VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond

TL;DR

This paper introduces the VME dataset for vehicle detection in Middle Eastern satellite images and a comprehensive benchmark to improve model accuracy across diverse geographic regions.

Contribution

It presents a new region-specific dataset and a benchmark dataset, addressing geographic bias and enhancing vehicle detection performance globally.

Findings

Models trained on existing datasets perform poorly on Middle Eastern images.

VME dataset significantly improves detection accuracy in the Middle East.

Models trained on CDSI achieve better global car detection results.

Abstract

Detecting vehicles in satellite images is crucial for traffic management, urban planning, and disaster response. However, current models struggle with real-world diversity, particularly across different regions. This challenge is amplified by geographic bias in existing datasets, which often focus on specific areas and overlook regions like the Middle East. To address this gap, we present the Vehicles in the Middle East (VME) dataset, designed explicitly for vehicle detection in high-resolution satellite images from Middle Eastern countries. Sourced from Maxar, the VME dataset spans 54 cities across 12 countries, comprising over 4,000 image tiles and more than 100,000 vehicles, annotated using both manual and semi-automated methods. Additionally, we introduce the largest benchmark dataset for Car Detection in Satellite Imagery (CDSI), combining images from multiple sources to enhance global car detection. Our experiments demonstrate that models trained on existing datasets perform poorly on Middle Eastern images, while the VME dataset significantly improves detection accuracy in this region. Moreover, state-of-the-art models trained on CDSI achieve substantial improvements in global car detection.