{"id":77658,"date":"2020-04-12T19:42:20","date_gmt":"2020-04-12T17:42:20","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/fairmot-sistema-dlya-bystrogo-otslezhivaniya-neskolkih-obektov-na-video"},"modified":"2020-04-12T19:42:20","modified_gmt":"2020-04-12T17:42:20","slug":"fairmot-sistema-dlya-bystrogo-otslezhivaniya-neskolkih-obektov-na-video","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sq\/blog\/news\/fairmot-sistema-dlya-bystrogo-otslezhivaniya-neskolkih-obektov-na-video","title":{"rendered":"FairMOT, nj\u00eb sistem p\u00ebr ndjekjen e shpejt\u00eb t\u00eb disa objekteve n\u00eb video","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Hulumtuesit nga kompania Microsoft dhe Universiteti Qendror i Kin\u00ebs kan\u00eb zhvilluar<\/a><\/noindex> nj\u00eb metod\u00eb e re e lart\u00eb e performanc\u00ebs p\u00ebr ndjekjen e disa objekteve n\u00eb video duke p\u00ebrdorur teknologjit\u00eb e m\u00ebsimit t\u00eb makineris\u00eb \u2014 FairMOT (Ndjekja e Drejt\u00eb e Shum\u00eb Objekteve). Kodi me implementimin e metod\u00ebs mbi Pytorch dhe modelet e trajnuara jan\u00eb publikuar<\/a><\/noindex> n\u00eb GitHub. <\/p>\n

Shumica e metodave ekzistuese p\u00ebr ndjekjen e objekteve p\u00ebrdorin dy faza, secila prej t\u00eb cilave implementohet nga nj\u00eb rrjet neural i ve\u00e7ant\u00eb. N\u00eb faz\u00ebn e par\u00eb, zbatohet modeli p\u00ebr identifikimin e vendeve t\u00eb objekteve t\u00eb interesit, nd\u00ebrsa n\u00eb faz\u00ebn e dyt\u00eb p\u00ebrdoret modeli i k\u00ebrkimit t\u00eb asocimeve, i cili aplikohet p\u00ebr ri-identifikimin e objekteve dhe lidhjen e tyre me ankorat. <\/p>\n

N\u00eb FairMOT aplikohet nj\u00eb implementim me nj\u00eb faz\u00eb i bazuar n\u00eb rrjetin neural konvolucional t\u00eb deformuesh\u00ebm (DCNv2<\/a><\/noindex>, Rrjeti Konvolucional Deformues), i cili lejon t\u00eb arrihet nj\u00eb rritje t\u00eb konsiderueshme t\u00eb shpejt\u00ebsis\u00eb s\u00eb ndjekjes s\u00eb objekteve. FairMOT punon pa lidhje ankorash, duke p\u00ebrdorur mekanizmin e riidentifikimit p\u00ebr t\u00eb p\u00ebrcaktuar devijimet e qendrave t\u00eb objekteve n\u00eb nj\u00eb hart\u00eb t\u00eb objekteve me sakt\u00ebsi t\u00eb lart\u00eb. N\u00eb paralel, ekzekutohet nj\u00eb procesor, i cili vler\u00ebson ve\u00e7orit\u00eb individuale t\u00eb objekteve, t\u00eb cilat mund t\u00eb p\u00ebrdoren p\u00ebr t\u00eb parashikuar identitetin e tyre, nd\u00ebrsa moduli kryesor p\u00ebrcjell k\u00ebto ve\u00e7ori p\u00ebr manipulimin e objekteve me p\u00ebrmasa t\u00eb ndryshme.
\n

\"FairMOT,<\/center><\/p>\n

P\u00ebr trajnimimin e modelit n\u00eb FairMOT \u00ebsht\u00eb p\u00ebrdorur nj\u00eb kombinim i gjasht\u00eb grupeve t\u00eb t\u00eb dh\u00ebnave publike p\u00ebr identifikimin dhe k\u00ebrkimin e njer\u00ebzve (ETH, CityPerson, CalTech, MOT17, CUHK-SYSU). Modeli \u00ebsht\u00eb testuar duke p\u00ebrdorur grupe verifikimi t\u00eb videove 2DMOT15<\/a><\/noindex>, MOT16<\/a><\/noindex>, MOT17<\/a><\/noindex> dhe MOT20<\/a><\/noindex>, t\u00eb ofruara nga projekti MOT Challenge<\/a><\/noindex> dhe q\u00eb mbulojn\u00eb situata t\u00eb ndryshme, l\u00ebvizjen ose rotacionin e kamer\u00ebs, dhe k\u00ebndet e ndryshme t\u00eb pamjes. Testimi i kryer tregoi se
\nFairMOT p\u00ebrpara<\/a><\/noindex> modelet konkurente m\u00eb t\u00eb shpejta TrackRCNN<\/a><\/noindex> dhe JDE<\/a><\/noindex> n\u00eb testimin e videove me 30 kadra n\u00eb sekond\u00eb, duke demonstruar performanc\u00ebn e mjaftueshme p\u00ebr analizimin e flukseve normale t\u00eb videove. <\/p>\n

