A Weak Supervision Learning Approach Towards an Equitable Mobility Estimation

TL;DR

This paper introduces a weak supervision method to estimate parking lot occupancy from low-resolution satellite images, reducing the need for costly high-res data and enabling scalable urban mobility analysis in underserved regions.

Contribution

It presents a novel weak supervision framework that uses coarse labels to train a comparison model for occupancy estimation, applicable in low-resource settings.

Findings

Achieved an AUC of 0.92 on large parking lots.

Reduced reliance on high-resolution imagery.

Demonstrated potential for scalable urban mobility analysis.

Abstract

The scarcity and high cost of labeled high-resolution imagery have long challenged remote sensing applications, particularly in low-income regions where high-resolution data are scarce. In this study, we propose a weak supervision framework that estimates parking lot occupancy using 3m resolution satellite imagery. By leveraging coarse temporal labels -- based on the assumption that parking lots of major supermarkets and hardware stores in Germany are typically full on Saturdays and empty on Sundays -- we train a pairwise comparison model that achieves an AUC of 0.92 on large parking lots. The proposed approach minimizes the reliance on expensive high-resolution images and holds promise for scalable urban mobility analysis. Moreover, the method can be adapted to assess transit patterns and resource allocation in vulnerable communities, providing a data-driven basis to improve the well-being of those most in need.