Deep learning integrated tracking algorithm based on target movement trajectory prediction
The invention discloses a deep learning integrated tracking algorithm based on target movement trajectory prediction. The algorithm comprises the steps: firstly reading a video frame sequence, and obtaining an initial frame image; then initializing a target tracking position, and calculating semanti...
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 | AN ZHIYONG HAO FANGJING XIE QINGSONG SHEN JINGWEI LI BO |
| description | The invention discloses a deep learning integrated tracking algorithm based on target movement trajectory prediction. The algorithm comprises the steps: firstly reading a video frame sequence, and obtaining an initial frame image; then initializing a target tracking position, and calculating semantic information pre_label of a tracking target by using a detection algorithm; calculating a color feature average template S; judging whether a detection algorithm can be started or not; predicting the moving direction of the target object according to the t-5 frame and the t-15 frame, and screening k potential target objects of which the semantics is pre_label; and finally, respectively extracting three color features of the K target objects and performing similarity calculation on the three color features and the template S, selecting a maximum similarity value SDr from K similarity results, and if SDr is greater than tp, performing deviation correction on a tracking result by using a target object tracking frame |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113744313A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113744313A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113744313A3</originalsourceid><addsrcrecordid>eNqNijEKwkAQRdNYiHqH8QAWYQPWEhUrKyubMG6-68ZkdpkMgrfXgAewevDemxfXPZCpB6tECRTFEJQNLZmyf06O-5A02mOgG4_fkISMNcBoSC8MEJveDt6Svikr2ugtJlkWszv3I1Y_Lor18XCpTxvk1GDM7CGwpj6XpdtWlSvdzv3zfAB8iTvM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Deep learning integrated tracking algorithm based on target movement trajectory prediction</title><source>esp@cenet</source><creator>AN ZHIYONG ; HAO FANGJING ; XIE QINGSONG ; SHEN JINGWEI ; LI BO</creator><creatorcontrib>AN ZHIYONG ; HAO FANGJING ; XIE QINGSONG ; SHEN JINGWEI ; LI BO</creatorcontrib><description>The invention discloses a deep learning integrated tracking algorithm based on target movement trajectory prediction. The algorithm comprises the steps: firstly reading a video frame sequence, and obtaining an initial frame image; then initializing a target tracking position, and calculating semantic information pre_label of a tracking target by using a detection algorithm; calculating a color feature average template S; judging whether a detection algorithm can be started or not; predicting the moving direction of the target object according to the t-5 frame and the t-15 frame, and screening k potential target objects of which the semantics is pre_label; and finally, respectively extracting three color features of the K target objects and performing similarity calculation on the three color features and the template S, selecting a maximum similarity value SDr from K similarity results, and if SDr is greater than tp, performing deviation correction on a tracking result by using a target object tracking frame</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>2021</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=20211203&DB=EPODOC&CC=CN&NR=113744313A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25563,76318</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211203&DB=EPODOC&CC=CN&NR=113744313A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>AN ZHIYONG</creatorcontrib><creatorcontrib>HAO FANGJING</creatorcontrib><creatorcontrib>XIE QINGSONG</creatorcontrib><creatorcontrib>SHEN JINGWEI</creatorcontrib><creatorcontrib>LI BO</creatorcontrib><title>Deep learning integrated tracking algorithm based on target movement trajectory prediction</title><description>The invention discloses a deep learning integrated tracking algorithm based on target movement trajectory prediction. The algorithm comprises the steps: firstly reading a video frame sequence, and obtaining an initial frame image; then initializing a target tracking position, and calculating semantic information pre_label of a tracking target by using a detection algorithm; calculating a color feature average template S; judging whether a detection algorithm can be started or not; predicting the moving direction of the target object according to the t-5 frame and the t-15 frame, and screening k potential target objects of which the semantics is pre_label; and finally, respectively extracting three color features of the K target objects and performing similarity calculation on the three color features and the template S, selecting a maximum similarity value SDr from K similarity results, and if SDr is greater than tp, performing deviation correction on a tracking result by using a target object tracking frame</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNijEKwkAQRdNYiHqH8QAWYQPWEhUrKyubMG6-68ZkdpkMgrfXgAewevDemxfXPZCpB6tECRTFEJQNLZmyf06O-5A02mOgG4_fkISMNcBoSC8MEJveDt6Svikr2ugtJlkWszv3I1Y_Lor18XCpTxvk1GDM7CGwpj6XpdtWlSvdzv3zfAB8iTvM</recordid><startdate>20211203</startdate><enddate>20211203</enddate><creator>AN ZHIYONG</creator><creator>HAO FANGJING</creator><creator>XIE QINGSONG</creator><creator>SHEN JINGWEI</creator><creator>LI BO</creator><scope>EVB</scope></search><sort><creationdate>20211203</creationdate><title>Deep learning integrated tracking algorithm based on target movement trajectory prediction</title><author>AN ZHIYONG ; HAO FANGJING ; XIE QINGSONG ; SHEN JINGWEI ; LI BO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113744313A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</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>AN ZHIYONG</creatorcontrib><creatorcontrib>HAO FANGJING</creatorcontrib><creatorcontrib>XIE QINGSONG</creatorcontrib><creatorcontrib>SHEN JINGWEI</creatorcontrib><creatorcontrib>LI BO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>AN ZHIYONG</au><au>HAO FANGJING</au><au>XIE QINGSONG</au><au>SHEN JINGWEI</au><au>LI BO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Deep learning integrated tracking algorithm based on target movement trajectory prediction</title><date>2021-12-03</date><risdate>2021</risdate><abstract>The invention discloses a deep learning integrated tracking algorithm based on target movement trajectory prediction. The algorithm comprises the steps: firstly reading a video frame sequence, and obtaining an initial frame image; then initializing a target tracking position, and calculating semantic information pre_label of a tracking target by using a detection algorithm; calculating a color feature average template S; judging whether a detection algorithm can be started or not; predicting the moving direction of the target object according to the t-5 frame and the t-15 frame, and screening k potential target objects of which the semantics is pre_label; and finally, respectively extracting three color features of the K target objects and performing similarity calculation on the three color features and the template S, selecting a maximum similarity value SDr from K similarity results, and if SDr is greater than tp, performing deviation correction on a tracking result by using a target object tracking frame</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN113744313A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Deep learning integrated tracking algorithm based on target movement trajectory prediction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T21%3A03%3A38IST&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=AN%20ZHIYONG&rft.date=2021-12-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113744313A%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 |