{"id":122,"date":"2023-05-09T18:21:31","date_gmt":"2023-05-09T18:21:31","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/?page_id=122"},"modified":"2023-12-19T00:58:42","modified_gmt":"2023-12-19T00:58:42","slug":"results","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/","title":{"rendered":"Results"},"content":{"rendered":"\n<h1 class=\"wp-block-heading\"><strong>Qualitative Analysis<\/strong><\/h1>\n\n\n\n<p>The image below shows the input images that were unseen during training and rendered 3D models from the poses predicted by the trained network. The alignment between the input images and rendered 3D models shows that the network is learning to predict poses that are close to the actual poses from which the images have been captured.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"303\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.26.56\u202fPM-1024x303.png\" alt=\"\" class=\"wp-image-300\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.26.56\u202fPM-1024x303.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.26.56\u202fPM-300x89.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.26.56\u202fPM-768x228.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.26.56\u202fPM-1536x455.png 1536w, https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.26.56\u202fPM.png 2032w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption class=\"wp-element-caption\">Figure: The top row shows the input images for the pose prediction network and the bottom row shows the rendered RGB images of the 3D model from predicted poses<\/figcaption><\/figure>\n\n\n\n<h1 class=\"wp-block-heading\"><strong>Quantitative Analysis<\/strong><\/h1>\n\n\n\n<p>We quantify our model by measuring errors in the translational and rotation components of the pose. We quantify the error in translational error using RMSE and rotational error using cosine similarity between ground truth and predicted quaternions. The metrics are defined as follows.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"474\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.34.24\u202fPM-1024x474.png\" alt=\"\" class=\"wp-image-301\" style=\"width:338px;height:auto\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.34.24\u202fPM-1024x474.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.34.24\u202fPM-300x139.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.34.24\u202fPM-768x356.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-content\/uploads\/sites\/82\/2023\/12\/Screenshot-2023-12-18-at-7.34.24\u202fPM.png 1188w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption class=\"wp-element-caption\">Figure: Metrics used to quantify our model<\/figcaption><\/figure>\n<\/div>\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td class=\"has-text-align-center\" data-align=\"center\"><strong>Metric<\/strong><\/td><td class=\"has-text-align-center\" data-align=\"center\"><strong>Value<\/strong><\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">Position Error<\/td><td class=\"has-text-align-center\" data-align=\"center\">1.44 meters<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">Angular Error<\/td><td class=\"has-text-align-center\" data-align=\"center\">5.38 degrees<\/td><\/tr><\/tbody><\/table><figcaption class=\"wp-element-caption\">Table: Metrics on the unseen validation dataset<\/figcaption><\/figure>\n\n\n\n<p>The table above shows the metrics computed on the unseen validation dataset. The position and angular errors are a fraction of the size of the C17 aircraft which is more than 50m long.<\/p>\n\n\n\n<h1 class=\"wp-block-heading\"><strong>Inference<\/strong><\/h1>\n\n\n\n<p>Since the model is a prototype of a model that will be used in commercial applications, we measured metrics relevant to the deployment of the model. The table below shows the metrics.<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td class=\"has-text-align-center\" data-align=\"center\"><strong>Metric<\/strong><\/td><td class=\"has-text-align-center\" data-align=\"center\"><strong>Value<\/strong><\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">No. of parameters<\/td><td class=\"has-text-align-center\" data-align=\"center\">21.3<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">Inference time<\/td><td class=\"has-text-align-center\" data-align=\"center\">2.7 ms\u00a0<br>(at full precision on RTX 3090Ti)<\/td><\/tr><tr><td class=\"has-text-align-center\" data-align=\"center\">FLOPS<\/td><td class=\"has-text-align-center\" data-align=\"center\">38.4 billion<\/td><\/tr><\/tbody><\/table><figcaption class=\"wp-element-caption\">Table: Metrics relevant for model inference<\/figcaption><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Qualitative Analysis The image below shows the input images that were unseen during training and rendered 3D models from the poses predicted by the trained network. The alignment between the input images and rendered 3D models shows that the network is learning to predict poses that are close to the actual poses from which the &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Results&#8221;<\/span><\/a><\/p>\n","protected":false},"author":164,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-122","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>Results - Automated Aircraft Inspection<\/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\/f23team5\/results\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Results - Automated Aircraft Inspection\" \/>\n<meta property=\"og:description\" content=\"Qualitative Analysis The image below shows the input images that were unseen during training and rendered 3D models from the poses predicted by the trained network. The alignment between the input images and rendered 3D models shows that the network is learning to predict poses that are close to the actual poses from which the &hellip; Continue reading &quot;Results&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/\" \/>\n<meta property=\"og:site_name\" content=\"Automated Aircraft Inspection\" \/>\n<meta property=\"article:modified_time\" content=\"2023-12-19T00:58:42+00:00\" \/>\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\\\/f23team5\\\/results\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/results\\\/\",\"name\":\"Results - Automated Aircraft Inspection\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/#website\"},\"datePublished\":\"2023-05-09T18:21:31+00:00\",\"dateModified\":\"2023-12-19T00:58:42+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/results\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/results\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/results\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Results\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/\",\"name\":\"Automated Aircraft Inspection\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/f23team5\\\/?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":"Results - Automated Aircraft Inspection","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\/f23team5\/results\/","og_locale":"en_US","og_type":"article","og_title":"Results - Automated Aircraft Inspection","og_description":"Qualitative Analysis The image below shows the input images that were unseen during training and rendered 3D models from the poses predicted by the trained network. The alignment between the input images and rendered 3D models shows that the network is learning to predict poses that are close to the actual poses from which the &hellip; Continue reading \"Results\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/","og_site_name":"Automated Aircraft Inspection","article_modified_time":"2023-12-19T00:58:42+00:00","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\/f23team5\/results\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/","name":"Results - Automated Aircraft Inspection","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/#website"},"datePublished":"2023-05-09T18:21:31+00:00","dateModified":"2023-12-19T00:58:42+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/results\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/"},{"@type":"ListItem","position":2,"name":"Results"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/","name":"Automated Aircraft Inspection","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/?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\/f23team5\/wp-json\/wp\/v2\/pages\/122","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-json\/wp\/v2\/users\/164"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-json\/wp\/v2\/comments?post=122"}],"version-history":[{"count":22,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-json\/wp\/v2\/pages\/122\/revisions"}],"predecessor-version":[{"id":309,"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-json\/wp\/v2\/pages\/122\/revisions\/309"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/f23team5\/wp-json\/wp\/v2\/media?parent=122"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}