This thesis presents a method for extracting structured roof surfaces from remote sensing images. It achieved this by combining semantic segmentation with polygon-based refinement, which allows rooftop boundaries to be described more accurately using line and shape information. The method includes three main stages: (1) using an instance segmentation model to detect and classify rooftop areas; (2) generating polygonal candidates for plannar roof regions based on detected line features; and (3) optimizing label assignments through a Markov Random Field (MRF) model, which integrates prediction confidence with the spatial relationships between polygons. Experiments on benchmark datasets show that this approach improves the accuracy and consistency of rooftop segmentation while reducing incorrect detections. The system is modular and flexible, making it suitable for applications that require reliable roof structure analysis in urban environments.

This project presents an indoor navigation system based on image matching, aiming to address the challenges of localization and navigation in indoor environments. The system utilizes Simultaneous Localization and Mapping (SLAM) technology to capture high-resolution images and point cloud data, combined with the VGG16 model from Convolutional Neural Networks (CNN) for image processing, feature extraction, and matching.

In our research, we conducted experiments at the Faculty of Architecture and the Built Environment of Delft University of Technology, using a SLAM scanner to obtain 360-degree panoramic images and point cloud data of the indoor environment. Through cube mapping projection, we converted the panoramic images into six planar views, selecting the front, right, and left views as positioning references. Additionally, we reconstructed the indoor environment structure and designed node networks for positioning and navigation.

The technical architecture of this system comprises three main components: VGG16-based image feature extraction, cosine similarity-based image matching, and DBSCAN algorithm for location clustering. Through this method, the system can achieve real-time localization results after image capture and provide users with optimal paths using the A* navigation algorithm.

Experimental results show that when using single image matching, the system's room localization accuracy reaches 74.65\%. When employing multiple image matching and DBSCAN clustering methods, the accuracy significantly improves. In our final evaluation involving 116 positions, the system successfully matched 111 of these positions to their correct rooms, achieving a localization accuracy of 95.69\%.

This research not only provides an innovative solution for indoor positioning and navigation but also points the way for future research, including support for multi-floor navigation, enhancing CNN model performance, and automating building processing. This technology has the potential for widespread application in complex indoor environments such as large buildings, conference centers, and university campuses, offering users accurate, real-time positioning and navigation services.