构建首个多时段高空无人机行人重识别压力测试数据集
DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person Recognition
- 设计多时段、跨场景的无人机航拍行人数据集，模拟真实复杂条件
- 现有顶尖模型在该数据集上检测准确率下降80%，重识别排名1性能降超70%
- 适合评估长期行人识别与鲁棒性，支持检测/跟踪/动作等多任务研究
行人重识别（ReID）技术在受控地面环境下表现良好，但在真实复杂场景中严重失效。这主要源于分辨率、视角、尺度、遮挡及服装或会话漂移带来的极端数据变异性。现有公开数据集未充分涵盖此类变异性，制约了技术进步。本文提出DetReIDX，一个大规模空中-地面行人数据集，专为真实场景下的ReID压力测试而设计。该数据集包含509个身份、超过1300万边界框，采集自三大洲七所大学校园，无人机飞行高度5.8至120米。关键创新在于：每位目标至少在不同日期被记录两次，且存在服装、光照和位置变化，可真实评估长期行人重识别能力。数据还标注了16项软生物特征及多任务标签（检测、跟踪、ReID、动作识别）。实验表明，当暴露于DetReIDX条件时，当前最先进方法在检测任务上准确率下降高达80%，在Rank-1 ReID性能下降超过70%。数据集、标注与官方评估协议已公开：https://www.it.ubi.pt/DetReIDX/
原文摘要 · Abstract (English)
Person reidentification (ReID) technology has been considered to perform relatively well under controlled, ground-level conditions, but it breaks down when deployed in challenging real-world settings. Evidently, this is due to extreme data variability factors such as resolution, viewpoint changes, scale variations, occlusions, and appearance shifts from clothing or session drifts. Moreover, the publicly available data sets do not realistically incorporate such kinds and magnitudes of variability, which limits the progress of this technology. This paper introduces DetReIDX, a large-scale aerial-ground person dataset, that was explicitly designed as a stress test to ReID under real-world conditions. DetReIDX is a multi-session set that includes over 13 million bounding boxes from 509 identities, collected in seven university campuses from three continents, with drone altitudes between 5.8 and 120 meters. More important, as a key novelty, DetReIDX subjects were recorded in (at least) two sessions on different days, with changes in clothing, daylight and location, making it suitable to actually evaluate long-term person ReID. Plus, data were annotated from 16 soft biometric attributes and multitask labels for detection, tracking, ReID, and action recognition. In order to provide empirical evidence of DetReIDX usefulness, we considered the specific tasks of human detection and ReID, where SOTA methods catastrophically degrade performance (up to 80% in detection accuracy and over 70% in Rank-1 ReID) when exposed to DetReIDXs conditions. The dataset, annotations, and official evaluation protocols are publicly available at https://www.it.ubi.pt/DetReIDX/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。