no code implementations • 12 Apr 2024 • Girmaw Abebe Tadesse, Caleb Robinson, Gilles Quentin Hacheme, Akram Zaytar, Rahul Dodhia, Tsering Wangyal Shawa, Juan M. Lavista Ferres, Emmanuel H. Kreike
This study explores object detection in historical aerial photographs of Namibia to identify long-term environmental changes.
no code implementations • 5 Mar 2024 • Akram Zaytar, Caleb Robinson, Gilles Q. Hacheme, Girmaw A. Tadesse, Rahul Dodhia, Juan M. Lavista Ferres, Lacey F. Hughey, Jared A. Stabach, Irene Amoke
Rare object detection is a fundamental task in applied geospatial machine learning, however is often challenging due to large amounts of high-resolution satellite or aerial imagery and few or no labeled positive samples to start with.
no code implementations • 13 Jan 2024 • Gilles Quentin Hacheme, Akram Zaytar, Girmaw Abebe Tadesse, Caleb Robinson, Rahul Dodhia, Juan M. Lavista Ferres, Stephen Wood
We conduct experiments to demonstrate the benefits of the improved weak labels generated by our method.
1 code implementation • 12 Jan 2024 • Caleb Robinson, Isaac Corley, Anthony Ortiz, Rahul Dodhia, Juan M. Lavista Ferres, Peyman Najafirad
In this work we propose a road segmentation benchmark dataset, Chesapeake Roads Spatial Context (RSC), for evaluating the spatial long-range context understanding of geospatial machine learning models and show how commonly used semantic segmentation models can fail at this task.
Ranked #1 on Road Segmentation on ChesapeakeRSC
no code implementations • 11 Dec 2023 • Anthony Cintron Roman, Jennifer Wortman Vaughan, Valerie See, Steph Ballard, Jehu Torres, Caleb Robinson, Juan M. Lavista Ferres
This paper introduces a no-code, machine-readable documentation framework for open datasets, with a focus on responsible AI (RAI) considerations.
no code implementations • 21 Jun 2023 • Caleb Robinson, Simone Fobi Nsutezo, Anthony Ortiz, Tina Sederholm, Rahul Dodhia, Cameron Birge, Kasie Richards, Kris Pitcher, Paulo Duarte, Juan M. Lavista Ferres
Rapid and accurate building damage assessments from high-resolution satellite imagery following a natural disaster is essential to inform and optimize first responder efforts.
1 code implementation • 22 May 2023 • Isaac Corley, Caleb Robinson, Rahul Dodhia, Juan M. Lavista Ferres, Peyman Najafirad
Research in self-supervised learning (SSL) with natural images has progressed rapidly in recent years and is now increasingly being applied to and benchmarked with datasets containing remotely sensed imagery.
1 code implementation • 10 Jun 2022 • Caleb Robinson, Anthony Ortiz, Hogeun Park, Nancy Lozano Gracia, Jon Kher Kaw, Tina Sederholm, Rahul Dodhia, Juan M. Lavista Ferres
Innovations in computer vision algorithms for satellite image analysis can enable us to explore global challenges such as urbanization and land use change at the planetary level.
1 code implementation • 17 Nov 2021 • Adam J. Stewart, Caleb Robinson, Isaac A. Corley, Anthony Ortiz, Juan M. Lavista Ferres, Arindam Banerjee
Deep learning methods are particularly promising for modeling many remote sensing tasks given the success of deep neural networks in similar computer vision tasks and the sheer volume of remotely sensed imagery available.
no code implementations • 29 Jun 2021 • Caleb Robinson, Anthony Ortiz, Lacey Hughey, Jared A. Stabach, Juan M. Lavista Ferres
Localizing and counting large ungulates -- hoofed mammals like cows and elk -- in very high-resolution satellite imagery is an important task for supporting ecological studies.
1 code implementation • 17 Mar 2021 • Caleb Robinson, Anthony Ortiz, Juan M. Lavista Ferres, Brandon Anderson, Daniel E. Ho
For instance, in rural settings, the pre-construction area may look similar to the surrounding environment until the building is constructed.
no code implementations • 4 Oct 2020 • Anusua Trivedi, Sreya Muppalla, Shreyaan Pathak, Azadeh Mobasher, Pawel Janowski, Rahul Dodhia, Juan M. Lavista Ferres
Bissoto et al. experimented with different bounding-box based masks and showed that deep learning models could classify skin lesion images without clinically meaningful information in the input data.