IGN 5-2
Wildlife big data: Processing images from large scale photo surveys with eMammal

Tuesday, August 11, 2015
345, Baltimore Convention Center
Tavis Forrester, Conservation and Research Center, Smithsonian Institution - National Zoological Park, Front Royal, VA
William J. McShea, Conservation Ecology Center, Smithsonian Conservation Biology Institute at the National Zoological Park, Front Royal, VA
Robert Costello, National Outreach Program, Smithsonian Institution - National Museum of Natural History
Roland W. Kays, North Carolina Museum of Natural Sciences, Raleigh, NC
Modern motion sensitive cameras, or camera traps, are non-invasive survey tools that produce a photo “voucher” for each observation and can be used at large scales relatively cheaply and easily. However, they also produce a flood of data and images that can overwhelm researchers. To harness the power of big data for wildlife the Smithsonian has built a workflow that includes custom software, computer vision, cloud based workflows, and expert data review. The process quickly moves photos and data from the field to the eMammal repository and aggregates data from multiple projects to be used for research and conservation.