AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 1241 - 1251
• Main Authors: Nguyen, Huy, Nguyen, Kien, Pemasiri, Akila, Liu, Feng, Sridharan, Sridha, Fookes, Clinton
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10.06.2025
• Subjects: aerial-ground person re-identification; Benchmark testing; Cameras; Codes; Computer vision; cross-platform person re-identification; Distance measurement; Drones; Identification of persons; large-scale dataset; multi-stream network; Pattern recognition; Representation learning; Robustness; video-based person re-identification
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52734.2025.00124

We introduce AG-VPReID, a new large-scale dataset for aerial-ground video-based person re-identification (ReID) that comprises 6,632 subjects, 32,321 tracklets and over 9.6 million frames captured by drones (altitudes ranging from 15-120m), CCTV, and wearable cameras. This dataset offers a real-world benchmark for evaluating the robustness to significant viewpoint changes, scale variations, and resolution differences in cross-platform aerial-ground settings. In addition, to address these challenges, we propose AG-VPReID-Net, an end-to-end framework composed of three complementary streams: (1) an Adapted Temporal-Spatial Stream addressing motion pattern inconsistencies and facilitating temporal feature learning, (2) a Normalized Appearance Stream leveraging physics-informed techniques to tackle resolution and appearance changes, and (3) a Multi-Scale Attention Stream handling scale variations across drone altitudes. We integrate visual-semantic cues from all streams to form a robust, viewpoint-invariant whole-body representation. Extensive experiments demonstrate that AG-VPReID-Net outperforms state-of-the-art approaches on both our new dataset and existing video-based ReID benchmarks, showcasing its effectiveness and generalizability. Nevertheless, the performance gap observed on AG-VPReID across all methods underscores the dataset's challenging nature. The dataset, code and trained models are available at AG-VPReID-Net.