Travel anchor classification lane line detection method based on time sequence
The invention discloses a line anchor classification lane line detection method based on a time sequence. The method comprises the steps of 1, obtaining a training sample, 2, preprocessing a sample set picture, 3, processing before training, 4, carrying out network training, 5, processing features o...
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 | ZENG YUZHOU WANG JISHEN |
| description | The invention discloses a line anchor classification lane line detection method based on a time sequence. The method comprises the steps of 1, obtaining a training sample, 2, preprocessing a sample set picture, 3, processing before training, 4, carrying out network training, 5, processing features of a training image, and 6, carrying out training, recognition and classification. According to the method, a feature aggregation mode of continuous multi-frame input of mixed deep convolution LSTM processing is used, enhancement of feature extraction is focused on, the calculation amount is greatly reduced, the problem that rich semantic information cannot be extracted through general down-sampling is solved, a lane in a current frame can be predicted by using multiple previous frames, and the lane prediction efficiency is improved. Even if the lane is damaged or degraded due to shadow, stain and shielding, the lane line can be quickly detected on the premise of ensuring the precision.
本发明公开一种基于时序的行锚分类车道线检测方法，包括步骤一 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115311638A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115311638A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115311638A3</originalsourceid><addsrcrecordid>eNqNikEKwjAQRbNxIeodxgN0EYLiVorSVVfdl3HySwNpUjvR81vEA7j5j_f4W9N2C78RiZOMeSGJrBqGIFxCThQ5gWJYx6NAvm1CGbOnBys8rV7CBFI8X0iCvdkMHBWHH3fmeL91dVNhzj10ZkFC6evW2pOz9uwuV_fP5wMinTaQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Travel anchor classification lane line detection method based on time sequence</title><source>esp@cenet</source><creator>ZENG YUZHOU ; WANG JISHEN</creator><creatorcontrib>ZENG YUZHOU ; WANG JISHEN</creatorcontrib><description>The invention discloses a line anchor classification lane line detection method based on a time sequence. The method comprises the steps of 1, obtaining a training sample, 2, preprocessing a sample set picture, 3, processing before training, 4, carrying out network training, 5, processing features of a training image, and 6, carrying out training, recognition and classification. According to the method, a feature aggregation mode of continuous multi-frame input of mixed deep convolution LSTM processing is used, enhancement of feature extraction is focused on, the calculation amount is greatly reduced, the problem that rich semantic information cannot be extracted through general down-sampling is solved, a lane in a current frame can be predicted by using multiple previous frames, and the lane prediction efficiency is improved. Even if the lane is damaged or degraded due to shadow, stain and shielding, the lane line can be quickly detected on the premise of ensuring the precision.
本发明公开一种基于时序的行锚分类车道线检测方法，包括步骤一</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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=20221108&DB=EPODOC&CC=CN&NR=115311638A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221108&DB=EPODOC&CC=CN&NR=115311638A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZENG YUZHOU</creatorcontrib><creatorcontrib>WANG JISHEN</creatorcontrib><title>Travel anchor classification lane line detection method based on time sequence</title><description>The invention discloses a line anchor classification lane line detection method based on a time sequence. The method comprises the steps of 1, obtaining a training sample, 2, preprocessing a sample set picture, 3, processing before training, 4, carrying out network training, 5, processing features of a training image, and 6, carrying out training, recognition and classification. According to the method, a feature aggregation mode of continuous multi-frame input of mixed deep convolution LSTM processing is used, enhancement of feature extraction is focused on, the calculation amount is greatly reduced, the problem that rich semantic information cannot be extracted through general down-sampling is solved, a lane in a current frame can be predicted by using multiple previous frames, and the lane prediction efficiency is improved. Even if the lane is damaged or degraded due to shadow, stain and shielding, the lane line can be quickly detected on the premise of ensuring the precision.
本发明公开一种基于时序的行锚分类车道线检测方法，包括步骤一</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNikEKwjAQRbNxIeodxgN0EYLiVorSVVfdl3HySwNpUjvR81vEA7j5j_f4W9N2C78RiZOMeSGJrBqGIFxCThQ5gWJYx6NAvm1CGbOnBys8rV7CBFI8X0iCvdkMHBWHH3fmeL91dVNhzj10ZkFC6evW2pOz9uwuV_fP5wMinTaQ</recordid><startdate>20221108</startdate><enddate>20221108</enddate><creator>ZENG YUZHOU</creator><creator>WANG JISHEN</creator><scope>EVB</scope></search><sort><creationdate>20221108</creationdate><title>Travel anchor classification lane line detection method based on time sequence</title><author>ZENG YUZHOU ; WANG JISHEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115311638A3</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZENG YUZHOU</creatorcontrib><creatorcontrib>WANG JISHEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZENG YUZHOU</au><au>WANG JISHEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Travel anchor classification lane line detection method based on time sequence</title><date>2022-11-08</date><risdate>2022</risdate><abstract>The invention discloses a line anchor classification lane line detection method based on a time sequence. The method comprises the steps of 1, obtaining a training sample, 2, preprocessing a sample set picture, 3, processing before training, 4, carrying out network training, 5, processing features of a training image, and 6, carrying out training, recognition and classification. According to the method, a feature aggregation mode of continuous multi-frame input of mixed deep convolution LSTM processing is used, enhancement of feature extraction is focused on, the calculation amount is greatly reduced, the problem that rich semantic information cannot be extracted through general down-sampling is solved, a lane in a current frame can be predicted by using multiple previous frames, and the lane prediction efficiency is improved. Even if the lane is damaged or degraded due to shadow, stain and shielding, the lane line can be quickly detected on the premise of ensuring the precision.
本发明公开一种基于时序的行锚分类车道线检测方法，包括步骤一</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115311638A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Travel anchor classification lane line detection method based on time sequence |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T07%3A03%3A42IST&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=ZENG%20YUZHOU&rft.date=2022-11-08&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115311638A%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 |