SkyScapes - Fine-Grained Semantic Understanding of Aerial Scenes
| Autor: | Arne Schumann, Eleonora Vig, Lars Sommer, Corentin Henry, Seyed Majid Azimi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Feature extraction 0211 other engineering and technologies Computer Science - Computer Vision and Pattern Recognition Convolutional Neural Network 02 engineering and technology computer.software_genre Edge detection Segmentation 0202 electrical engineering electronic engineering information engineering Aerial image 021101 geological & geomatics engineering Photogrammetrie und Bildanalyse business.industry Deep learning Vegetation Object (computer science) 020201 artificial intelligence & image processing Artificial intelligence Data mining business HD-Map computer |
| Zdroj: | ICCV |
| Popis: | Understanding the complex urban infrastructure with centimeter-level accuracy is essential for many applications from autonomous driving to mapping, infrastructure monitoring, and urban management. Aerial images provide valuable information over a large area instantaneously; nevertheless, no current dataset captures the complexity of aerial scenes at the level of granularity required by real-world applications. To address this, we introduce SkyScapes, an aerial image dataset with highly-accurate, fine-grained annotations for pixel-level semantic labeling. SkyScapes provides annotations for 31 semantic categories ranging from large structures, such as buildings, roads and vegetation, to fine details, such as 12 (sub-)categories of lane markings. We have defined two main tasks on this dataset: dense semantic segmentation and multi-class lane-marking prediction. We carry out extensive experiments to evaluate state-of-the-art segmentation methods on SkyScapes. Existing methods struggle to deal with the wide range of classes, object sizes, scales, and fine details present. We therefore propose a novel multi-task model, which incorporates semantic edge detection and is better tuned for feature extraction from a wide range of scales. This model achieves notable improvements over the baselines in region outlines and level of detail on both tasks. Accepted in IEEE ICCV19 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|