SkyScapes – Fine-Grained Semantic Understanding of Aerial Scenes

by   Seyed Majid Azimi, et al.

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.


page 1

page 3

page 5

page 7

page 8


UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation

We present the UrbanBIS benchmark for large-scale 3D urban understanding...

The Cityscapes Dataset for Semantic Urban Scene Understanding

Visual understanding of complex urban street scenes is an enabling facto...

Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark

With the increasing interest and rapid development of methods for Ultra-...

Human-centric Relation Segmentation: Dataset and Solution

Vision and language understanding techniques have achieved remarkable pr...

A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios

Research in autonomous driving for unstructured environments suffers fro...

COFGA: Classification Of Fine-Grained Features In Aerial Images

Classification between thousands of classes in high-resolution images is...

Please sign up or login with your details

Forgot password? Click here to reset