{"id":322,"date":"2022-12-21T00:52:36","date_gmt":"2022-12-21T00:52:36","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/?page_id=322"},"modified":"2022-12-21T01:02:47","modified_gmt":"2022-12-21T01:02:47","slug":"fall-2022-3","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/","title":{"rendered":"Fall 2022"},"content":{"rendered":"\n<h1 class=\"has-text-align-center wp-block-heading\"><strong>New dataset and pipeline<\/strong><\/h1>\n\n\n\n<p>To review, the challenges we face with Synthetic Dataset generation are as follows:<\/p>\n\n\n\n<ol class=\"wp-block-list\"><li>It is very time-consuming to build a dataset. <\/li><li>Multiview setting requires a lot of hacking to the game.<\/li><li>Domain transfer would be a problem<\/li><\/ol>\n\n\n\n<p>With these challenges in mind, we pivoted to the TBD Pedestrian dataset by CMU, which is multi-view and provides camera matrices and 2D trajectory labels for every pedestrian in all 3 camera views. The dataset is time synchronized so we know the frame number, pedestrian ID, and position coordinates of every person across all views. <\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23-1024x476.png\" alt=\"\" class=\"wp-image-258\" width=\"848\" height=\"394\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23-1024x476.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23-300x140.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23-768x357.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23.png 1197w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Proposed pipeline <\/figcaption><\/figure>\n\n\n\n<p>The pipeline we designed for 3D trajectory prediction is as follows:<\/p>\n\n\n\n<ol class=\"wp-block-list\"><li>Perform 2D pose estimation with ViTPose on all 3 camera views<\/li><li>Use a Greedy approach to match the bounding boxes of each pedestrian across at least 2 camera views. <\/li><li>Create a dataset of 2D pose sequences for each pedestrian across 2 camera views.<\/li><li>Perform triangulation using the camera matrices and the 2D pose sequences to obtain the 3D pose ground truth for each pedestrian<\/li><li>Perform trajectory forecasting to predict the 3D trajectories of each pedestrian<\/li><\/ol>\n\n\n\n<h2 class=\"has-text-align-left wp-block-heading\"><strong>(I) 2D Pose Estimation with ViTPose<\/strong><\/h2>\n\n\n\n<h2 class=\"has-text-align-center wp-block-heading\">Results of ViTPose on TBD Dataset<\/h2>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"480\" height=\"384\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/view11_compress.gif\" alt=\"\" class=\"wp-image-251\" \/><figcaption>Results on View 1<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"480\" height=\"384\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/view22_compress.gif\" alt=\"\" class=\"wp-image-252\" \/><figcaption>Results on View 2<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"480\" height=\"384\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/view33_compress.gif\" alt=\"\" class=\"wp-image-254\" \/><figcaption>Results on View 3<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>(II) Bounding Box Matching<\/strong><\/h2>\n\n\n\n<p>Now that we have obtained the bounding boxes and 2D pose key points for each pedestrian, we need to match them across camera views. We need 2D pose sequences for each pedestrian across camera views so that we can triangulate them to obtain 3D pose key points. Since 2 views are sufficient for triangulation, we perform bounding box matching for View 1 and View 2. <\/p>\n\n\n\n<p>To match pedestrians across views, we use the following greedy approach:<\/p>\n\n\n\n<ol class=\"wp-block-list\"><li>for each pedestrian with a trajectory label and pedestrian ID, for the first frame of that pedestrian ID, we find the closest bounding box to the trajectory point. <\/li><li>for subsequent frames, we track that bounding box, by finding the bounding box with the highest IOU with the previous frame<\/li><\/ol>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"480\" height=\"384\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/match1.gif\" alt=\"\" class=\"wp-image-259\" \/><figcaption>Matching 2D trajectory label to bounding box in View 1<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"480\" height=\"384\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/match2.gif\" alt=\"\" class=\"wp-image-260\" \/><figcaption>Matching 2D trajectory label to bounding box in View 2<\/figcaption><\/figure>\n\n\n\n<p>We now have a sequence of 2D pose trajectories for each pedestrian in both views, on which we can now perform triangulation to obtain 3D pose information.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>(III) Triangulation<\/strong><\/h2>\n\n\n\n<p>We use 2D pose sequences from view 1 and view 2, and the camera matrices for triangulation to obtain 3D ground truth pose sequences for each pedestrian.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"534\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-24-1024x534.png\" alt=\"\" class=\"wp-image-262\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-24-1024x534.