Search papers, labs, and topics across Lattice.
This paper introduces the DriveFace dataset, specifically designed for on-the-move face recognition in vehicular border control, addressing the limitations of existing datasets that fail to capture real-world challenges like motion blur and variable lighting. The dataset includes near-infrared (NIR) vehicle-crossing videos paired with smartphone-based pre-enrollment data, providing a more representative benchmark for evaluating biometric authentication systems in dynamic environments. Baseline evaluations reveal significant performance limitations of state-of-the-art models under these conditions, underscoring the necessity for tailored approaches in this domain.
Real-world conditions expose critical performance gaps in face recognition systems, with state-of-the-art models struggling under the challenges of motion blur and occlusion.
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.
