受社交分组和时空位移先验信息启发的拥挤视频个体计数
Crowded Video Individual Counting Informed by Social Grouping and Spatial-Temporal Displacement Priors
AI总结：
本文提出OMAN++方法，通过引入社交分组和时空位移先验信息，提升拥挤场景下视频个体计数的准确性。
摘要：
视频个体计数（VIC）是一种 recently 引入的任务，旨在从视频中估计行人流量。它扩展了视频人群计数（VCC）的范围，超越了每帧行人计数。与VCC不同，后者学习跨帧计数行人，而VIC必须在帧之间识别共存的行人，这实际上是一个对应问题。然而，现有的VIC方法在拥挤场景如地铁通勤中表现不佳。为了解决这个问题，我们构建了WuhanMetroCrowd，这是第一个VIC数据集之一，能够描述拥挤、动态的行人流动。它具有稀疏到密集的密度水平、短到长的视频片段、慢到快的流动变化、前到后外观变化以及明到暗的遮挡。为了更好地适应人群，我们重新思考VIC的性质，并识别了两个信息性先验：i）社交分组先验，表明行人倾向于成群聚集；ii）时空位移先验，表明个体不能物理上瞬间移动。前者促使我们放松VIC通常使用的标准一对一（O2O）匹配，采用一对一多（O2M）匹配，通过隐式上下文生成器和O2M匹配器实现；后者促进了位移先验注入器的设计，不仅加强了O2M匹配，还增强了特征提取和模型训练。这些设计共同形成了一种新的强VIC基线OMAN++。广泛的实验表明，OMAN++不仅在标准的SenseCrowd、CroHD和MovingDroneCrowd基准上优于最先进的VIC基线，而且在拥挤场景中表现出明显优势，在我们的WuhanMetroCrowd数据集上误差减少了38.12%。代码、数据和预训练模型可在https://github.com/tiny-smart/OMAN上获得。
英文摘要：
Video Individual Counting (VIC) is a recently introduced task aiming to estimate pedestrian flux from a video. It extends Video Crowd Counting (VCC) beyond the per-frame pedestrian count. In contrast to VCC that learns to count pedestrians across frames, VIC must identify co-existent pedestrians between frames, which turns out to be a correspondence problem. Existing VIC approaches, however, can underperform in congested scenes such as metro commuting. To address this, we build WuhanMetroCrowd, one of the first VIC datasets that characterize crowded, dynamic pedestrian flows. It features sparse-to-dense density levels, short-to-long video clips, slow-to-fast flow variations, front-to-back appearance changes, and light-to-heavy occlusions. To better adapt VIC approaches to crowds, we rethink the nature of VIC and recognize two informative priors: i) the social grouping prior that indicates pedestrians tend to gather in groups and ii) the spatial-temporal displacement prior that informs an individual cannot teleport physically. The former inspires us to relax the standard one-to-one (O2O) matching used by VIC to one-to-many (O2M) matching, implemented by an implicit context generator and a O2M matcher; the latter facilitates the design of a displacement prior injector, which strengthens not only O2M matching but also feature extraction and model training. These designs jointly form a novel and strong VIC baseline OMAN++. Extensive experiments show that OMAN++ not only outperforms state-of-the-art VIC baselines on the standard SenseCrowd, CroHD, and MovingDroneCrowd benchmarks, but also indicates a clear advantage in crowded scenes, with a 38.12% error reduction on our WuhanMetroCrowd dataset. Code, data, and pretrained models are available at https://github.com/tiny-smart/OMAN.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
