Issue link: https://geospatial.trimble.com/en/resources/i/1397023
Each year thousands of people are forced away from their homes by natural disasters or political unrest. They often end up in refugee camps supported by non- governmental organizations (NGOs) that provide food, shelter and medical assistance. To manage their operations efficiently, NGOs and other agencies need to know how many people are in a given camp. overview Location AUSTRIA TRANSFORMING THE WAY THE WORLD WORKS TRANSFORMING THE WAY THE WORLD WORKS Large refugee camps can hold more than one hundred thousand people. NGOs such as Doctors Without Borders (DWB) rely on population data in allocating resources to prevent sickness and malnutrition in the camps. But it is difficult to acquire accurate data on camp populations. While imagery from satellites and aircraft can help, manually extracting population information from aerial photos is slow and expensive. DWB teamed with experts at the University of Salzburg's Department of Geoinformatics (Z_GIS) to find a better approach. "It's essential to develop accurate data quickly and to repeat the measurements as needed," said Dr. Stefan Lang, division head and associate professor at Z_GIS. "Once we capture a particular area then we can do recursive monitoring. It's important to have tools that we can use to repeat our analysis and not start from scratch." AUTOMATED ANALYSIS Z_GIS is developing automated approaches to extract population information from satellite images of refugee camps. Z_GIS obtains very high-resolution (VHR) satellite imagery from commercial providers and processes the photos with Trimble eCognition software to develop estimates on the number of physical dwelling units in a camp. Teams can then add ground data on the average number of residents per dwelling, enabling them to estimate the size and distribution of the population. The process can be repeated to quantify population change and movement within a camp. Because camps can change rapidly during a crisis, the ability to repeat the population analysis quickly is important. eCognition uses an approach called Object- Based Image Analysis (OBIA) to identify and classify features in an image. According to Dr. Dirk Tiede, one of Lang's colleagues at Z_GIS, OBIA offers greater flexibility and efficiency than earlier pixel-based analysis techniques. Using eCognition rule-sets, Tiede can effectively train