{"@type": "dcat:Dataset", "accessLevel": "public", "accrualPeriodicity": "irregular", "bureauCode": ["026:00"], "contactPoint": {"@type": "vcard:Contact", "fn": "Elizabeth Foughty", "hasEmail": "mailto:elizabeth.a.foughty@nasa.gov"}, "description": "Classification of Mars Terrain Using Multiple Data Sources\r\n\r\nAlan Kraut1, David Wettergreen1\r\n\r\nABSTRACT. Images of Mars are being collected faster than they can be analyzed by planetary\r\nscientists. Automatic analysis of images would enable more rapid and more consistent image\r\ninterpretation and could draft geologic maps where none yet exist. In this work we develop a\r\nmethod for incorporating images from multiple instruments to classify Martian terrain into\r\nmultiple types. Each image is segmented into contiguous groups of similar pixels, called\r\nsuperpixels, with an associated vector of discriminative features. We have developed and\r\ntested several classification algorithms to associate a best class to each superpixel. These\r\nclassifiers are trained using three different manual classifications with between 2 and 6 classes.\r\nAutomatic classification accuracies of 50 to 80% are achieved in leave-one-out cross-validation\r\nacross 20 scenes using a multi-class boosting classifier.", "distribution": [{"@type": "dcat:Distribution", "description": "Classification of Mars Terrain Using Multiple Data Sources", "downloadURL": "https://c3.nasa.gov/dashlink/static/media/publication/Paper_5_.pdf", "format": "PDF", "mediaType": "application/pdf", "title": "Paper 5 .pdf"}], "identifier": "DASHLINK_227", "issued": "2010-10-13", "keyword": ["ames", "dashlink", "nasa"], "landingPage": "https://c3.nasa.gov/dashlink/resources/227/", "modified": "2025-03-31", "programCode": ["026:029"], "publisher": {"@type": "org:Organization", "name": "Dashlink"}, "title": "Classification of Mars Terrain Using Multiple Data Sources"}