Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Robinson, Caleb, Corley, Isaac, Ortiz, Anthony, Dodhia, Rahul, Ferres, Juan M. Lavista, Najafirad, Peyman
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911756355371008
author Robinson, Caleb
Corley, Isaac
Ortiz, Anthony
Dodhia, Rahul
Ferres, Juan M. Lavista
Najafirad, Peyman
author_facet Robinson, Caleb
Corley, Isaac
Ortiz, Anthony
Dodhia, Rahul
Ferres, Juan M. Lavista
Najafirad, Peyman
contents Fully understanding a complex high-resolution satellite or aerial imagery scene often requires spatial reasoning over a broad relevant context. The human object recognition system is able to understand object in a scene over a long-range relevant context. For example, if a human observes an aerial scene that shows sections of road broken up by tree canopy, then they will be unlikely to conclude that the road has actually been broken up into disjoint pieces by trees and instead think that the canopy of nearby trees is occluding the road. However, there is limited research being conducted to understand long-range context understanding of modern machine learning models. 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. For example, we show that a U-Net trained to segment roads from background in aerial imagery achieves an 84% recall on unoccluded roads, but just 63.5% recall on roads covered by tree canopy despite being trained to model both the same way. We further analyze how the performance of models changes as the relevant context for a decision (unoccluded roads in our case) varies in distance. We release the code to reproduce our experiments and dataset of imagery and masks to encourage future research in this direction -- https://github.com/isaaccorley/ChesapeakeRSC.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06762
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery
Robinson, Caleb
Corley, Isaac
Ortiz, Anthony
Dodhia, Rahul
Ferres, Juan M. Lavista
Najafirad, Peyman
Computer Vision and Pattern Recognition
Machine Learning
Fully understanding a complex high-resolution satellite or aerial imagery scene often requires spatial reasoning over a broad relevant context. The human object recognition system is able to understand object in a scene over a long-range relevant context. For example, if a human observes an aerial scene that shows sections of road broken up by tree canopy, then they will be unlikely to conclude that the road has actually been broken up into disjoint pieces by trees and instead think that the canopy of nearby trees is occluding the road. However, there is limited research being conducted to understand long-range context understanding of modern machine learning models. 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. For example, we show that a U-Net trained to segment roads from background in aerial imagery achieves an 84% recall on unoccluded roads, but just 63.5% recall on roads covered by tree canopy despite being trained to model both the same way. We further analyze how the performance of models changes as the relevant context for a decision (unoccluded roads in our case) varies in distance. We release the code to reproduce our experiments and dataset of imagery and masks to encourage future research in this direction -- https://github.com/isaaccorley/ChesapeakeRSC.
title Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.06762