Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

SkyScapes ­Fine-Grained Semantic Understanding of Aerial Scenes

: Azimi, Seyed M.; Henry, Crentin; Sommer, Lars; Schumann, Arne; Vig, Eleonora

Fulltext (PDF; )

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
IEEE/CVF International Conference on Computer Vision, ICCV 2019. Proceedings : 27 October - 2 November 2019, Seoul, Korea
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2019
ISBN: 978-1-7281-4803-8
ISBN: 978-1-7281-4804-5
ISBN: 978-1-7281-5023-9
International Conference on Computer Vision (ICCV) <17, 2019, Seoul>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()
deep learning; convolutional neural network; segmentation; HD-Map

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.