A Comparative Analysis of Object-Based and Pixel-Based Classification of RADARSAT-2 C-Band and Optical Satellite Data for Mapping Shoreline Types in the Canadian Arctic

Abstract. With increasing ship traffic and natural resource extraction in the Canadian Arctic, the chance of an oil spill occurring is steadily increasing. Oil deposited in the marine environment will impact the ocean, and as it is washed onto shore many species and their habitats. In 2009, Environment Canada initiated a project to produce baseline coastal information required for operational prioritization in the event of a marine oil spill in the Canadian Arctic. Earth observation data can potentially be used to improve on traditional mapping methods. RADARSAT-2 C-band data and geotagged videography were collected for selected sites in the Canadian Arctic. Object-based classification was compared to pixel-based classification using two of these pilot sites, Richards Island (Northwest Territories) and Ivvavik (Yukon Territory). The object-based classification achieved an overall accuracy of 74% at Richards Island and 63% at Ivvavik, whereas the pixel-based reached 73% at both sites. To test transferability, the classifiers developed at Richards Island were applied to Ivvavik. In this case, the object-based classification achieved an overall accuracy of 78% and the pixel-based reached 71%. Results showed that characterizing shorelines in the Arctic using Earth observation data for oil spill cleanup response activities is possible. Resume. Avec l'accroissement du trafic maritime et de l'exploitation des ressources naturelles dans l'Arctique canadien les risques d'un deversement d'hydrocarbure sont en augmentation. Les depots d'hydrocarbures auront un impact sur l'environnement marin. En 2009, Environnement Canada a initie un projet qui visait a ameliorer la connaissance des types de rivage afin de prioriser les operations de nettoyage dans l'eventualite d'un deversement d'hydrocarbure. Des videos geo-references et des images RADARSAT-2 ont ete acquis pour plusieurs sites de l'Arctique canadien. Une classification orientee-objet a ete comparee a une classification pixel-a-pixel pour deux de ces sites, soit l'ile Richards (Territoires du Nord-Ouest) et Ivvavik (Yukon). La classification orientee-objet a atteint une precision globale de 74% a l'ile Richards et de 63% a Ivvavik.La classification pixel-a-pixel a atteint une precision globale de 73% a chacun des sites. Les methodes de classification developpees a l'ile Richards ont ete appliquees a Ivvavik afin d'evaluer la transferabilite. La classification orientee-objet a atteint une precision globale de 78% et la classification pixel-a-pixel de 71%. Dans l'ensemble, les resultats ont demontres que les types de rivage de l'Arctique canadien peuvent etre caracterises a partir de donnees d'observation de la terre afin de supporter les operations de nettoyage.