452</isbn><isbn>3540229450</isbn><isbn>9783540286493</isbn><isbn>3540286497</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2004</creationdate><recordtype>conference_proceeding</recordtype><recordid>eNpFkE1PAjEQhutXIkH-gYe9eKy2ne62PRKiSIJyQM7N7G4LRdwl2w2J_noLmDiXSZ73zWTyEHLP2SNnTD0ZpSnQXDIqdCENBcv1BRklDAmeGFySAS84pwDSXP1nwshcXJMBAyaoURJuySjGLUsjuNagB-R9WeHO0VlzwC5g02eLcuuqPptg79ZtF36wD22TrWJo1hlm5_a4xn0fDi57c9jQ5Sb4Pls67KrNHbnxuItu9LeHZPXy_DF5pfPFdDYZz2kllOlpYVheOJZXwtSydCA5CChzqHMpjS-99qqUKGWlndHgwSPTquQKmMPcqxqG5OF8d48xveQ7bKoQ7b4LX9h92yRDKc556olzL6aoWbvOlm37GS1n9ijXJlMWbHJlTyLtUS78AgvUZos</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Leibe, Bastian</creator><creator>Schiele, Bernt</creator><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>IQODW</scope></search><sort><creationdate>2004</creationdate><title>Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search</title><author>Leibe, Bastian ; Schiele, Bernt</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c279t-69056e05c29d4be341323b53d5449fbf8f7b4a44c8e983f3fa087b1730ea5f7d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computer science; control theory; systems</topic><topic>Equal Error Rate</topic><topic>Exact sciences and technology</topic><topic>Interest Point</topic><topic>Interest Point Detector</topic><topic>Learning and adaptive systems</topic><topic>Object Categorization</topic><topic>Object Detection</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Leibe, Bastian</creatorcontrib><creatorcontrib>Schiele, Bernt</creatorcontrib><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Leibe, Bastian</au><au>Schiele, Bernt</au><au>Bülthoff, Heinrich H.</au><au>Rasmussen, Carl Edward</au><au>Schölkopf, Bernhard</au><au>Giese, Martin A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search</atitle><btitle>Lecture notes in computer science</btitle><date>2004</date><risdate>2004</risdate><spage>145</spage><epage>153</epage><pages>145-153</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>9783540229452</isbn><isbn>3540229450</isbn><eisbn>9783540286493</eisbn><eisbn>3540286497</eisbn><abstract>The goal of our work is object categorization in real-world scenes. That is, given a novel image we want to recognize and localize unseen-before objects based on their similarity to a learned object category. For use in a real-world system, it is important that this includes the ability to recognize objects at multiple scales.
In this paper, we present an approach to multi-scale object categorization using scale-invariant interest points and a scale-adaptive Mean-Shift search. The approach builds on the method from [12], which has been demonstrated to achieve excellent results for the single-scale case, and extends it to multiple scales. We present an experimental comparison of the influence of different interest point operators and quantitatively show the method’s robustness to large scale changes.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/978-3-540-28649-3_18</doi><tpages>9</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Lecture notes in computer science, 2004, p.145-153 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_16177111 |
| source | Springer Books |
| subjects | Applied sciences Artificial intelligence Computer science control theory systems Equal Error Rate Exact sciences and technology Interest Point Interest Point Detector Learning and adaptive systems Object Categorization Object Detection |
| title | Scale-Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T20%3A17%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-pascalfrancis_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Scale-Invariant%20Object%20Categorization%20Using%20a%20Scale-Adaptive%20Mean-Shift%20Search&rft.btitle=Lecture%20notes%20in%20computer%20science&rft.au=Leibe,%20Bastian&rft.date=2004&rft.spage=145&rft.epage=153&rft.pages=145-153&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=9783540229452&rft.isbn_list=3540229450&rft_id=info:doi/10.1007/978-3-540-28649-3_18&rft_dat=%3Cpascalfrancis_sprin%3E16177111%3C/pascalfrancis_sprin%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540286493&rft.eisbn_list=3540286497&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |