Description
Earths surface is subject to constant change due to natural phenomena or human intervention. The process of identifying those changes is called “change detection” (CD) and is a core problem in environmental monitoring, disaster monitoring, city expansion and land cover.In the field of geoinformatics, working with two-dimensional (2D) data is popular due to their underlying, well-organized raster based structure. However, raster data comes with significant drawbacks for object based change detection. For example, the object detection that precedes the change detection in 2D data is usually subject to uncertainties due to perspective and atmospheric effects. Another shortcoming of 2D change identification is the lack of possibilities to identify changes in height as 2D data does not provide elevation information directly. At the same time, studies on the use of deep learning for change detection tasks which also take the third spatial dimension into account, are not sufficiently explored. Hence, the inner workings of systems that are able to segment objects in aerial- and satellite-imagery are not clear as well. This is where the explainability of AI-systems comes into play.
This PhD project aims to fill the gap between tasks of object based detection with two- and three-dimensional data and explain the inner workings of systems and the degree three-dimensional data is utilized for segmentation tasks.
| Period | 3 Feb 2021 → … |
|---|