Signal from Space: Detecting Schools and Towers to Bridge the Digital Divide

• URL: http://arxiv.org/abs/2607.02724v1
• Date: Thu, 02 Jul 2026 19:19:39 GMT
• Title: Signal from Space: Detecting Schools and Towers to Bridge the Digital Divide
• Abstract summary: The Giga Initiative aims to connect every school to the internet, but doing so at scale requires efficient methods to map schools and assess surrounding connectivity infrastructure.<n>We propose a scalable, vision-only framework that uses high-resolution satellite imagery and transfer learning to address both tasks simultaneously.
• Score: 38.087411856667465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable internet access is essential for modern education, yet millions of school-aged children especially in developing regions remain offline due to unconnected schools. The Giga Initiative aims to connect every school to the internet, but doing so at scale requires efficient methods to map schools and assess surrounding connectivity infrastructure without relying on sparse or noisy third-party datasets. In this work, we propose a scalable, vision-only framework that uses high-resolution satellite imagery and transfer learning to address both tasks simultaneously. By adapting pre-trained object detection models to new geographical regions with minimal labeled data, we detect schools and cell towers directly from space. We then analyze the spatial relationship between detected schools and nearby towers as a proxy for connectivity availability. This purely imagery-driven pipeline enables large-scale infrastructure mapping, reduces dependency on auxiliary data, and supports data-driven prioritization of connectivity investments in underserved areas. Our approach is demonstrated on real satellite imagery from Lesotho, showing strong performance across this region.

Related papers

• Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning [49.671779378073886]
  We propose a weakly supervised framework for school detection from aerial imagery.<n>Our method is specifically designed for low-data regimes, where manual annotations are extremely scarce.<n>All models, training code and auto-labeled data will be publicly released to foster future research and real-world impact.
  arXiv  Detail & Related papers  (2026-05-05T16:51:28Z)
• A Multi-tiered Human-in-the-loop Approach for Interactive School Mapping Using Earth Observation and Machine Learning [2.0898079211815452]
  This paper presents a multi-tiered human-in-the-loop framework for interactive school mapping.<n>It is designed to improve the accuracy and completeness of educational facility records in developing regions.
  arXiv  Detail & Related papers  (2025-10-31T13:15:22Z)
• GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization [70.65458151146767]
  Cross-view localization is crucial for large-scale outdoor applications like autonomous navigation and augmented reality.<n>Existing methods often rely on fully supervised learning, which requires costly ground-truth pose annotations.<n>We propose GeoDistill, a framework that uses teacher-student learning with Field-of-View (FoV)-based masking.
  arXiv  Detail & Related papers  (2025-07-15T03:00:15Z)
• Large-scale School Mapping using Weakly Supervised Deep Learning for Universal School Connectivity [0.0]
  We propose a cost-effective, scalable approach to locating schools in high-resolution satellite images using weakly supervised deep learning techniques.<n>Our best models, which combine vision transformers and convolutional neural networks, achieve AUPRC values above 0.96 across 10 pilot African countries.
  arXiv  Detail & Related papers  (2024-12-19T14:06:56Z)
• Semantic Segmentation of Vegetation in Remote Sensing Imagery Using Deep Learning [77.34726150561087]
  We propose an approach for creating a multi-modal and large-temporal dataset comprised of publicly available Remote Sensing data. We use Convolutional Neural Networks (CNN) models that are capable of separating different classes of vegetation.
  arXiv  Detail & Related papers  (2022-09-28T18:51:59Z)
• Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World [83.36195426897768]
  We propose VRVO, a novel framework for retrieving the absolute scale from virtual data. We first train a scale-aware disparity network using both monocular real images and stereo virtual data. The resulting scale-consistent disparities are then integrated with a direct VO system.
  arXiv  Detail & Related papers  (2022-03-11T01:51:54Z)
• Geography-Aware Self-Supervised Learning [79.4009241781968]
  We show that due to their different characteristics, a non-trivial gap persists between contrastive and supervised learning on standard benchmarks. We propose novel training methods that exploit the spatially aligned structure of remote sensing data. Our experiments show that our proposed method closes the gap between contrastive and supervised learning on image classification, object detection and semantic segmentation for remote sensing.
  arXiv  Detail & Related papers  (2020-11-19T17:29:13Z)
• Utilizing Satellite Imagery Datasets and Machine Learning Data Models to Evaluate Infrastructure Change in Undeveloped Regions [0.0]
  This research aims to allow automated monitoring for largescale infrastructure projects, such as railways, to determine reliable metrics that define and predict the direction construction initiatives could take. By utilizing photogrammetric techniques on available satellite data to create 3D Meshes and Digital Surface Models (DSM) we hope to effectively predict transport routes.
  arXiv  Detail & Related papers  (2020-09-01T02:11:14Z)
• Boundary Regularized Building Footprint Extraction From Satellite Images Using Deep Neural Network [6.371173732947292]
  We propose a novel deep neural network, which enables to jointly detect building instance and regularize noisy building boundary shapes from a single satellite imagery. Our model can accomplish multi-tasks of object localization, recognition, semantic labelling and geometric shape extraction simultaneously.
  arXiv  Detail & Related papers  (2020-06-23T17:24:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.