Atlas Urban Index: A VLM-Based Approach for Spatially and Temporally Calibrated Urban Development Monitoring

TL;DR

The paper presents the Atlas Urban Index (AUI), a novel satellite imagery-based metric leveraging Vision-Language Models to accurately monitor urban development over time, overcoming limitations of traditional indices like NDBI.

Contribution

It introduces a VLM-based approach for spatially and temporally calibrated urban development measurement using Sentinel-2 data, with strategies to improve reliability and stability.

Findings

AUI outperforms NDBI in qualitative experiments on Bangalore.

The method effectively mitigates atmospheric noise, seasonal variation, and cloud cover.

AUI provides more consistent and reliable urban development scores.

Abstract

We introduce the {\em Atlas Urban Index} (AUI), a metric for measuring urban development computed using Sentinel-2 \citep{spoto2012sentinel2} satellite imagery. Existing approaches, such as the {\em Normalized Difference Built-up Index} (NDBI), often struggle to accurately capture urban development due to factors like atmospheric noise, seasonal variation, and cloud cover. These limitations hinder large-scale monitoring of human development and urbanization. To address these challenges, we propose an approach that leverages {\em Vision-Language Models }(VLMs) to provide a development score for regions. Specifically, we collect a time series of Sentinel-2 images for each region. Then, we further process the images within fixed time windows to get an image with minimal cloud cover, which serves as the representative image for that time window. To ensure consistent scoring, we adopt two strategies: (i) providing the VLM with a curated set of reference images representing different levels of urbanization, and (ii) supplying the most recent past image to both anchor temporal consistency and mitigate cloud-related noise in the current image. Together, these components enable AUI to overcome the challenges of traditional urbanization indices and produce more reliable and stable development scores. Our qualitative experiments on Bangalore suggest that AUI outperforms standard indices such as NDBI.