We work collectively by engaging groups of volunteers for collection of geospatial data and crowdsourcing of placenames. Under the current pilot, methods used are being developed and optimized by the core group prior to wider application. The current approach for collection of geospatial data is by annotation of features as polygons on satellite images using Google Earth. Volunteers are allocated grid squares to annotate using standardized methods and following a set of predefined rules. The polygons are exported as a KML file and sent to a validation team who assess the quality and accuracy of the annotation against a set of quality criteria and approves or rejects the completed grid for inclusion in the dataset. Any rejected grids are reannotated and reassessed. Once, complete, the next step will be to label the polygons with the names of communities. We plan to do this through crowdsourcing.
How We Work
We support communicable disease control programs under the Ministry of Health and Family Welfare (MOHFW) in Bangladesh through collection of high quality, high resolution geospatial data. The initial goal is to map communities in selected rural areas. Once, complete, the next stap will be to label the polygons with the names of communities through crowdsourcing.