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-24-300x156.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-24-768x400.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-24.png 1232w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Approach for Triangulation<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"555\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-25-1024x555.png\" alt=\"\" class=\"wp-image-264\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-25-1024x555.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-25-300x163.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-25-768x416.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-25.png 1195w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Perform triangulation to obtain 3D pose ground truth information<\/figcaption><\/figure>\n\n\n\n<p>However, the triangulated 3D joints are noisy due to the downstream errors from both pose estimation and bounding box matching.  Hence to obtain a smoother trajectory with less jitter we apply smoothening on skeleton gravity, limb length, and limb angles.<\/p>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-1 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"640\" height=\"480\" data-id=\"303\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image37-2.gif\" alt=\"\" class=\"wp-image-303\" \/><figcaption>Before smoothing<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"600\" height=\"450\" data-id=\"304\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image40.gif\" alt=\"\" class=\"wp-image-304\" \/><figcaption>After smoothing<\/figcaption><\/figure>\n<\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>(IV) Trajectory Forecasting<\/strong><\/h2>\n\n\n\n<p>We take 2 approaches to trajectory forecasting:<\/p>\n\n\n\n<ol class=\"wp-block-list\"><li>Predicting 3D point trajectory <\/li><\/ol>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-29-1024x225.png\" alt=\"\" class=\"wp-image-283\" width=\"841\" height=\"185\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-29-1024x225.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-29-300x66.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-29-768x169.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-29.png 1212w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Pipeline for prediction 3D point trajectory<\/figcaption><\/figure>\n\n\n\n<h2 class=\"has-text-align-center wp-block-heading\"><strong>Result<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-2 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"600\" height=\"450\" data-id=\"296\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image42.gif\" alt=\"\" class=\"wp-image-296\" \/><figcaption>Input 3D sequence<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"600\" height=\"450\" data-id=\"297\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image43.gif\" alt=\"\" class=\"wp-image-297\" \/><figcaption>Output 3D point trajectory<\/figcaption><\/figure>\n<\/figure>\n\n\n\n<p>2. Predicting 3D skeleton and trajectory<\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-30-1024x350.png\" alt=\"\" class=\"wp-image-284\" width=\"869\" height=\"297\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-30-1024x350.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-30-300x102.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-30-768x262.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-30.png 1210w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>Pipeline for prediction 3D skeleton trajectory<\/figcaption><\/figure>\n\n\n\n<h2 class=\"has-text-align-center wp-block-heading\"><strong>Result<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-default is-cropped wp-block-gallery-3 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"600\" height=\"450\" data-id=\"299\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image41.gif\" alt=\"\" class=\"wp-image-299\" \/><figcaption>Input 3D sequence<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"600\" height=\"450\" data-id=\"298\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image42-1.gif\" alt=\"\" class=\"wp-image-298\" \/><figcaption>Output 3D skeleton and trajectory prediction<\/figcaption><\/figure>\n<\/figure>\n","protected":false},"excerpt":{"rendered":"<p>New dataset and pipeline To review, the challenges we face with Synthetic Dataset generation are as follows: It is very time-consuming to build a dataset. Multiview setting requires a lot of hacking to the game. Domain transfer would be a problem With these challenges in mind, we pivoted to the TBD Pedestrian dataset by CMU, &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Fall 2022&#8221;<\/span><\/a><\/p>\n","protected":false},"author":137,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-322","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>Fall 2022 - Modeling and Understanding Pedestrian Behavior<\/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\/2022team11\/fall-2022-3\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Fall 2022 - Modeling and Understanding Pedestrian Behavior\" \/>\n<meta property=\"og:description\" content=\"New dataset and pipeline To review, the challenges we face with Synthetic Dataset generation are as follows: It is very time-consuming to build a dataset. Multiview setting requires a lot of hacking to the game. Domain transfer would be a problem With these challenges in mind, we pivoted to the TBD Pedestrian dataset by CMU, &hellip; Continue reading &quot;Fall 2022&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/\" \/>\n<meta property=\"og:site_name\" content=\"Modeling and Understanding Pedestrian Behavior\" \/>\n<meta property=\"article:modified_time\" content=\"2022-12-21T01:02:47+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23-1024x476.