{"id":168,"date":"2020-12-22T22:22:20","date_gmt":"2020-12-22T22:22:20","guid":{"rendered":"http:\/\/mscvprojects.ri.cmu.edu\/2020teama\/?page_id=168"},"modified":"2020-12-22T23:24:37","modified_gmt":"2020-12-22T23:24:37","slug":"semantic-maps-for-relocalization","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/","title":{"rendered":"Semantic Maps for Relocalization"},"content":{"rendered":"\n<h4 class=\"wp-block-heading\">Setup<\/h4>\n\n\n\n<p>Given trajectories of multiple passes from a scene, we collect pairs of frames which are close in the world coordinate system:<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"690\" height=\"266\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes.png\" alt=\"\" class=\"wp-image-175\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes.png 690w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes-300x116.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes-230x89.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes-350x135.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes-480x185.png 480w\" sizes=\"auto, (max-width: 690px) 100vw, 690px\" \/><figcaption>Fig 1: Pairs of RGBD frames are used with their relative pose as ground truth, to evaluate relocalization<\/figcaption><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"486\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-1024x486.png\" alt=\"\" class=\"wp-image-176\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-1024x486.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-300x142.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-768x364.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-830x394.png 830w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-230x109.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-350x166.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1-480x228.png 480w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmaps-1.png 1204w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption>Fig 2: Pipeline for PnP based alignment of an RGBD frame with 3D ORB keypoints for relative pose estimation<\/figcaption><\/figure>\n\n\n\n<p>Compared to brute-force based matching, semantic map based matching will only take correspondendences which belong to same semantic category in both the images.<\/p>\n\n\n\n<h4 class=\"wp-block-heading\">Quantitative Results<\/h4>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"476\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-1024x476.png\" alt=\"\" class=\"wp-image-178\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-1024x476.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-300x139.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-768x357.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-830x386.png 830w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-230x107.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-350x163.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1-480x223.png 480w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semanticmap_table-1.png 1185w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption>Table 1: Accuracy of relocalization for Brute Force, Semantic-map based, and hybrid matching. Relocalization is said to be successful if the estimated pose error is &lt; ~0.1m in translation, and &lt; ~30deg in rotation.<\/figcaption><\/figure>\n\n\n\n<p>We see that the brute force approach outperforms the semantic map based approach, however, the error both the approaches make seem to be complimentary:<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"849\" height=\"267\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g.png\" alt=\"\" class=\"wp-image-179\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g.png 849w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g-300x94.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g-768x242.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g-830x261.png 830w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g-230x72.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g-350x110.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic1g-480x151.png 480w\" sizes=\"auto, (max-width: 849px) 100vw, 849px\" \/><figcaption>Fig 3: The figure shows error difference between semantic and bruteforce approaches, sorted in increasing order. Positive value means, for that sample, semantic map based matching creates more error, and vice-versa.<\/figcaption><\/figure>\n\n\n\n<p>Therefore, we try out a hybrid approach, where both methods are used, and number of inliers is used to choose one between them. Figure below shows that it does improve the performance, but as evident in Table 1, that improvement is not very high. <\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"842\" height=\"262\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g.png\" alt=\"\" class=\"wp-image-180\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g.png 842w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g-300x93.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g-768x239.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g-830x258.png 830w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g-230x72.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g-350x109.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/semantic2g-480x149.png 480w\" sizes=\"auto, (max-width: 842px) 100vw, 842px\" \/><figcaption>Fig 4: The figure shows error difference between semantic and hybrid approaches, sorted in increasing order. Positive value means, for that sample, semantic map based matching creates more error, and vice-versa. Notice how it it like a thinned out version of previous graph.<\/figcaption><\/figure>\n\n\n\n<h4 class=\"wp-block-heading\">Qualitative Results<\/h4>\n\n\n\n<p>The qualitative results below show a pair of images in RGB and in semantic-map format. The matches are done on RGB features, but semantic maps were used to guide them, so that&#8217;s why we show the semantic maps in (ii) approach. Translation and rotation errors are written for all cases.<\/p>\n\n\n\n<p>A: Semantic maps performing better than brute force approach:<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s1.png\" alt=\"\" class=\"wp-image-181\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s1.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s1-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s1-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s1-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s1-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s2.png\" alt=\"\" class=\"wp-image-182\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s2.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s2-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s2-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s2-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s2-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s3.png\" alt=\"\" class=\"wp-image-183\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s3.