Polygonizing Roof Segments from High-Resolution Aerial Images Using Yolov8-Based Edge Detection

2025-03-12

Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

AI Summary

To address the challenges of roof detail extraction and vectorization reconstruction in high-resolution aerial imagery, this paper proposes an edge-detection-centric end-to-end framework, departing from conventional corner-driven paradigms. We innovatively adapt the YOLOv8 Oriented Bounding Box (OBB) model for sub-pixel-accurate roof edge detection, and introduce three key components: edge-guided polygonal fitting, geometry-constrained vertex generation, and a novel Raster-Vector fusion evaluation metric. Experiments on the SGA and Melville datasets achieve raster segmentation mIoU of 0.85–1.0 and oriented IoU (ovIoU) ≈ 0.97. In vectorization accuracy—measured by Hausdorff distance and PolyS—the method significantly outperforms baseline approaches. Moreover, it demonstrates strong generalization to unseen, complex roof structures, validating robustness beyond standard configurations.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This study presents a novel approach for roof detail extraction and vectorization using remote sensing images. Unlike previous geometric-primitive-based methods that rely on the detection of corners, our method focuses on edge detection as the primary mechanism for roof reconstruction, while utilizing geometric relationships to define corners and faces. We adapt the YOLOv8 OBB model, originally designed for rotated object detection, to extract roof edges effectively. Our method demonstrates robustness against noise and occlusion, leading to precise vectorized representations of building roofs. Experiments conducted on the SGA and Melville datasets highlight the method's effectiveness. At the raster level, our model outperforms the state-of-the-art foundation segmentation model (SAM), achieving a mIoU between 0.85 and 1 for most samples and an ovIoU close to 0.97. At the vector level, evaluation using the Hausdorff distance, PolyS metric, and our raster-vector-metric demonstrates significant improvements after polygonization, with a close approximation to the reference data. The method successfully handles diverse roof structures and refines edge gaps, even on complex roof structures of new, excluded from training datasets. Our findings underscore the potential of this approach to address challenges in automatic roof structure vectorization, supporting various applications such as urban terrain reconstruction.

Problem

• Extracting roof details from aerial images using edge detection.
• Vectorizing building roofs with high precision and robustness.
• Improving roof structure reconstruction for urban terrain applications.

Innovation

• YOLOv8 OBB model for edge detection
• Geometric relationships define corners and faces
• Robust against noise and occlusion