{"id":16,"date":"2019-04-26T15:27:40","date_gmt":"2019-04-26T15:27:40","guid":{"rendered":"http:\/\/mscvprojects.ri.cmu.edu\/2019teami\/?page_id=16"},"modified":"2019-12-07T01:43:55","modified_gmt":"2019-12-07T01:43:55","slug":"project-overview","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/","title":{"rendered":"Overview"},"content":{"rendered":"<ul>\n<li>Motivation\n<ul>\n<li>Real-time multi-person pedestrian tracking is a major component of many applications, e.g. autonomous driving or autonomous construction scenarios where pedestrians have to be detected and tracked in real time for safe operations.<\/li>\n<li>Recently, a lot of works have tackled the problem of real-time single object tracking. Although achieving state-of-the-art accuracy while running as fast as hundreds of frames per second, these algorithms focus on tracking single object only, which is sub-optimal in realistic settings.<\/li>\n<li>There are other recent methods that focus on multiple object tracking, which utilize a detection+tracking+assfication architecture. These methods achieve great performance but lack the ability to run in real time, which is essential to our work.<img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-medium wp-image-25\" src=\"http:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en-300x168.png\" alt=\"\" width=\"300\" height=\"168\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en-300x168.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en-768x430.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en.png 958w\" sizes=\"auto, (max-width: 300px) 100vw, 300px\" \/><\/li>\n<\/ul>\n<\/li>\n<li>Problem\n<ul>\n<li>The main challenge is to handle some difficult scenarios, such as occlusion, appearance change, pedestrian crossing.<\/li>\n<li>The second challenge is that the time complexity will increase with more tracking objects.<\/li>\n<\/ul>\n<\/li>\n<li>Solution\n<ul>\n<li><span style=\"font-weight: 400\">We are trying to use one-stage network for both detection and matching.<\/span><\/li>\n<li><span style=\"font-weight: 400\">We believe Graph Neural Network (GNN) is useful for simultaneous detection and association<\/span><\/li>\n<li><span style=\"font-weight: 400\">We designed a Non-Maximum Suppression specifically tailored for the tracking task<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Motivation Real-time multi-person pedestrian tracking is a major component of many applications, e.g. autonomous driving or autonomous construction scenarios where pedestrians have to be detected and tracked in real time for safe operations. Recently, a lot of works have tackled the problem of real-time single object tracking. Although achieving state-of-the-art accuracy while running as fast &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Overview&#8221;<\/span><\/a><\/p>\n","protected":false},"author":50,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-16","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Overview - Embedded Pedestrian Tracking and Detection<\/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:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Overview - Embedded Pedestrian Tracking and Detection\" \/>\n<meta property=\"og:description\" content=\"Motivation Real-time multi-person pedestrian tracking is a major component of many applications, e.g. autonomous driving or autonomous construction scenarios where pedestrians have to be detected and tracked in real time for safe operations. Recently, a lot of works have tackled the problem of real-time single object tracking. Although achieving state-of-the-art accuracy while running as fast &hellip; Continue reading &quot;Overview&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/\" \/>\n<meta property=\"og:site_name\" content=\"Embedded Pedestrian Tracking and Detection\" \/>\n<meta property=\"article:modified_time\" content=\"2019-12-07T01:43:55+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en.png\" \/>\n\t<meta property=\"og:image:width\" content=\"958\" \/>\n\t<meta property=\"og:image:height\" content=\"537\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/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:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/\",\"name\":\"Overview - Embedded Pedestrian Tracking and Detection\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/#primaryimage\"},\"thumbnailUrl\":\"http:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/wp-content\\\/uploads\\\/sites\\\/24\\\/2019\\\/05\\\/Image1509487en-300x168.png\",\"datePublished\":\"2019-04-26T15:27:40+00:00\",\"dateModified\":\"2019-12-07T01:43:55+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/wp-content\\\/uploads\\\/sites\\\/24\\\/2019\\\/05\\\/Image1509487en.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/wp-content\\\/uploads\\\/sites\\\/24\\\/2019\\\/05\\\/Image1509487en.png\",\"width\":958,\"height\":537},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/project-overview\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Overview\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/\",\"name\":\"Embedded Pedestrian Tracking and Detection\",\"description\":\"Chunhui Liu, Yongxin Wang, advised by Kris Kitani\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2019teami\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Overview - Embedded Pedestrian Tracking and Detection","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:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/","og_locale":"en_US","og_type":"article","og_title":"Overview - Embedded Pedestrian Tracking and Detection","og_description":"Motivation Real-time multi-person pedestrian tracking is a major component of many applications, e.g. autonomous driving or autonomous construction scenarios where pedestrians have to be detected and tracked in real time for safe operations. Recently, a lot of works have tackled the problem of real-time single object tracking. Although achieving state-of-the-art accuracy while running as fast &hellip; Continue reading \"Overview\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/","og_site_name":"Embedded Pedestrian Tracking and Detection","article_modified_time":"2019-12-07T01:43:55+00:00","og_image":[{"width":958,"height":537,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/","name":"Overview - Embedded Pedestrian Tracking and Detection","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/#primaryimage"},"thumbnailUrl":"http:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en-300x168.png","datePublished":"2019-04-26T15:27:40+00:00","dateModified":"2019-12-07T01:43:55+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-content\/uploads\/sites\/24\/2019\/05\/Image1509487en.png","width":958,"height":537},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/project-overview\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/"},{"@type":"ListItem","position":2,"name":"Overview"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/","name":"Embedded Pedestrian Tracking and Detection","description":"Chunhui Liu, Yongxin Wang, advised by Kris Kitani","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/pages\/16","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/users\/50"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/comments?post=16"}],"version-history":[{"count":5,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/pages\/16\/revisions"}],"predecessor-version":[{"id":47,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/pages\/16\/revisions\/47"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2019teami\/wp-json\/wp\/v2\/media?parent=16"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}