发表机构
University of Ottawa（渥太华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出活动条件专家混合框架，利用日常生活活动超越步态，通过DS-SDPNet实现毫米波点云人员识别，显著提升闭集识别和重识别性能。
AI 中文摘要
基于毫米波（mmWave）点云的人员识别主要依赖于步态。然而，室内行走通常短暂且频繁中断，而其他日常生活活动（ADLs）可能提供互补的身份信息。我们使用mm-ADL数据集（一个在受控协议下从11名受试者收集的新点云数据集）研究了跨七种ADLs的识别问题。这一扩展引入了异质状态和转换，其空间和时间特征随活动而变化。因此，我们研究了活动是否能为学习身份表征提供有用的上下文。我们提出了一种活动条件框架，其中人类活动识别路由器将每个片段分派给特定活动的身份专家。该框架实现为监督式专家混合模型，使用双流静态-动态PointNet（DS-SDPNet）将时间聚合的空间结构与帧间信息相结合。我们评估了闭集识别（ID）和受试者不相交的重识别（ReID）。使用学习到的硬路由，ID准确率从62.1%提高到68.0%。在两人居所的ReID设置中，硬路由将mAP从57.2%提高到75.4%，Rank-1准确率从59.1%提高到82.1%。在匹配的图库分区下，特定活动的专家也优于共享嵌入，表明收益不仅限于缩小图库范围。这些结果支持了在步态之外使用ADLs进行识别的可行性，以及在受控室内条件下活动条件化的价值。
英文摘要
Person identification from millimeter-wave (mmWave) point clouds has mainly relied on gait. Indoor walking, however, is often brief and interrupted, while other activities of daily living (ADLs) may provide complementary identity information. We investigate identification across seven ADLs using mm-ADL, a new point-cloud dataset collected from 11 subjects under a controlled protocol. This extension introduces heterogeneous states and transitions whose spatial and temporal characteristics vary with activity. We therefore study whether activity can provide useful context for learning identity representations. We propose an activity-conditioned framework in which a human activity recognition router dispatches each clip to an activity-specific identity expert. The framework is implemented as a supervised mixture of experts, using a dual-stream static-dynamic PointNet (DS-SDPNet) to combine time-aggregated spatial structure with frame-to-frame information. We evaluate closed-set identification (ID) and subject-disjoint re-identification (ReID). With learned hard routing, ID accuracy increases from 62.1% to 68.0%. In a two-occupant ReID setting, hard routing increases mAP from 57.2% to 75.4% and Rank-1 accuracy from 59.1% to 82.1%. Under a matched gallery partition, activity-specific experts also outperform a shared embedding, showing that the gain extends beyond restricting the gallery. These results support the feasibility of using ADLs beyond gait for identification and the value of activity conditioning under controlled indoor conditions.