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s3-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s3-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s3-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s3-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s4.png\" alt=\"\" class=\"wp-image-184\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s4.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s4-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s4-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s4-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/s4-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<p>B: Brute force approach performing better:<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b1.png\" alt=\"\" class=\"wp-image-187\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b1.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b1-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b1-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b1-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b1-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b2.png\" alt=\"\" class=\"wp-image-188\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b2.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b2-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b2-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b2-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b2-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b3.png\" alt=\"\" class=\"wp-image-189\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b3.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b3-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b3-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b3-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b3-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image\"><img loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"342\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b4.png\" alt=\"\" class=\"wp-image-190\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b4.png 512w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b4-300x200.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b4-230x154.png 230w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b4-350x234.png 350w, https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/b4-480x321.png 480w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Setup Given trajectories of multiple passes from a scene, we collect pairs of frames which are close in the world coordinate system: [&hellip;]<\/p>\n","protected":false},"author":70,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-168","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Semantic Maps for Relocalization - Long Term Mapping for SLAM in Dynamic Environments<\/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\/2020teama\/semantic-maps-for-relocalization\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Semantic Maps for Relocalization - Long Term Mapping for SLAM in Dynamic Environments\" \/>\n<meta property=\"og:description\" content=\"Setup Given trajectories of multiple passes from a scene, we collect pairs of frames which are close in the world coordinate system: [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/\" \/>\n<meta property=\"og:site_name\" content=\"Long Term Mapping for SLAM in Dynamic Environments\" \/>\n<meta property=\"article:modified_time\" content=\"2020-12-22T23:24:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes.png\" \/>\n\t<meta property=\"og:image:width\" content=\"690\" \/>\n\t<meta property=\"og:image:height\" content=\"266\" \/>\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=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/\",\"name\":\"Semantic Maps for Relocalization - Long Term Mapping for SLAM in Dynamic Environments\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/wp-content\\\/uploads\\\/sites\\\/31\\\/2020\\\/12\\\/passes.png\",\"datePublished\":\"2020-12-22T22:22:20+00:00\",\"dateModified\":\"2020-12-22T23:24:37+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/wp-content\\\/uploads\\\/sites\\\/31\\\/2020\\\/12\\\/passes.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/wp-content\\\/uploads\\\/sites\\\/31\\\/2020\\\/12\\\/passes.png\",\"width\":690,\"height\":266},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/semantic-maps-for-relocalization\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Semantic Maps for Relocalization\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/\",\"name\":\"Long Term Mapping for SLAM in Dynamic Environments\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2020teama\\\/?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":"Semantic Maps for Relocalization - Long Term Mapping for SLAM in Dynamic Environments","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\/2020teama\/semantic-maps-for-relocalization\/","og_locale":"en_US","og_type":"article","og_title":"Semantic Maps for Relocalization - Long Term Mapping for SLAM in Dynamic Environments","og_description":"Setup Given trajectories of multiple passes from a scene, we collect pairs of frames which are close in the world coordinate system: [&hellip;]","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/","og_site_name":"Long Term Mapping for SLAM in Dynamic Environments","article_modified_time":"2020-12-22T23:24:37+00:00","og_image":[{"width":690,"height":266,"url":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/","name":"Semantic Maps for Relocalization - Long Term Mapping for SLAM in Dynamic Environments","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes.png","datePublished":"2020-12-22T22:22:20+00:00","dateModified":"2020-12-22T23:24:37+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-content\/uploads\/sites\/31\/2020\/12\/passes.png","width":690,"height":266},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/semantic-maps-for-relocalization\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/"},{"@type":"ListItem","position":2,"name":"Semantic Maps for Relocalization"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/","name":"Long Term Mapping for SLAM in Dynamic Environments","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/?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\/2020teama\/wp-json\/wp\/v2\/pages\/168","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-json\/wp\/v2\/users\/70"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-json\/wp\/v2\/comments?post=168"}],"version-history":[{"count":3,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-json\/wp\/v2\/pages\/168\/revisions"}],"predecessor-version":[{"id":191,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-json\/wp\/v2\/pages\/168\/revisions\/191"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2020teama\/wp-json\/wp\/v2\/media?parent=168"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}