{"id":362,"date":"2017-08-17T13:45:06","date_gmt":"2017-08-17T13:45:06","guid":{"rendered":"http:\/\/crowdflow.phys.tue.nl\/wordpress\/?page_id=362"},"modified":"2017-08-17T13:57:36","modified_gmt":"2017-08-17T13:57:36","slug":"tracking-technology","status":"publish","type":"page","link":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/","title":{"rendered":"Tracking technology"},"content":{"rendered":"<p>(Page still under construction)<\/p>\n<p>Using overhead depth sensors as raw data source, we experimented on different technologies to perform pedestrian detection and tracking, going from off-line to real-time capabilities.&nbsp;<\/p>\n<p>Typically, we look at pedestrian tracking as a two-phase job:&nbsp;<\/p>\n<ol>\n<li>per-frame pedestrian localization<\/li>\n<li>tracking<\/li>\n<\/ol>\n<p>Most of our R&amp;D went into point 1. while we outsourced point 2. to scientifc libraries, specifically<\/p>\n<ul>\n<li><a href=\"http:\/\/www.openptv.net\/\">OpenPTV<\/a> in case of off-line tracking (thanks <a href=\"http:\/\/www.tau.ac.il\/~alexlib\/\">Alex Liberzon<\/a>)&nbsp;<img decoding=\"async\" loading=\"lazy\" class=\"\" src=\"http:\/\/www.openptv.net\/images\/openptv_original_logo.png\" alt=\"OpenPTV Logo\" width=\"118\" height=\"40\"><\/li>\n<li><a href=\"http:\/\/soft-matter.github.io\/trackpy\/v0.3.2\/\">trackpy<\/a> in case of real-time tracking.<\/li>\n<\/ul>\n<p>Although our localization methods are published in papers, our codes are, at least for now, not freely available. We are working on localization following two alternative approaches:<\/p>\n<ul>\n<li>Hierarchical clustering of the depth cloud&nbsp;<br \/>\n&nbsp; &nbsp;<span style=\"color: #808080;\">see e.g. &nbsp; &nbsp; A.Corbetta et al. Fluctuations around mean walking behaviours in diluted pedestrian flows. Phys. Rev. E, 95 , pp. 032316, 2017. &nbsp;(<a href=\"http:\/\/crowdflow.phys.tue.nl\/wordpress\/publications\/\">publications&nbsp;<i class=\"fa fa-external-link \" ><\/i><\/a>)<\/span><\/li>\n<li>Convolutional Neural Network-based analysis of the depth cloud<br \/>\n&nbsp; <span style=\"color: #808080;\">see &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; A.Corbetta et al. Weakly supervised training of deep convolutional neural networks for overhead pedestrian localization in depth fields, AVSS17, 2017. (<a href=\"http:\/\/crowdflow.phys.tue.nl\/wordpress\/publications\/\">publications&nbsp;<i class=\"fa fa-external-link \" ><\/i><\/a>) or <a href=\"http:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/deep-learning-based-localization\/\">this poster&nbsp;<i class=\"fa fa-file-image-o \" ><\/i><\/a><\/span><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>(Page still under construction) Using overhead depth sensors as raw data source, we experimented on different technologies to perform pedestrian detection and tracking, going from off-line to real-time capabilities.&nbsp; Typically, we look at pedestrian tracking as a two-phase job:&nbsp; per-frame pedestrian localization tracking Most of our R&amp;D went into point 1. while we outsourced point &hellip; <a href=\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Tracking technology&#8221;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"parent":106,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_mi_skip_tracking":false,"ngg_post_thumbnail":0},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.1 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Tracking technology - Crowdflow Research Group<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Tracking technology - Crowdflow Research Group\" \/>\n<meta property=\"og:description\" content=\"(Page still under construction) Using overhead depth sensors as raw data source, we experimented on different technologies to perform pedestrian detection and tracking, going from off-line to real-time capabilities.&nbsp; Typically, we look at pedestrian tracking as a two-phase job:&nbsp; per-frame pedestrian localization tracking Most of our R&amp;D went into point 1. while we outsourced point &hellip; Continue reading &quot;Tracking technology&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/\" \/>\n<meta property=\"og:site_name\" content=\"Crowdflow Research Group\" \/>\n<meta property=\"article:modified_time\" content=\"2017-08-17T13:57:36+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/www.openptv.net\/images\/openptv_original_logo.png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/\",\"url\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/\",\"name\":\"Tracking technology - Crowdflow Research Group\",\"isPartOf\":{\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#website\"},\"datePublished\":\"2017-08-17T13:45:06+00:00\",\"dateModified\":\"2017-08-17T13:57:36+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Concepts\",\"item\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Tracking technology\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#website\",\"url\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/\",\"name\":\"Crowdflow Research Group\",\"description\":\"Exploring crowd dynamics @ Eindhoven University of Technology\",\"publisher\":{\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#organization\",\"name\":\"Crowdflow reasearch group TU\/e\",\"url\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-content\/uploads\/2017\/09\/cropped-cropped-Logo-beta-1.png\",\"contentUrl\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-content\/uploads\/2017\/09\/cropped-cropped-Logo-beta-1.png\",\"width\":240,\"height\":107,\"caption\":\"Crowdflow reasearch group TU\/e\"},\"image\":{\"@id\":\"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#\/schema\/logo\/image\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Tracking technology - Crowdflow Research Group","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/","og_locale":"en_US","og_type":"article","og_title":"Tracking technology - Crowdflow Research Group","og_description":"(Page still under construction) Using overhead depth sensors as raw data source, we experimented on different technologies to perform pedestrian detection and tracking, going from off-line to real-time capabilities.&nbsp; Typically, we look at pedestrian tracking as a two-phase job:&nbsp; per-frame pedestrian localization tracking Most of our R&amp;D went into point 1. while we outsourced point &hellip; Continue reading \"Tracking technology\"","og_url":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/","og_site_name":"Crowdflow Research Group","article_modified_time":"2017-08-17T13:57:36+00:00","og_image":[{"url":"http:\/\/www.openptv.net\/images\/openptv_original_logo.png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/","url":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/","name":"Tracking technology - Crowdflow Research Group","isPartOf":{"@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#website"},"datePublished":"2017-08-17T13:45:06+00:00","dateModified":"2017-08-17T13:57:36+00:00","breadcrumb":{"@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/tracking-technology\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/"},{"@type":"ListItem","position":2,"name":"Concepts","item":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/projects\/"},{"@type":"ListItem","position":3,"name":"Tracking technology"}]},{"@type":"WebSite","@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#website","url":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/","name":"Crowdflow Research Group","description":"Exploring crowd dynamics @ Eindhoven University of Technology","publisher":{"@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#organization","name":"Crowdflow reasearch group TU\/e","url":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#\/schema\/logo\/image\/","url":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-content\/uploads\/2017\/09\/cropped-cropped-Logo-beta-1.png","contentUrl":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-content\/uploads\/2017\/09\/cropped-cropped-Logo-beta-1.png","width":240,"height":107,"caption":"Crowdflow reasearch group TU\/e"},"image":{"@id":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/pages\/362"}],"collection":[{"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/comments?post=362"}],"version-history":[{"count":7,"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/pages\/362\/revisions"}],"predecessor-version":[{"id":365,"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/pages\/362\/revisions\/365"}],"up":[{"embeddable":true,"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/pages\/106"}],"wp:attachment":[{"href":"https:\/\/crowdflow.phys.tue.nl\/wordpress\/wp-json\/wp\/v2\/media?parent=362"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}