Crowdsourcing the analysis of VHR aerial photographs of wild animals
© 2014 EPFL
Very High Resolution images produced in the context of the SAVMAP project funded by CODEV and elaborated by the Kuzikus Wildlife Reserve, the GIS Lab (LASIG) at EPFL, the Polytechnic of Namibia, and Drone Adventures will be used to protect wildlife in Namibia. Rangers want to know how many animals and what kinds are roaming about their wildlife reserve. To this end partners are interested in experimenting with crowdsourcing to make sense of this aerial imagery and raise awareness about wildlife in Namibia.
SAVMAP (Near real-time ultrahigh-resolution imaging from unmanned aerial vehicles for sustainable land use management and biodiversity conservation in semi-arid savanna under regional and global change) is an innovative transdisciplinary initiative whose goal is to develop a valuable monitoring tool for both sustainable land-use management and rare species conservation (black rhinoceros, see Visual) in semi-arid savanna in Namibia. SAVMAP uses near real-time ultrahigh-resolution photographic imaging facilitated by unmanned aerial vehicles (UAVs).
SAVMAP actions are described on the Drone Adventures' blog :
- Nature conservation mapping in Namibia
- Drones in Namibia: pictures, maps and videos
Among the different issues addressed, Rhino poaching is a growing problem. This criminal activity threatens to extinguish several rhino species in the short term. Rhino monitoring is thus important for their protection, and using digital maps in combination with MicroMappers to trace aerial images of rhinos could greatly improve rhino monitoring efforts. The pilot project starting now and described hereunder serves two goals. First, trying out the new Micromappers' Aerial Clicker (specific app) for future humanitarian deployments, and 2) assessing whether crowdsourcing can be used to correctly identify wild animals. Of course, as rhino poaching continues, the location of rhinos on the wildlife map will obviously not be included.
More information on this pilot crowdsourcing project on the :