WSCF-MVCC：弱监督校准-free多视角人群计数
WSCF-MVCC: Weakly-supervised Calibration-free Multi-view Crowd Counting
AI总结：
本文提出WSCF-MVCC方法，通过弱监督策略和自监督排名损失实现校准-free多视角人群计数，提升计数精度与实用性。
摘要：
多视角人群计数可以有效缓解单图像人群计数中常见的遮挡问题。现有的深度学习多视角人群计数方法将不同摄像头视角图像投影到一个共同空间以获得地面平面密度图，需要大量的、成本高昂的人群标注和摄像头校准。因此，提出了无需摄像头校准和场景级人群标注的校准-free方法。然而，现有校准-free方法仍需要昂贵的图像级人群标注来训练单视角计数模块。因此，在本文中，我们提出了一种弱监督校准-free多视角人群计数方法（WSCF-MVCC），直接使用人群计数作为单视角计数模块的监督，而不是从人群标注中构造的密度图。相反，采用了一种自监督的排名损失，利用多尺度先验来增强模型的感知能力，而无需额外的标注成本。此外，所提出的模型利用语义信息以实现更准确的视角匹配，并因此获得更精确的场景级人群计数估计。所提出的方法在三个广泛使用的多视角计数数据集上优于最先进的方法，在弱监督设置下表现优异，表明其比校准方法更适合实际部署。代码已发布在https://github.com/zqyq/Weakly-MVCC。
英文摘要：
Multi-view crowd counting can effectively mitigate occlusion issues that commonly arise in single-image crowd counting. Existing deep-learning multi-view crowd counting methods project different camera view images onto a common space to obtain ground-plane density maps, requiring abundant and costly crowd annotations and camera calibrations. Hence, calibration-free methods are proposed that do not require camera calibrations and scene-level crowd annotations. However, existing calibration-free methods still require expensive image-level crowd annotations for training the single-view counting module. Thus, in this paper, we propose a weakly-supervised calibration-free multi-view crowd counting method (WSCF-MVCC), directly using crowd count as supervision for the single-view counting module rather than density maps constructed from crowd annotations. Instead, a self-supervised ranking loss that leverages multi-scale priors is utilized to enhance the model's perceptual ability without additional annotation costs. What's more, the proposed model leverages semantic information to achieve a more accurate view matching and, consequently, a more precise scene-level crowd count estimation. The proposed method outperforms the state-of-the-art methods on three widely used multi-view counting datasets under weakly supervised settings, indicating that it is more suitable for practical deployment compared with calibrated methods. Code is released in https://github.com/zqyq/Weakly-MVCC.
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。
