Implementation method for enabling robot to perform visual location recognition in changing environment based on convolutional neural network and sequence matching
The invention discloses an implementation method for enabling a robot to perform visual location identification in a changing environment based on a convolutional neural network and sequence matching.According to the method, the characteristics of the non-overlapping areas between the pictures are e...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | LIU JINXIN XUE TAOLUE CHANG XIANGFENG LI WENWEN WANG YONG |
| description | The invention discloses an implementation method for enabling a robot to perform visual location identification in a changing environment based on a convolutional neural network and sequence matching.According to the method, the characteristics of the non-overlapping areas between the pictures are estimated on the convolution characteristic graphs of the pictures, then the characteristics are removed, and then the similarity distance between the pictures is calculated. Compared with an existing method based on a convolutional neural network, the method has real-time performance and higher anti-interference capacity for robot visual angle changes. Compared with an existing method based on a sequence matching technology, the matching sequence detection operator provided by the invention canmake full use of the information of the picture sequence, so that the robot can have higher location recognition accuracy and recall rate under extreme environmental changes.
本发明公开了一种基于卷积神经网络和序列匹配的在变化环境中让机器人进行视觉地点识别的实现方法，通过在图 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN110427953A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN110427953A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN110427953A3</originalsourceid><addsrcrecordid>eNqNjD0OwjAMRrswIOAO5gBIlB8hRlSBYGFiR27qthGJXZK0HIiLkhYOwPRZ8ntvnLwvtjFkiQMGLQyWQi0FlOKAGHOjuQInuQQIAg25-LDQad-iASPqKzlSUrEebs2gauSqF4k77YT7OuToqYAIKOFOTNvDscHUumHCS9wDkAvw9GyJFYHFoOrYmSajEo2n2W8nyfx0vGXnBTVyJ9-goujfs2uaLjer3X67Pqz_YT5p91gG</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Implementation method for enabling robot to perform visual location recognition in changing environment based on convolutional neural network and sequence matching</title><source>esp@cenet</source><creator>LIU JINXIN ; XUE TAOLUE ; CHANG XIANGFENG ; LI WENWEN ; WANG YONG</creator><creatorcontrib>LIU JINXIN ; XUE TAOLUE ; CHANG XIANGFENG ; LI WENWEN ; WANG YONG</creatorcontrib><description>The invention discloses an implementation method for enabling a robot to perform visual location identification in a changing environment based on a convolutional neural network and sequence matching.According to the method, the characteristics of the non-overlapping areas between the pictures are estimated on the convolution characteristic graphs of the pictures, then the characteristics are removed, and then the similarity distance between the pictures is calculated. Compared with an existing method based on a convolutional neural network, the method has real-time performance and higher anti-interference capacity for robot visual angle changes. Compared with an existing method based on a sequence matching technology, the matching sequence detection operator provided by the invention canmake full use of the information of the picture sequence, so that the robot can have higher location recognition accuracy and recall rate under extreme environmental changes.
本发明公开了一种基于卷积神经网络和序列匹配的在变化环境中让机器人进行视觉地点识别的实现方法，通过在图</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2019</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20191108&DB=EPODOC&CC=CN&NR=110427953A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20191108&DB=EPODOC&CC=CN&NR=110427953A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LIU JINXIN</creatorcontrib><creatorcontrib>XUE TAOLUE</creatorcontrib><creatorcontrib>CHANG XIANGFENG</creatorcontrib><creatorcontrib>LI WENWEN</creatorcontrib><creatorcontrib>WANG YONG</creatorcontrib><title>Implementation method for enabling robot to perform visual location recognition in changing environment based on convolutional neural network and sequence matching</title><description>The invention discloses an implementation method for enabling a robot to perform visual location identification in a changing environment based on a convolutional neural network and sequence matching.According to the method, the characteristics of the non-overlapping areas between the pictures are estimated on the convolution characteristic graphs of the pictures, then the characteristics are removed, and then the similarity distance between the pictures is calculated. Compared with an existing method based on a convolutional neural network, the method has real-time performance and higher anti-interference capacity for robot visual angle changes. Compared with an existing method based on a sequence matching technology, the matching sequence detection operator provided by the invention canmake full use of the information of the picture sequence, so that the robot can have higher location recognition accuracy and recall rate under extreme environmental changes.
本发明公开了一种基于卷积神经网络和序列匹配的在变化环境中让机器人进行视觉地点识别的实现方法，通过在图</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjD0OwjAMRrswIOAO5gBIlB8hRlSBYGFiR27qthGJXZK0HIiLkhYOwPRZ8ntvnLwvtjFkiQMGLQyWQi0FlOKAGHOjuQInuQQIAg25-LDQad-iASPqKzlSUrEebs2gauSqF4k77YT7OuToqYAIKOFOTNvDscHUumHCS9wDkAvw9GyJFYHFoOrYmSajEo2n2W8nyfx0vGXnBTVyJ9-goujfs2uaLjer3X67Pqz_YT5p91gG</recordid><startdate>20191108</startdate><enddate>20191108</enddate><creator>LIU JINXIN</creator><creator>XUE TAOLUE</creator><creator>CHANG XIANGFENG</creator><creator>LI WENWEN</creator><creator>WANG YONG</creator><scope>EVB</scope></search><sort><creationdate>20191108</creationdate><title>Implementation method for enabling robot to perform visual location recognition in changing environment based on convolutional neural network and sequence matching</title><author>LIU JINXIN ; XUE TAOLUE ; CHANG XIANGFENG ; LI WENWEN ; WANG YONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN110427953A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>LIU JINXIN</creatorcontrib><creatorcontrib>XUE TAOLUE</creatorcontrib><creatorcontrib>CHANG XIANGFENG</creatorcontrib><creatorcontrib>LI WENWEN</creatorcontrib><creatorcontrib>WANG YONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LIU JINXIN</au><au>XUE TAOLUE</au><au>CHANG XIANGFENG</au><au>LI WENWEN</au><au>WANG YONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Implementation method for enabling robot to perform visual location recognition in changing environment based on convolutional neural network and sequence matching</title><date>2019-11-08</date><risdate>2019</risdate><abstract>The invention discloses an implementation method for enabling a robot to perform visual location identification in a changing environment based on a convolutional neural network and sequence matching.According to the method, the characteristics of the non-overlapping areas between the pictures are estimated on the convolution characteristic graphs of the pictures, then the characteristics are removed, and then the similarity distance between the pictures is calculated. Compared with an existing method based on a convolutional neural network, the method has real-time performance and higher anti-interference capacity for robot visual angle changes. Compared with an existing method based on a sequence matching technology, the matching sequence detection operator provided by the invention canmake full use of the information of the picture sequence, so that the robot can have higher location recognition accuracy and recall rate under extreme environmental changes.
本发明公开了一种基于卷积神经网络和序列匹配的在变化环境中让机器人进行视觉地点识别的实现方法，通过在图</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN110427953A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Implementation method for enabling robot to perform visual location recognition in changing environment based on convolutional neural network and sequence matching |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T14%3A29%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=LIU%20JINXIN&rft.date=2019-11-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN110427953A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |