Unmanned Aerial Vehicles (UAVs) are becoming a valid alternative to traditional Geomatics acquisition systems, as they close the gap between higher resolution terrestrial images and the lower resolution airborne and satellite data. UAVs can be remotely controlled helicopters, fixed wind airplanes or kites. This course deals with algorithms and techniques for scene information extraction from images. Both geometric (i.e. 3D reconstruction) and semantic (i.e. 2D image understanding) aspects are described in the course.
In this course the 2D and 3D scene analysis will be explained, with focus on the use of data acquired by UAVs. The course is composed of two main parts. In the first part, the participants will focus on 2D scene analysis (semantic segmentation, object detection and tracking, modern deep learning), while during the second part, the participants will gain hands-on experience on the use of UAVs. The second part of the course will be given together with the course on “Earth Observation with UAVs”.
At the end of the course the participants will submit the output of an assignment on the dealt topics, the quality of which will contribute to the course mark.