<\/a><\/noindex><\/p>\n

Burimi: opennet.ru<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u0418\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0438\u0437 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438 Microsoft \u0438 \u0423\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u0426\u0435\u043d\u0442\u0440\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u041a\u0438\u0442\u0430\u044f \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0430\u043b\u0438 \u043d\u043e\u0432\u044b\u0439 \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0442\u0441\u043b\u0435\u0436\u0438\u0432\u0430\u043d\u0438\u044f \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432 \u043d\u0430 \u0432\u0438\u0434\u0435\u043e \u0441 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435\u043c \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f — FairMOT (Fair Multi-Object Tracking). \u041a\u043e\u0434 \u0441 \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0435\u0439 \u043c\u0435\u0442\u043e\u0434\u0430 \u043d\u0430 \u0431\u0430\u0437\u0435 Pytorch \u0438 \u043d\u0430\u0442\u0440\u0435\u043d\u0438\u0440\u043e\u0432\u0430\u043d\u043d\u044b\u0435 \u043c\u043e\u0434\u0435\u043b\u0438 \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d\u044b \u043d\u0430 GitHub. \u0411\u043e\u043b\u044c\u0448\u0438\u043d\u0441\u0442\u0432\u043e \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0449\u0438\u0445 \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043e\u0442\u0441\u043b\u0435\u0436\u0438\u0432\u0430\u043d\u0438\u044f \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044e\u0442 \u0434\u0432\u0430 \u044d\u0442\u0430\u043f\u0430, \u043a\u0430\u0436\u0434\u044b\u0439 \u0438\u0437 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 \u0440\u0435\u0430\u043b\u0438\u0437\u0443\u0435\u0442\u0441\u044f \u043e\u0442\u0434\u0435\u043b\u044c\u043d\u043e\u0439 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0439 \u0441\u0435\u0442\u044c\u044e. […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":77659,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-77658","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47FairMOT, sistemi p\u00ebr ndjekjen e shpejt\u00eb t\u00eb disa objekteve n\u00eb video | ProHoster","description":"Shkenc\u00ebtar\u00ebt nga kompania Microsoft dhe Universiteti Qendror i Kin\u00ebs kan\u00eb zhvilluar nj\u00eb metod\u00eb t\u00eb re me performanc\u00eb t\u00eb lart\u00eb p\u00ebr gjurmimin.","canonical_url":"https:\/\/prohoster.info\/sq\/blog\/news\/fairmot-sistema-dlya-bystrogo-otslezhivaniya-neskolkih-obektov-na-video","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"sq_AL","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47FairMOT, \u0441\u0438\u0441\u0442\u0435\u043c\u0430 \u0434\u043b\u044f \u0431\u044b\u0441\u0442\u0440\u043e\u0433\u043e \u043e\u0442\u0441\u043b\u0435\u0436\u0438\u0432\u0430\u043d\u0438\u044f \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432 \u043d\u0430 \u0432\u0438\u0434\u0435\u043e | ProHoster","og:description":"\u0418\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0438\u0437 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438 Microsoft \u0438 \u0423\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u0426\u0435\u043d\u0442\u0440\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u041a\u0438\u0442\u0430\u044f \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0430\u043b\u0438 \u043d\u043e\u0432\u044b\u0439 \u0432\u044b\u0441\u043e\u043a\u043e\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u043e\u0442\u0441\u043b\u0435\u0436\u0438\u0432\u0430\u043d\u0438\u044f.","og:url":"https:\/\/prohoster.info\/sq\/blog\/news\/fairmot-sistema-dlya-bystrogo-otslezhivaniya-neskolkih-obektov-na-video","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2020-04-12T17:42:20+00:00","article:modified_time":"2020-04-12T17:42:20+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"77658","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":null,"breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-02-28 17:14:22","updated":"2022-09-27 15:09:24","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts\/77658","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/comments?post=77658"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts\/77658\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media\/77659"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media?parent=77658"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/categories?post=77658"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/tags?post=77658"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}