arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.00452cs.CVcs.LG
收藏

通过估计人流量来计算人数

Counting People by Estimating People Flows

École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)

Weizhe Liu, Mathieu Salzmann, Pascal Fua

摘要:

在拥挤场景中计算人数的现代方法依赖于深度网络来估计单个图像中的人密度。因此,只有极少数利用视频序列中的时间一致性,并且那些仅在连续帧上施加弱平滑度约束的视频序列。在本文中,我们主张估计连续图像之间的图像位置的人流量,并从这些流量推断的人密度,而不是直接回归。这使我们能够施加更强的约束来编码人数守恒。因此,它显著提高了性能,而无需更复杂的架构。此外,它允许我们利用人流和光流之间的相关性,以进一步改善结果。我们还表明,在空间和时间上利用人员守恒约束,可以在具有更少注释的主动学习环境中训练深度人群计数模型。这显著降低了注释成本,同时仍然导致与完全监督情况类似的性能。

英文摘要:

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing them. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it allows us to exploit the correlation between people flow and optical flow to further improve the results. We also show that leveraging people conservation constraints in both a spatial and temporal manner makes it possible to train a deep crowd counting model in an active learning setting with much fewer annotations. This significantly reduces the annotation cost while still leading to similar performance to the full supervision case.

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。

↑