DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

SkyScapes - Fine-Grained Semantic Understanding of Aerial Scenes

Azimi, Seyedmajid and Henry, Corentin and Sommer, Lars and Schumann, Arne and Vig, Eleonora (2019) SkyScapes - Fine-Grained Semantic Understanding of Aerial Scenes. In: 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019, pp. 1-11. IEEE. ICCV 2019, 2019-10-27 - 2019-11-02, Seoul, Korea. doi: 10.1109/ICCV.2019.00749.

[img] PDF


Understanding the complex urban infrastructure withcentimeter-level accuracy is essential for many applicationsfrom autonomous driving to mapping, infrastructure monitoring, and urban management. Aerial images providevaluable information over a large area instantaneously; nevertheless, no current dataset captures the complexityof aerial scenes at the level of granularity required byreal-world applications. To address this, we introduceSkyScapes, an aerial image dataset with highly-accurate,fine-grained annotations for pixel-level semantic labeling.SkyScapes provides annotations for 31 semantic categoriesranging from large structures, such as buildings, roadsand vegetation, to fine details, such as 12 (sub-)categories of lane markings. We have defined two main tasks onthis dataset: dense semantic segmentation and multi-classlane-marking prediction. We carry out extensive exper-iments to evaluate state-of-the-art segmentation methodson SkyScapes. Existing methods struggle to deal with thewide range of classes, object sizes, scales, and fine detailspresent. We therefore propose a novel multi-task model,which incorporates semantic edge detection and is bettertuned for feature extraction from a wide range of scales.This model achieves notable improvements over the base-lines in region outlines and level of detail on both tasks.

Item URL in elib:https://elib.dlr.de/131251/
Document Type:Conference or Workshop Item (Speech, Poster)
Title:SkyScapes - Fine-Grained Semantic Understanding of Aerial Scenes
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Azimi, SeyedmajidUNSPECIFIEDhttps://orcid.org/0000-0002-6084-2272UNSPECIFIED
Henry, CorentinUNSPECIFIEDhttps://orcid.org/0000-0002-4330-3058UNSPECIFIED
Journal or Publication Title:17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
Page Range:pp. 1-11
Keywords:Deep learning, Convolutional Neural Network, Segmentation, HD-Map
Event Title:ICCV 2019
Event Location:Seoul, Korea
Event Type:international Conference
Event Start Date:27 October 2019
Event End Date:2 November 2019
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Road Transport
DLR - Research area:Transport
DLR - Program:V ST Straßenverkehr
DLR - Research theme (Project):V - NGC KoFiF (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > Photogrammetry and Image Analysis
Deposited By: Bahmanyar, Gholamreza
Deposited On:26 Nov 2019 15:01
Last Modified:24 Apr 2024 20:34

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.