{"id":11989,"date":"2023-03-17T08:09:15","date_gmt":"2023-03-17T11:09:15","guid":{"rendered":"https:\/\/www.fie.undef.edu.ar\/ceptm\/?p=11989"},"modified":"2023-03-17T08:14:48","modified_gmt":"2023-03-17T11:14:48","slug":"sistema-robotico-que-utiliza-imagenes-multiespectrales-e-inteligencia-artificial-para-buscar-victimas-del-terremoto","status":"publish","type":"post","link":"https:\/\/www.fie.undef.edu.ar\/ceptm\/?p=11989","title":{"rendered":"Sistema rob\u00f3tico que utiliza im\u00e1genes multiespectrales e inteligencia artificial para buscar v\u00edctimas del terremoto"},"content":{"rendered":"<p>Las terribles secuelas de los recientes terremotos que sacudieron Siria y Turqu\u00eda dejan en claro por qu\u00e9 se necesita una variedad de tecnolog\u00edas para buscar sobrevivientes entre los escombros de los edificios destruidos. Ahora, investigadores de la Universidad Polit\u00e9cnica de Madrid han desarrollado un sistema rob\u00f3tico aut\u00f3nomo que combina inteligencia artificial con im\u00e1genes multiespectrales para buscar personas en entornos peligrosos y de dif\u00edcil acceso posteriores a un desastre.<\/p>\n<hr \/>\n<p>The horrific aftermath of the recent earthquakes that struck Syria and Turkey makes it clear why a range of technologies are needed to search for survivors in the rubble of destroyed buildings. Now, researchers at the Polytechnic University of Madrid have developed an autonomous robotic system that combines artificial intelligence with multispectral imaging to search for people in dangerous and difficult to access post-disaster environments.<\/p>\n<p>The system uses an Altum multispectral camera that operates at five wavelengths \u2013 red, green and blue visible light; near infrared; and red edge light. The camera is attached to a remote-controlled quadruped robot that can be deployed in dangerous environments such as a collapsed building.<\/p>\n<p><a href=\"https:\/\/www.car.upm-csic.es\/authors\/cap-christyan-mario-ulloa-cruz\/\" target=\"_blank\" rel=\"noopener\">Christyan Cruz Ulloa<\/a>\u00a0and colleagues developed multispectral indexes that can be used to identify people within rubble. An index is a way of combining images taken at different wavelengths to enhance the ability of the multispectral imaging system to identify specific objects. Such indexes are often used to identify vegetation in satellite images, but no index had existed for identifying people in a rubble environment.<\/p>\n<p><strong>Convolutional neural networks<\/strong><\/p>\n<p>Once the team had identified an index that was suitable for both indoor and outdoor identification of people within a background of rubble, the next step was to train several convolutional neural networks (CNNs) to identify human forms \u2013 such as a torso, head and hand \u2013 within rubble. The researchers then compared efficacy of the different CNNs. This allowed them to select the best CNN for this application \u2013 a CNN called YOLOv5m.<\/p>\n<p>The researchers then compared their prototype technique with previous systems, which tend to use either red-green-blue or infrared imaging to locate victims. They conclude that their multispectral system has greater versatility when it comes to locating people in both indoor and outdoor environments.<\/p>\n<p><strong>Fuente:<\/strong> <a href=\"https:\/\/physicsworld.com\/a\/robotic-system-uses-multispectral-imaging-and-artificial-intelligence-to-search-for-earthquake-victims\/\" target=\"_blank\" rel=\"noopener\"><em>https:\/\/physicsworld.com<\/em><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Las terribles secuelas de los recientes terremotos que sacudieron Siria y Turqu\u00eda dejan en claro por qu\u00e9 se necesita una variedad de tecnolog\u00edas para buscar&hellip; <\/p>\n","protected":false},"author":1,"featured_media":11990,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[2,36],"tags":[],"_links":{"self":[{"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=\/wp\/v2\/posts\/11989"}],"collection":[{"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=11989"}],"version-history":[{"count":2,"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=\/wp\/v2\/posts\/11989\/revisions"}],"predecessor-version":[{"id":11992,"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=\/wp\/v2\/posts\/11989\/revisions\/11992"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=\/wp\/v2\/media\/11990"}],"wp:attachment":[{"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=11989"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=11989"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.fie.undef.edu.ar\/ceptm\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=11989"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}