{"id":35,"date":"2018-10-14T04:15:23","date_gmt":"2018-10-14T04:15:23","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/?p=35"},"modified":"2018-10-14T04:16:43","modified_gmt":"2018-10-14T04:16:43","slug":"status-update-10-13-18","status":"publish","type":"post","link":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/2018\/10\/14\/status-update-10-13-18\/","title":{"rendered":"Status Update 10\/13\/18"},"content":{"rendered":"<h1><strong>Aayush<\/strong><\/h1>\n<ul>\n<li>Worked on the design review presentation and the design document<\/li>\n<li>Came across a paper on &#8220;Real-time eye blinking detection using facial landmarks&#8221; and used that idea along with OpenCV and dlib to implement eye open\/close detection algorithm. The algorithm maps 68 facial landmarks onto the input image.<\/li>\n<\/ul>\n<p>Eye markers for open and closed eyes look like:<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"size-medium wp-image-38 alignleft\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.08.00-PM-300x131.png\" alt=\"\" width=\"300\" height=\"131\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.08.00-PM-300x131.png 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.08.00-PM.png 632w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>The algorithm then computes distances between the features for each of the eyes and averages them out to give a number. I trained it on various baby images and it seems to work really well. (only 1 out of 100 was incorrectly classified).<\/p>\n<p>Correctly detecting open eyes:<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-medium wp-image-39\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.51-PM-300x192.png\" alt=\"\" width=\"300\" height=\"192\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.51-PM-300x192.png 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.51-PM-768x491.png 768w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.51-PM-1024x655.png 1024w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.51-PM.png 1796w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<p>Correctly detecting closed eyes:<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-medium wp-image-41\" src=\"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.24-PM-300x192.png\" alt=\"\" width=\"300\" height=\"192\" srcset=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.24-PM-300x192.png 300w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.24-PM-768x491.png 768w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.24-PM-1024x655.png 1024w, https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-content\/uploads\/sites\/5\/2018\/10\/Screen-Shot-2018-10-13-at-10.09.24-PM.png 1154w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/p>\n<ul>\n<li>I also developed a simple android application to save accelerometer data into a file on the phone so that we can use it to test sleep detection algorithm. The app currently saves acceleration along 3 x-axis, y-axis and z-axis.<\/li>\n<\/ul>\n<h1><strong>Angela<\/strong><\/h1>\n<ul>\n<li>Worked on the design review presentation and the design document<\/li>\n<li>Identified important types of patterns that distinguish sleep and wake accelerometer data for the use cases that we were interested in\n<ul>\n<li>Sleep with short bursts of movement around once per minute<\/li>\n<li>Regular activity, irregular acceleration<\/li>\n<li>Regular activity, sinusoidal acceleration for motion artifact<\/li>\n<\/ul>\n<\/li>\n<li>Ran different simulations on simulated accelerometer data to measure accuracy\n<ul>\n<li>Got an accuracy of 99%<\/li>\n<\/ul>\n<\/li>\n<li>Ran simulations on simulated heart rate data with motion artifact and noise\n<ul>\n<li>Got an accuracy of 98%<\/li>\n<li>BPM of 120 to 150<\/li>\n<\/ul>\n<\/li>\n<li>Reevaluated some testing data sets<\/li>\n<li>Read papers on sensor fusion for computer vision\n<ul>\n<li>Goals for next week are to see how to apply this to our problem<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Aayush Worked on the design review presentation and the design document Came across a paper on &#8220;Real-time eye blinking detection using facial landmarks&#8221; and used that idea along with OpenCV and dlib to implement eye open\/close detection algorithm. The algorithm maps 68 facial landmarks onto the input image. Eye markers for open and closed eyes &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/2018\/10\/14\/status-update-10-13-18\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Status Update 10\/13\/18&#8221;<\/span><\/a><\/p>\n","protected":false},"author":24,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"image","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/posts\/35"}],"collection":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/users\/24"}],"replies":[{"embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/comments?post=35"}],"version-history":[{"count":10,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/posts\/35\/revisions"}],"predecessor-version":[{"id":50,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/posts\/35\/revisions\/50"}],"wp:attachment":[{"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/media?parent=35"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/categories?post=35"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/course.ece.cmu.edu\/~ece500\/projects\/f18-team1\/wp-json\/wp\/v2\/tags?post=35"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}