{"id":148,"date":"2012-02-13T09:26:26","date_gmt":"2012-02-13T09:26:26","guid":{"rendered":"http:\/\/www.giovannigualdi.com\/wordpress\/?page_id=148"},"modified":"2012-02-13T14:12:51","modified_gmt":"2012-02-13T14:12:51","slug":"obstacle-detection-and-classification-based-on-vision","status":"publish","type":"page","link":"http:\/\/www.giovannigualdi.com\/?page_id=148","title":{"rendered":"Obstacle Detection and Classification"},"content":{"rendered":"<p>Thanks to a research grant I got on stereo vision topics in 2010, I produced an application <span style=\"color: #993300;\">exploiting both depth images and visible spectrum images<\/span> (i.e. regular images), aimed to <span style=\"color: #993300;\">detection of obstacles and their classification<\/span> (i.e. understanding if they are pedestrians, vehicles, debris, etc.).<\/p>\n<p>I eventually produced an application <span style=\"color: #993300;\">aimed to the safety in tractors, for the business in precision agriculture.<\/span><\/p>\n<p>Let me show here a <span style=\"color: #993300;\">test installation on a car and a demo video<\/span>; the speed of the car and of the events happening, much higher than a tractor, make the detection definitively more challenging.<\/p>\n<p><a class=\"highslide\" title=\"car-setup.jpg\" onclick=\"return hs.expand(this )\" href=\"\/wordpress\/wp-content\/uploads\/2012\/02\/car-setup.jpg\" target=\"_blank\"><img class=\"aligncenter\" src=\"\/wordpress\/wp-content\/uploads\/2012\/02\/car-setup-t.jpg\" alt=\"car-setup-t.jpg\" \/><\/a><\/p>\n<div class=\"youtube\" style=\"width: 640; height: 360;\"><object width=\"640\" height=\"360\" classid=\"clsid:d27cdb6e-ae6d-11cf-96b8-444553540000\" codebase=\"http:\/\/download.macromedia.com\/pub\/shockwave\/cabs\/flash\/swflash.cab#version=6,0,40,0\"><param name=\"wmode\" value=\"transparent\" \/><param name=\"src\" value=\"http:\/\/www.youtube.com\/v\/gnStBtDTi2w&amp;rel=0&amp;hd=1&amp;autohide=1\" \/><embed width=\"640\" height=\"360\" type=\"application\/x-shockwave-flash\" src=\"http:\/\/www.youtube.com\/v\/gnStBtDTi2w&amp;rel=0&amp;hd=1&amp;autohide=1\" wmode=\"transparent\" \/><\/object><\/div>\n<ul>\n<li>on the left frame you will see the regular video<\/li>\n<li>on the center frame there is the depth image<\/li>\n<li>on the right the superimposition of the two: here you can also see a white rectangle, that is the focus of attention of detection, which is automatically positioned based on the ground level estimation.<\/li>\n<li>obstacles are highlighted in green (metric distance in the upper part of the central frame)<\/li>\n<li>obstacle that are too close are highlighted in red (the threshold between green and red is just a parameter).<\/li>\n<li>pedestrians are boxed in yellow.<\/li>\n<\/ul>\n<p>A few more demo videos: <span style=\"color: #993300;\">the last one is taken under heavy rain.<\/span><\/p>\n<div class=\"youtube\" style=\"width: 640; height: 360;\"><object width=\"640\" height=\"360\" classid=\"clsid:d27cdb6e-ae6d-11cf-96b8-444553540000\" codebase=\"http:\/\/download.macromedia.com\/pub\/shockwave\/cabs\/flash\/swflash.cab#version=6,0,40,0\"><param name=\"wmode\" value=\"transparent\" \/><param name=\"src\" value=\"http:\/\/www.youtube.com\/v\/icavXTsI5P0&amp;rel=0&amp;hd=1&amp;autohide=1\" \/><embed width=\"640\" height=\"360\" type=\"application\/x-shockwave-flash\" src=\"http:\/\/www.youtube.com\/v\/icavXTsI5P0&amp;rel=0&amp;hd=1&amp;autohide=1\" wmode=\"transparent\" \/><\/object><\/div>\n<div class=\"youtube\" style=\"width: 640; height: 360;\"><object width=\"640\" height=\"360\" classid=\"clsid:d27cdb6e-ae6d-11cf-96b8-444553540000\" codebase=\"http:\/\/download.macromedia.com\/pub\/shockwave\/cabs\/flash\/swflash.cab#version=6,0,40,0\"><param name=\"wmode\" value=\"transparent\" \/><param name=\"src\" value=\"http:\/\/www.youtube.com\/v\/s8GdHZQdjlU&amp;rel=0&amp;hd=1&amp;autohide=1\" \/><embed width=\"640\" height=\"360\" type=\"application\/x-shockwave-flash\" src=\"http:\/\/www.youtube.com\/v\/s8GdHZQdjlU&amp;rel=0&amp;hd=1&amp;autohide=1\" wmode=\"transparent\" \/><\/object><\/div>\n<div class=\"youtube\" style=\"width: 640; height: 360;\"><object width=\"640\" height=\"360\" classid=\"clsid:d27cdb6e-ae6d-11cf-96b8-444553540000\" codebase=\"http:\/\/download.macromedia.com\/pub\/shockwave\/cabs\/flash\/swflash.cab#version=6,0,40,0\"><param name=\"wmode\" value=\"transparent\" \/><param name=\"src\" value=\"http:\/\/www.youtube.com\/v\/rwnCzI7CJmY&amp;rel=0&amp;hd=1&amp;autohide=1\" \/><embed width=\"640\" height=\"360\" type=\"application\/x-shockwave-flash\" src=\"http:\/\/www.youtube.com\/v\/rwnCzI7CJmY&amp;rel=0&amp;hd=1&amp;autohide=1\" wmode=\"transparent\" \/><\/object><\/div>\n<p>Acknowledgment for this work<\/p>\n<ul>\n<li>Spinner 2013 &#8220;Persone al futuro&#8221; (Ministero del Lavoro e delle Politiche Sociali, Regione Emilia Romagna, Fondo sociale europeo dell&#8217;Unione Europea),<\/li>\n<li>ReLab<\/li>\n<li>ImageLab<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Thanks to a research grant I got on stereo vision topics in 2010, I produced an application exploiting both depth images and visible spectrum images (i.e. regular images), aimed to detection of obstacles and their classification (i.e. understanding if they &hellip; <a href=\"http:\/\/www.giovannigualdi.com\/?page_id=148\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"open","ping_status":"open","template":"","meta":[],"_links":{"self":[{"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=\/wp\/v2\/pages\/148"}],"collection":[{"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=148"}],"version-history":[{"count":5,"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=\/wp\/v2\/pages\/148\/revisions"}],"predecessor-version":[{"id":150,"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=\/wp\/v2\/pages\/148\/revisions\/150"}],"wp:attachment":[{"href":"http:\/\/www.giovannigualdi.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=148"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}