Aerial-Ground Person Re-ID
Authors:
- Huy NguyenHNHuy Nguyen
- Kien NguyenKNKien Nguyen
- Sridha SridharanSSSridha Sridharan
- Clinton FookesCFClinton Fookes
Preprint
Abstract
Person re-ID matches persons across multiple non-overlapping cameras. Despite the increasing deployment of airborne platforms in surveillance, current existing person re-ID benchmarks' focus is on ground-ground matching and very limited efforts on aerial-aerial matching. We propose a new benchmark dataset - AG-ReID, which performs person re-ID matching in a new setting: across aerial and ground cameras. Our dataset contains 21,983 images of 388 identities and 15 soft attributes for each identity. The data was collected by a UAV flying at altitudes between 15 to 45 meters and a ground-based CCTV camera on a university campus. Our dataset presents a novel elevated-viewpoint challenge for person re-ID due to the significant difference in person appearance across these cameras. We propose an explainable algorithm to guide the person re-ID model's training with soft attributes to address this challenge. Experiments demonstrate the efficacy of our method on the aerial-ground person re-ID task. The dataset will be published and the baseline codes will be open-sourced to facilitate research in this area.Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- FastReID: A Pytorch Toolbox for General Instance Re-identification2023
- The P-DESTRE: A Fully Annotated Dataset for Pedestrian Detection, Tracking, and Short/Long-Term Re-Identification From Aerial DevicesIEEE Transactions on Information Forensics and Security, 2020
- Person Re-Identification in Aerial ImageryIEEE Transactions on Multimedia, 2020