{"id":393,"date":"2022-02-01T10:04:52","date_gmt":"2022-02-01T10:04:52","guid":{"rendered":"https:\/\/www2.kios.ucy.ac.cy\/ARTION\/?page_id=393"},"modified":"2025-02-13T08:03:34","modified_gmt":"2025-02-13T08:03:34","slug":"disaster-detector-classifier","status":"publish","type":"page","link":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/disaster-detector-classifier\/","title":{"rendered":"Disaster Detector \/ Classifier"},"content":{"rendered":"\n
\n

Developed by: Raphael Makrigiorgis and Elia Nicolaou<\/p>\n\n\n\n

Disaster detector and classifier for detecting fires, floods, and building disasters. <\/p>\n\n\n\n

The data that was used was taken from images from the Internet (YouTube, Kaggle) and from various missions that KIOS captured using UAVs (mostly for fires. The data was trained using Google’s online classifier[1]. A TensorFlow model was then exported and further used for detecting where exactly in the image or video frames a disaster is found. <\/p>\n\n\n\n

In order to convert the classifier to an object detector, upon capturing video frames, the image is rescaled to smaller images like a pyramid. Then, for each rescaled  frame a sliding window with a fixed size is passed through the image and classifying each region of interest.  These classifications are converted to boxes, therefore having multiple sized boxes depending on frame size. Finally, non-maxima suppression is used on these boxes to get the final detection boxes on the original frame. <\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n
\n\n\n\n

[1]<\/a> Teachable Machine.<\/em> (last accessed on 1\/2\/2022) https:\/\/teachablemachine.withgoogle.com\/<\/a><\/p>\n<\/div><\/div>\n\n\n\n

\n
\n
\n

Software<\/h3>\n<\/div>\n\n\n\n
\n

Code written in Python is available here: <\/p>\n\n\n\n

https:\/\/zenodo.org\/record\/5938343#.YfkSQ2hBzIU<\/a><\/p>\n<\/div>\n<\/div>\n<\/div><\/div>\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

Developed by: Raphael Makrigiorgis and Elia Nicolaou Disaster detector and classifier for detecting fires, floods, and building disasters. The data that was used was taken from images from the Internet (YouTube, Kaggle) and from various missions that KIOS captured using UAVs (mostly for fires. The data was trained using Google’s online classifier[1]. A TensorFlow model… Continue reading Disaster Detector \/ Classifier<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-393","page","type-page","status-publish","hentry","entry"],"_links":{"self":[{"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/pages\/393","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/comments?post=393"}],"version-history":[{"count":8,"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/pages\/393\/revisions"}],"predecessor-version":[{"id":556,"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/pages\/393\/revisions\/556"}],"wp:attachment":[{"href":"https:\/\/www.kios.ucy.ac.cy\/ARTION\/wp-json\/wp\/v2\/media?parent=393"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}