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=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/\",\"name\":\"Fall 2022 - Modeling and Understanding Pedestrian Behavior\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/wp-content\\\/uploads\\\/sites\\\/66\\\/2022\\\/12\\\/image-23-1024x476.png\",\"datePublished\":\"2022-12-21T00:52:36+00:00\",\"dateModified\":\"2022-12-21T01:02:47+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/wp-content\\\/uploads\\\/sites\\\/66\\\/2022\\\/12\\\/image-23.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/wp-content\\\/uploads\\\/sites\\\/66\\\/2022\\\/12\\\/image-23.png\",\"width\":1197,\"height\":557},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/fall-2022-3\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Fall 2022\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/\",\"name\":\"Modeling and Understanding Pedestrian Behavior\",\"description\":\"Students: Adithya Sampath, Mu Chien Hsu | Advisors: Laszlo Jeni (CMU) and Koichiro Niinuma (Fujitsu) | Industry Sponsor: Fujitsu |\",\"publisher\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/#organization\",\"name\":\"Modeling and Understanding Pedestrian Behavior\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/wp-content\\\/uploads\\\/sites\\\/66\\\/2022\\\/05\\\/cropped-download.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/wp-content\\\/uploads\\\/sites\\\/66\\\/2022\\\/05\\\/cropped-download.png\",\"width\":532,\"height\":250,\"caption\":\"Modeling and Understanding Pedestrian Behavior\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team11\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Fall 2022 - Modeling and Understanding Pedestrian Behavior","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\/2022team11\/fall-2022-3\/","og_locale":"en_US","og_type":"article","og_title":"Fall 2022 - Modeling and Understanding Pedestrian Behavior","og_description":"New dataset and pipeline To review, the challenges we face with Synthetic Dataset generation are as follows: It is very time-consuming to build a dataset. Multiview setting requires a lot of hacking to the game. Domain transfer would be a problem With these challenges in mind, we pivoted to the TBD Pedestrian dataset by CMU, &hellip; Continue reading \"Fall 2022\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/","og_site_name":"Modeling and Understanding Pedestrian Behavior","article_modified_time":"2022-12-21T01:02:47+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23-1024x476.png","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/","name":"Fall 2022 - Modeling and Understanding Pedestrian Behavior","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23-1024x476.png","datePublished":"2022-12-21T00:52:36+00:00","dateModified":"2022-12-21T01:02:47+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/12\/image-23.png","width":1197,"height":557},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/fall-2022-3\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/"},{"@type":"ListItem","position":2,"name":"Fall 2022"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/","name":"Modeling and Understanding Pedestrian Behavior","description":"Students: Adithya Sampath, Mu Chien Hsu | Advisors: Laszlo Jeni (CMU) and Koichiro Niinuma (Fujitsu) | Industry Sponsor: Fujitsu |","publisher":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/#organization","name":"Modeling and Understanding Pedestrian Behavior","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/#\/schema\/logo\/image\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/05\/cropped-download.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-content\/uploads\/sites\/66\/2022\/05\/cropped-download.png","width":532,"height":250,"caption":"Modeling and Understanding Pedestrian Behavior"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/pages\/322","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/users\/137"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/comments?post=322"}],"version-history":[{"count":3,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/pages\/322\/revisions"}],"predecessor-version":[{"id":344,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/pages\/322\/revisions\/344"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team11\/wp-json\/wp\/v2\/media?parent=322"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}