{"id":6639,"date":"2020-06-12T10:28:57","date_gmt":"2020-06-12T08:28:57","guid":{"rendered":"https:\/\/nr.stage.dekodes.no\/nyheter\/charcoal-kilns-at-lesja-are-detected-in-airborne-laser-data-using-deep-learning\/"},"modified":"2021-05-26T16:58:18","modified_gmt":"2021-05-26T14:58:18","slug":"charcoal-kilns-at-lesja-are-detected-in-airborne-laser-data-using-deep-learning","status":"publish","type":"post","link":"https:\/\/nr.stage.dekodes.no\/en\/news\/charcoal-kilns-at-lesja-are-detected-in-airborne-laser-data-using-deep-learning\/","title":{"rendered":"Charcoal kilns at Lesja are detected in airborne laser data using deep learning"},"content":{"rendered":"

\"\"\"\"NR Researchers Arnt-B\u00f8rre Salberg and \u00d8ivind Due Trier are now using deep learning for semi-automatic detection of charcoal kilns from airborne laser scanning (ALS) data. Preliminary results indicate that this is very effective compared to traditional pattern recognition methods. <\/em><\/p>\n

With deep learning, 85% of the kilns are detected, with only 10% false positives in addition. With traditional pattern recognition on similar problems, the correct classification rate was lower, and the number of false positives was orders of magnitude higher.<\/p>\n

Charcoal kilns were used by ironworks a few hundred years ago. E.g., in Lesja municipality, Oppland County, Norway, there was an ironwork from 1660-1812. For the purpose of historical documentation, archaeologists are interested in mapping the exact location and size of each charcoal kiln. It is difficult to hand-craft an automatic detection method that may locate charcoal kilns. However, a number of image detection problems have been solved recently by the use of deep learing.<\/p>\n

In 2012 an image recognition system based on deep convolutional neural network (CNN) won the ImageNet contest with a clear margin to competing algorithms. This sparked a revolution in computer vision, and today we have witnessed that deep learning-based systems have drastically surpassed previous state-of-the-art results in image classification accuracy. \u00a0In order to train a CNN with high performance, a substantial amount of labelled training images is needed. For many applications this is not feasible. However, a \u201csmall data approach\u201d exists. It has been successfully demonstrated that the features extracted from a deep CNN, carefully trained on the large ImageNet database, may be applied as generic feature representations and thereby applied to perform a wide variety of vision tasks. \u00a0<\/p>\n

We have applied this \u201csmall data approach\u201d approach to extract image features from a digital terrain model derived from the ALS data. From each image crop the deep network outputs 4096 image features, which are applied as input to a linear support vector machine that is trained to distinguish charcoal kilns from lookalikes.<\/p>\n

In the initial experiment, deep learning is used within a 3 \u00d7 3 km\u00b2 area at Sandom in Lesja municipality, containing 375 charcoal kilns. Crossvalidation gives 85% correct classification. In addition, only 10% false positives are obtained. This is dramatically better than the results we have previously obtained using traditional pattern recognition for the detection of grave mounds and charcoal kilns.<\/p>\n

Read more about the project CultSearcher<\/a>.<\/p>\n

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

NR Researchers Arnt-B\u00f8rre Salberg and \u00d8ivind Due Trier are now using deep learning for semi-automatic detection of charcoal kilns from airborne laser scanning (ALS) data. Preliminary results indicate that this is very effective compared to traditional pattern recognition methods.<\/p>\n

With deep learning, 85% of the kilns are detected, with only 10% false positives in addition. With traditional pattern recognition on similar problems, the correct classification rate was lower, and the number of false positives was orders of magnitude higher.<\/p>\n","protected":false},"author":2,"featured_media":6640,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_trash_the_other_posts":false,"editor_notices":[],"footnotes":""},"categories":[1],"tags":[],"class_list":{"0":"post-6639","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-news"},"acf":[],"_links":{"self":[{"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/posts\/6639","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/comments?post=6639"}],"version-history":[{"count":3,"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/posts\/6639\/revisions"}],"predecessor-version":[{"id":12343,"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/posts\/6639\/revisions\/12343"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/media\/6640"}],"wp:attachment":[{"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/media?parent=6639"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/categories?post=6639"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nr.stage.dekodes.no\/en\/wp-json\/wp\/v2\/tags?post=6639"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}