Semantic Segmentation of RGB-Z Aerial Imagery Using Convolutional Neural Networks

Semantic segmentation (or pixel-level classification) of remotely sensed imagery has shown to be useful for applications in fields as mapping of land cover, object detection, change detection and land-use analysis. Deep learning algorithms called convolutional neural networks (CNNs) have shown to outperform traditional computer vision and...

3D city modeling for automated verification of safety compliance rules

During the MSc Geomatics program at the Delft University of Technology, the students execute a synthesis project. The project aims to investigate a real-world problem and to bring students and teachers/supervisors in cooperation with a company or public agency (e.g. municipalities). The students are challenged to use their existing knowledge in...