L2RW
收藏资源简介:
L2RW是一个旨在模拟真实世界隐私保护下的可见光-红外行人重识别场景的基准数据集。该数据集由南京信息工程大学计算机科学与技术学院和University of Oulu中心for Machine Vision and Signal Analysis共同创建,通过设计三种协议(相机独立、实体独立和实体共享)来模拟不同隐私约束场景。数据集整合了多个现有数据集,以交叉域方式评估,以模拟真实世界场景,解决隐私保护和所有权问题,适用于可见光-红外行人重识别技术研究。
L2RW is a benchmark dataset designed to simulate real-world privacy-preserving visible-infrared person re-identification (ReID) scenarios. This dataset was jointly created by the School of Computer Science and Technology, Nanjing University of Information Science and Technology, and the Center for Machine Vision and Signal Analysis, University of Oulu. Three protocols, namely camera-independent, identity-independent and identity-shared, are designed to simulate different privacy-constrained scenarios. The dataset integrates multiple existing datasets and conducts cross-domain evaluations to simulate real-world scenarios, addressing issues related to privacy protection and data ownership, and is suitable for research on visible-infrared person re-identification technologies.

- 1From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification南京信息工程大学计算机科学与技术学院, University of Oulu中心 for Machine Vision and Signal Analysis · 2025年



