{
	"$schema": "https://resources.data.gov/schemas/dcat-us/v1.1/schema/catalog.json",
	"conformsTo": "https://project-open-data.cio.gov/v1.1/schema",
	"dataset": [
		{
			"accessLevel": "public",
			"bureauCode": [
				"021:04"
			],
			"contactPoint": {
				"fn": "National Transportation Library Data Curator",
				"hasEmail": "mailto:ntldatacurator@dot.gov"
			},
			"dataQuality": true,
			"description": "In this project, we devised an innovative approach to produce highly detailed orthomosaics of road surfaces, with a spatial resolution as fine as millimeters, utilizing panoramic photos obtained from a mobile camera system combined with Structure-from-Motion technology. Our method emphasizes the necessity of accurately masking out the ego-vehicle (the vehicle carrying the camera), the sky, and any moving objects (such as cars, bicycles, and pedestrians) present in the street scenes captured by the photos. We employed a combination of deep learning, image processing techniques, and manual editing to perform this masking process. It was observed that removing these objects from the images facilitates precise photo alignment and often leads to a substantial enhancement in the quality of the orthomosaics. We tested our methodology at three different sites across two different islands with contrasting traffic conditions and surrounding environments (campus, urban, and rural). We found that the resulting orthomosaics are readily applicable for GIS analysis and the assessment of road conditions and damages. Moving forward, the methodology could be refined further by automating the masking process, particularly through the integration of deep learning models. Additionally, we discovered that the timing of photo capture significantly influences the quality of the orthomosaic, with midday proving to be a preferable time window compared to early morning or late afternoon to minimize shadow effects in the orthomosaics.",
			"distribution": [
				{
					"@type": "dcat:Distribution",
					"accessURL": "https://doi.org/10.5061/dryad.4mw6m90jc",
					"format": "MD",
					"mediaType": "text/markdown",
					"description": "README document for the project. Includes title, authorship and affiliation, and .zip package information.",
					"title": "README.md"
				}
			],
			"format": "ZIP",
			"identifier": "https://doi.org/10.5061/dryad.4mw6m90jc",
			"issued": "2024-04-30",
			"keyword": [
				"Cameras",
				"Data",
				"Road construction",
				"Safety analysis",
				"Laser radar"
			],
			"landingPage": "https://doi.org/10.5061/dryad.4mw6m90jc",
			"language": [
				"en-US"
			],
			"license": "https://creativecommons.org/publicdomain/zero/1.0/legalcodee",
			"modified": "2024-04-30",
			"policyStatement": "This dataset was made public under the requirements enumerated in the U.S. Department of Transportation's 'Plan to Increase Public Access to the Results of Federally-Funded Scientific Research' Version 1.1 << https://doi.org/10.21949/1520559 >> and guidelines suggested by the DOT Public Access website << https://doi.org/10.21949/1503647  >>, in effect and current as of December 03, 2020.",
			"policyURL": "https://doi.org/10.21949/1520559 , https://doi.org/10.21949/1503647 ",
			"programCode": [
				"021:053"
			],
			"publisher": {
				"@type": "org:Organization",
				"name": "METRANS Pacific Southwest Region 9 University Transportation Center (UTC)",
				"subOrganizationOf": {
					"@type": "org:Organization",
					"name": "University of California",
					"subOrganizationOf": {
						"@type": "org:Organization",
						"name": "Office of the Assistant Secretary for Research and Technology",
						"subOrganizationOf": {
							"@type": "org:Organization",
							"name": "Department of Transportation",
							"subOrganizationOf": {
								"@type": "org:Organization",
								"name": "U.S. Government"
							}
						}
					}
				}
			},
			"references": [
				"https://doi.org/10.25554/9hxw-3y87"
			],
			"spatial": "United States, Hawaii",
			"title": "Rapid and Accurate Assessment of Road Damage by Integrating Data from Mobile Camera Systems (MCS) and Mobile LiDAR Systems (MLS) [supporting dataset]",
			"webService": null
		}
	]
}