Abstract
BACKGROUND: Despite availability of valuable ecological data in published thematic maps, manual methods to transfer published maps to a more accessible digital format are time-intensive. Application of object-based image analysis makes digitization faster. METHODS: Using object-based image analysis followed by random forests classification, we rapidly digitized choropleth maps of white-tailed deer (Odocoileus virginianus) densities in the conterminous US during 1982 and 2001 to 2005 (hereafter, 2003), allowing access to deer density information stored in images. RESULTS: The digitization process took about one day each per deer density map, of which about two hours was computer processing time, which will differ due to factors such as resolution and number of objects. Deer were present in 4.75 million km(2) (60% of the area) and 5.56 million km(2) (70%) during 1982 and 2003, respectively. Population and density in areas with deer presence were 17.15 million and 3.6 deer/km(2) during 1982 and 29.93 million and 5.4 deer/km(2) during 2003. Greatest densities were 7.2 deer/km(2) in Georgia during 1982 and 14.6 deer/km(2) in Wisconsin during 2003. Six states had deer densities ≥9.8 deer/km(2) during 2003. Colorado, Idaho, and Oregon had greatest increases in population and area of deer presence, and deer expansion is likely to continue into western states. Error in these estimates may be similar to error resulting from differential reporting by state agencies. Deer densities likely are within historical levels in most of the US. DISCUSSION: This method rapidly reclaimed informational value of deer density maps, enabling greater analysis, and similarly may be applied to digitize a variety of published maps to geographic information system layers, which permit greater analysis.