Stereo matching method and system based on binocular camera
The invention discloses a stereo matching method and system based on a binocular camera. The method comprises the following steps: collecting continuous multi-frame left and right eye images in a target area; performing parallax matching cost calculation on the left eye image and the right eye image...
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 | YANG CHAO GE FANGHAI LIU YONGCAI WANG PENG ZHU HAITAO |
| description | The invention discloses a stereo matching method and system based on a binocular camera. The method comprises the following steps: collecting continuous multi-frame left and right eye images in a target area; performing parallax matching cost calculation on the left eye image and the right eye image to obtain a plurality of parallax matching cost values; aggregation in multiple directions is carried out on each parallax matching cost value, and calculation is carried out through argmax (maximum independent variable point set) to obtain a parallax map corresponding to the maximum parallax matching cost value; and carrying out normalization processing on the disparity map, and carrying out sub-pixel disparity calculation to obtain a stereo matching result. According to the method, effective deployment in a deep learning chip is realized, time and effects are met, the method has better generalization ability, the effect in sub-pixel precision is better, and the algorithm precision and generalization ability of s |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114926521A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114926521A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114926521A3</originalsourceid><addsrcrecordid>eNrjZLAOLkktSs1XyE0sSc7IzEtXyE0tychPUUjMS1EoriwuSc1VSEosTk1RyM9TSMrMy08uzUksUkhOzE0tSuRhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoaGJpZGZqZGho7GxKgBAJxkLzo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Stereo matching method and system based on binocular camera</title><source>esp@cenet</source><creator>YANG CHAO ; GE FANGHAI ; LIU YONGCAI ; WANG PENG ; ZHU HAITAO</creator><creatorcontrib>YANG CHAO ; GE FANGHAI ; LIU YONGCAI ; WANG PENG ; ZHU HAITAO</creatorcontrib><description>The invention discloses a stereo matching method and system based on a binocular camera. The method comprises the following steps: collecting continuous multi-frame left and right eye images in a target area; performing parallax matching cost calculation on the left eye image and the right eye image to obtain a plurality of parallax matching cost values; aggregation in multiple directions is carried out on each parallax matching cost value, and calculation is carried out through argmax (maximum independent variable point set) to obtain a parallax map corresponding to the maximum parallax matching cost value; and carrying out normalization processing on the disparity map, and carrying out sub-pixel disparity calculation to obtain a stereo matching result. According to the method, effective deployment in a deep learning chip is realized, time and effects are met, the method has better generalization ability, the effect in sub-pixel precision is better, and the algorithm precision and generalization ability of s</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2022</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=20220819&DB=EPODOC&CC=CN&NR=114926521A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220819&DB=EPODOC&CC=CN&NR=114926521A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YANG CHAO</creatorcontrib><creatorcontrib>GE FANGHAI</creatorcontrib><creatorcontrib>LIU YONGCAI</creatorcontrib><creatorcontrib>WANG PENG</creatorcontrib><creatorcontrib>ZHU HAITAO</creatorcontrib><title>Stereo matching method and system based on binocular camera</title><description>The invention discloses a stereo matching method and system based on a binocular camera. The method comprises the following steps: collecting continuous multi-frame left and right eye images in a target area; performing parallax matching cost calculation on the left eye image and the right eye image to obtain a plurality of parallax matching cost values; aggregation in multiple directions is carried out on each parallax matching cost value, and calculation is carried out through argmax (maximum independent variable point set) to obtain a parallax map corresponding to the maximum parallax matching cost value; and carrying out normalization processing on the disparity map, and carrying out sub-pixel disparity calculation to obtain a stereo matching result. According to the method, effective deployment in a deep learning chip is realized, time and effects are met, the method has better generalization ability, the effect in sub-pixel precision is better, and the algorithm precision and generalization ability of s</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAOLkktSs1XyE0sSc7IzEtXyE0tychPUUjMS1EoriwuSc1VSEosTk1RyM9TSMrMy08uzUksUkhOzE0tSuRhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqXmpJfHOfoaGJpZGZqZGho7GxKgBAJxkLzo</recordid><startdate>20220819</startdate><enddate>20220819</enddate><creator>YANG CHAO</creator><creator>GE FANGHAI</creator><creator>LIU YONGCAI</creator><creator>WANG PENG</creator><creator>ZHU HAITAO</creator><scope>EVB</scope></search><sort><creationdate>20220819</creationdate><title>Stereo matching method and system based on binocular camera</title><author>YANG CHAO ; GE FANGHAI ; LIU YONGCAI ; WANG PENG ; ZHU HAITAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114926521A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>YANG CHAO</creatorcontrib><creatorcontrib>GE FANGHAI</creatorcontrib><creatorcontrib>LIU YONGCAI</creatorcontrib><creatorcontrib>WANG PENG</creatorcontrib><creatorcontrib>ZHU HAITAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YANG CHAO</au><au>GE FANGHAI</au><au>LIU YONGCAI</au><au>WANG PENG</au><au>ZHU HAITAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Stereo matching method and system based on binocular camera</title><date>2022-08-19</date><risdate>2022</risdate><abstract>The invention discloses a stereo matching method and system based on a binocular camera. The method comprises the following steps: collecting continuous multi-frame left and right eye images in a target area; performing parallax matching cost calculation on the left eye image and the right eye image to obtain a plurality of parallax matching cost values; aggregation in multiple directions is carried out on each parallax matching cost value, and calculation is carried out through argmax (maximum independent variable point set) to obtain a parallax map corresponding to the maximum parallax matching cost value; and carrying out normalization processing on the disparity map, and carrying out sub-pixel disparity calculation to obtain a stereo matching result. According to the method, effective deployment in a deep learning chip is realized, time and effects are met, the method has better generalization ability, the effect in sub-pixel precision is better, and the algorithm precision and generalization ability of s</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114926521A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Stereo matching method and system based on binocular camera |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T01%3A45%3A32IST&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=YANG%20CHAO&rft.date=2022-08-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114926521A%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 |