2 code implementations • 6 Jul 2022 • Adam Van Etten
In this paper we explore the efficacy and drawbacks of adversarial camouflage in an overhead imagery context.
no code implementations • 23 Feb 2021 • Adam Van Etten, Daniel Hogan
Building footprints provide a useful proxy for a great many humanitarian applications.
1 code implementation • CVPR 2021 • Adam Van Etten, Daniel Hogan, Jesus Martinez-Manso, Jacob Shermeyer, Nicholas Weir, Ryan Lewis
Each building is assigned a unique identifier (i. e. address), which permits tracking of individual objects over time.
no code implementations • 4 Jun 2020 • Jacob Shermeyer, Thomas Hossler, Adam Van Etten, Daniel Hogan, Ryan Lewis, Daeil Kim
RarePlanes is a unique open-source machine learning dataset that incorporates both real and synthetically generated satellite imagery.
3 code implementations • 14 Apr 2020 • Jacob Shermeyer, Daniel Hogan, Jason Brown, Adam Van Etten, Nicholas Weir, Fabio Pacifici, Ronny Haensch, Alexei Bastidas, Scott Soenen, Todd Bacastow, Ryan Lewis
The dataset and challenge focus on mapping and building footprint extraction using a combination of these data sources.
no code implementations • 16 Jan 2020 • Adam Van Etten, Jacob Shermeyer, Daniel Hogan, Nicholas Weir, Ryan Lewis
Identification of road networks and optimal routes directly from remote sensing is of critical importance to a broad array of humanitarian and commercial applications.
no code implementations • 6 Aug 2019 • Adam Van Etten
We also test our algorithm on Google satellite imagery with OpenStreetMap labels, and find a 23% improvement over previous work.
no code implementations • 22 Apr 2019 • Adam Van Etten
We find an aggregate score of APLS = 0. 73, and a TOPO score of 0. 58 (a significant improvement over existing methods).
no code implementations • ICCV 2019 • Nicholas Weir, David Lindenbaum, Alexei Bastidas, Adam Van Etten, Sean McPherson, Jacob Shermeyer, Varun Kumar, Hanlin Tang
To address this problem, we present an open source Multi-View Overhead Imagery dataset, termed SpaceNet MVOI, with 27 unique looks from a broad range of viewing angles (-32. 5 degrees to 54. 0 degrees).
2 code implementations • 10 Dec 2018 • Jacob Shermeyer, Adam Van Etten
We also quantify the performance of object detection as a function of native resolution and object pixel size.
no code implementations • 25 Sep 2018 • Adam Van Etten
Building upon the tensorflow object detection API paper, this pipeline offers a unified approach to multiple object detection frameworks that can run inference on images of arbitrary size.
1 code implementation • 3 Jul 2018 • Adam Van Etten, Dave Lindenbaum, Todd M. Bacastow
Foundational mapping remains a challenge in many parts of the world, particularly in dynamic scenarios such as natural disasters when timely updates are critical.
Ranked #1 on Object Detection on SpaceNet 1
7 code implementations • 24 May 2018 • Adam Van Etten
We further explore resolution and object size requirements by systematically testing the pipeline at decreasing resolution, and conclude that objects only ~5 pixels in size can still be localized with high confidence.