Large-Scale Synthetic Urban Dataset for Aerial Scene Understanding

The geometric extraction and semantic understanding in bird's eye view plays an important role in cyber-physical-social systems (CPSS), because it can help human or intelligent agents (IAs) to perceive larger range of environment. Moreover, due to lack of comprehensive dataset from oblique pers...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020, Vol.8, p.42131-42140
Main Authors: Gao, Qian, Shen, Xukun, Niu, Wensheng
Format: Article
Language:English
Subjects:
Algorithms
Buildings
Datasets
Deep learning
Elevation
environment understanding
geometric extraction
Intelligent agents
Labels
large-scale urban scene
Machine learning
Rendering (computer graphics)
Roads
Scene analysis
semantic segmentation
Semantics
synthetic data set
Three-dimensional displays
Unmanned aerial vehicles
Urban areas
Virtual cameras
Virtual reality
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The geometric extraction and semantic understanding in bird's eye view plays an important role in cyber-physical-social systems (CPSS), because it can help human or intelligent agents (IAs) to perceive larger range of environment. Moreover, due to lack of comprehensive dataset from oblique perspective, fog-end deep learning algorithms for this purpose is still in blank. In this paper, we propose a novel method to generate synthetic large-scale dataset for geometric and semantic urban scene understanding from bird's eye view. There are two main steps involved, one is modeling and the other is rendering, which are processed by CityEngine and UnrealEngine4 respectively. In this way, synthetic aligned multi-model data are obtained efficiently, including spectral images, semantic labels, depth and normal maps. Specifically, terrain elevation, street graph, building style and trees distribution are all randomly generated according realistic situation, a few of handcrafted semantic labels annotated by colors spread throughout the scene, virtual cameras moved according to realistic trajectories of unmanned aerial vehicles (UAVs). For evaluation of practicability of our dataset, we manually labeled tens of aerial images downloaded from internet. And the experiment result show that, in both pure and combined mode, the dataset can improve the performance significantly.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.2976686