City-Scale Road Extraction from Satellite Imagery v2: Road Speeds and Travel Times

@article{Etten2020CityScaleRE,
  title={City-Scale Road Extraction from Satellite Imagery v2: Road Speeds and Travel Times},
  author={A. V. Etten},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={1775-1784}
}
  • A. V. Etten
  • Published 2020
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
Automated road network extraction from remote sensing imagery remains a significant challenge despite its importance in a broad array of applications. [...] Key Result Metric scores decrease by only 4% on large graphs when using travel time rather than geometric distance for edge weights, indicating that optimizing routing for travel time is feasible with this approach.Expand
Cloud Based Automatic Building and Road Extraction from Large Scale Open Geospatial Datasets
We author Jupyter notebooks to develop deep learning models on Amazon SageMaker instance. These models automatically extract building footprints and road networks from open geospatial datasets. TheExpand
RoadRouter: Multi-Task Learning of Road Network Extraction with Graph Representation
TLDR
This work proposes the pixel-wise orientation CRF specific for bridging the fragmented road segments, and formalizes an image transformation protocol to parse the topology from the road segmentation. Expand
Semantic Labeling of Large-Area Geographic Regions Using Multiview and Multidate Satellite Images and Noisy OSM Training Labels
  • Bharath Comandur, A. Kak
  • Computer Science, Engineering
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • 2021
We present a novel multiview training framework and convolutional neural network (CNN) architecture for combining information from multiple overlapping satellite images and noisy training labelsExpand
Dynamic Traffic Modeling From Overhead Imagery
  • Scott Workman, N. Jacobs
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
This work proposes an automatic approach for generating dynamic maps of traffic speeds using convolutional neural networks, which operates on overhead imagery, is conditioned on location and time, and outputs a local motion model that captures likely directions of travel and corresponding travel speeds. Expand
Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review - Part II: Applications
TLDR
The main finding is that CNNs are in an advanced transition phase from computer vision to EO, and it is argued that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. Expand
Multimodal Urban Remote Sensing Image Registration Via Roadcross Triangular Feature
  • Kun Yu, Xiao Zheng, +6 authors Jie Ma
  • Computer Science
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • 2021
TLDR
The qualitative and quantitative experimental results show that the proposed method significantly outperforms other state-of-the-art methods, even when others completely fail to achieve the registration task of cross-modal images, the method still maintains good robustness and matching efficiency. Expand
Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review-Part I: Evolution and Recent Trends
TLDR
An overview of the evolution of DL with a focus on image segmentation and object detection in convolutional neural networks (CNN) starts in 2012, when a CNN set new standards in image recognition, and lasts until late 2019. Expand
Earth transformed: detailed mapping of global human modification from 1990 to 2017
Abstract. Data on the extent, patterns, and trends of human land use are critically important to support global and national priorities for conservation and sustainable development. To inform theseExpand
Can real-time Artificial Intelligence techniques be applied to Synthetic EnvironmentsCan real-time Artificial Intelligence techniques be applied to Synthetic Environments
The increasing proliferation of source data poses a significant challenge to the capabilities of Synthetic Environment (SE) generation pipelines to transform this data with the necessary agility,Expand
Road Network and Travel Time Extraction from Multiple Look Angles with Spacenet Data
TLDR
The combined model exhibits greatly improved robustness over angle-specific models, despite the very different appearance of road networks at extremely oblique off-nadir angles versus images captured from directly overhead. Expand

References

SHOWING 1-10 OF 32 REFERENCES
City-scale Road Extraction from Satellite Imagery
TLDR
This work creates an algorithm to extract road networks directly from imagery over city-scale regions, which can subsequently be used for routing purposes, and demonstrates that one can use the extracted road network for any number of applications, such as optimized routing. Expand
RoadTracer: Automatic Extraction of Road Networks from Aerial Images
TLDR
This work proposes RoadTracer, a new method to automatically construct accurate road network maps from aerial images that uses an iterative search process guided by a CNN-based decision function to derive the road network graph directly from the output of the CNN. Expand
Enhancing Road Maps by Parsing Aerial Images Around the World
TLDR
This paper proposes to exploit aerial images in order to enhance freely available world maps using OpenStreetMap using a Markov random field parameterized in terms of the location of the road-segment centerlines as well as their width to enable very efficient inference and returns only topologically correct roads. Expand
Unthule: An Incremental Graph Construction Process for Robust Road Map Extraction from Aerial Images
TLDR
This work proposes a novel approach, Unthule, to construct highly accurate road maps from aerial images, which uses an incremental search process guided by a CNN-based decision function to derive the road network graph directly from the output of the CNN. Expand
Automatic extraction of road network from aerial images
TLDR
An automatic method to extract road network from high-resolution aerial images through the use of a consecutive linear features detection algorithm that is mainly based on the three following steps. Expand
A New Approach to Urban Road Extraction Using High-Resolution Aerial Image
TLDR
In this study, a knowledge-based method is established and proposed; this method incorporates the spatial texture feature into urban road extraction and results show that the completeness, correctness, and quality of the results could reach approximately 94%, 90% and 86% respectively, indicating that the proposed method is effective forurban road extraction. Expand
DeepRoadMapper: Extracting Road Topology from Aerial Images
TLDR
This paper takes advantage of the latest developments in deep learning to have an initial segmentation of the aerial images and proposes an algorithm that reasons about missing connections in the extracted road topology as a shortest path problem that can be solved efficiently. Expand
A Higher-Order CRF Model for Road Network Extraction
TLDR
A novel CRF formulation for road labeling is developed, in which the prior is represented by higher-order cliques that connect sets of super pixels along straight line segments, which significantly improves both the per-pixel accuracy and the topological correctness of the extracted roads. Expand
A Gibbs Point Process for Road Extraction from Remotely Sensed Images
TLDR
A new method for the extraction of roads from remotely sensed images is proposed, under the assumption that roads form a thin network in the image, by connected line segments by minimizing an energy function. Expand
Machine learning for aerial image labeling
Information extracted from aerial photographs has found applications in a wide range of areas including urban planning, crop and forest management, disaster relief, and climate modeling. At present,Expand
...
1
2
3
4
...