DriveFace: A Cross-Spectral Through-Glass Face Dataset for On-the-Move Vehicular Border Control

2026-07-15

AI Summary

Existing datasets fail to capture the real-world challenges of face recognition in cross-border mobile vehicle inspection, such as motion blur, illumination variations, occlusions, and cross-spectral registration discrepancies. To address this gap, this work introduces the first cross-spectral face dataset tailored to this scenario, comprising paired samples of near-infrared in-vehicle videos—captured through car windows of moving vehicles—and pre-enrolled visible-spectrum images acquired via smartphones. This dataset establishes a benchmark for contactless, long-range border inspection face recognition and enables end-to-end model evaluation. Baseline experiments demonstrate a significant performance drop of state-of-the-art models on this dataset, confirming the complexity of the scenario and underscoring the need for specialized algorithmic solutions.

Abstract

The continuous growth in cross-border mobility places increasing pressure on existing border control infrastructures, motivating on-the-move biometric authentication, in which travellers are identified directly inside their vehicles at checkpoints. Face recognition is well-suited to this setting, as it can be acquired passively and at a distance. Its development, however, is hindered by the lack of representative datasets: existing benchmarks are collected in controlled environments and do not capture the challenges inherent to vehicular acquisition, including motion blur, variable illumination, occlusions, and cross-spectral enrollment. To address this gap, we introduce a dataset for on-the-move face recognition in border-control scenarios, comprising NIR vehicle-crossing videos paired with smartphone-based pre-enrollment data. Baseline evaluations with state-of-the-art models show clear performance limitations under these realistic conditions, highlighting the need for dedicated methods to advance the field.

Problem

• cross-spectral
• through-glass
• on-the-move
• face recognition
• vehicular border control

Innovation

• cross-spectral face recognition
• through-glass imaging
• on-the-move biometrics
• vehicular border control
• NIR-visible dataset