Road Network and Travel Time Extraction from Multiple Look Angles with Spacenet Data

  title={Road Network and Travel Time Extraction from Multiple Look Angles with Spacenet Data},
  author={Adam Van Etten and Jacob Shermeyer and Daniel Hogan and Nicholas Weir and Ryan Lewis},
  journal={IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium},
Identification of road networks and optimal routes directly from remote sensing is of critical importance to a broad array of humanitarian and commercial applications. Yet while identification of road pixels has been attempted before, estimation of route travel times from overhead imagery remains a novel problem, particularly for off-nadir overhead imagery. To this end, we extract road networks with travel time estimates from the SpaceNet MVOI dataset. Utilizing the CRESIv2 framework, we… 

Figures from this paper

The SpaceNet Multi-Temporal Urban Development Challenge
This paper details the top-5 winning approaches, as well as analysis of results that yielded a handful of interesting anecdotes such as decreasing performance with latitude.
A Maximum Independent Set Method for Scheduling Earth Observing Satellite Constellations
A new approach for solving the satellite scheduling problem by generating an infeasibility-based graph representation of the problem and finding a maximal independent set of vertices for the graph that is able to find a feasible schedule with 8% more collections in 75% less time.


City-Scale Road Extraction from Satellite Imagery v2: Road Speeds and Travel Times
  • A. V. Etten
  • Computer Science
    2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2020
This work explores road network extraction at scale with inference of semantic features of the graph, identifying speed limits and route travel times for each roadway with City-Scale Road Extraction from Satellite Imagery v2 (CRESIv2), finding that optimizing routing for travel time is feasible.
SpaceNet: A Remote Sensing Dataset and Challenge Series
It is proposed that the frequent revisits of earth imaging satellite constellations may accelerate existing efforts to quickly update foundational maps when combined with advanced machine learning techniques.
SpaceNet MVOI: A Multi-View Overhead Imagery Dataset
It is found that state of the art segmentation and object detection models struggle to identify buildings in off-nadir imagery and generalize poorly to unseen views, presenting an important benchmark to explore the broadly relevant challenge of detecting small, heterogeneous target objects in visually dynamic contexts.
The Cityscapes Dataset for Semantic Urban Scene Understanding
This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity.
Benchmark Dataset for Automatic Damaged Building Detection from Post-Hurricane Remotely Sensed Imagery
A scalable framework for creating benchmark datasets of hurricane-damaged buildings and public sharing of the resulting benchmark datasets for Greater Houston area after Hurricane Harvey in 2017 are presented.
From Satellite Imagery to Disaster Insights
A framework for change detection using Convolutional Neural Networks on satellite images which can then be thresholded and clustered together into grids to find areas which have been most severely affected by a disaster is proposed.
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources
The challenges of using deep learning for remote-sensing data analysis are analyzed, recent advances are reviewed, and resources are provided that hope will make deep learning in remote sensing seem ridiculously simple.
A Large Dataset of Object Scans
A dataset of more than ten thousand 3D scans of real objects, from shoes, mugs, and toys to grand pianos, construction vehicles, and large outdoor sculptures is created.