Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will
potentially lead to a lower recall rate and a higher threshold introduces more
false positives. This problem is more severe in pedestrian detection because
the instance density varies more intensively. However, previous works on NMS
don't consider or vaguely consider the factor of the existent of nearby
pedestrians. Thus, we propose Nearby Objects Hallucinator (NOH), which
pinpoints the objects nearby each proposal with a Gaussian distribution,
together with NOH-NMS, which dynamically eases the suppression for the space
that might contain other objects with a high likelihood. Compared to
Greedy-NMS, our method, as the state-of-the-art, improves by $3.9\%$ AP,
$5.1\%$ Recall, and $0.8\%$ $\text{MR}^{-2}$ on CrowdHuman to $89.0\%$ AP and
$92.9\%$ Recall, and $43.9\%$ $\text{MR}^{-2}$ respectively.

该研究提出了一种名为 NOH 的方法，它可以通过确定每个提案附近的对象来改进 Greedy-NMS 算法，NOH-NMS 可以动态地减少可能包含其他对象的空间的抑制，并在行人检测领域 State-of-the-art 水平与传统算法相比，该方法分别提高了 3.9％的 AP，5.1％的召回率和 0.8％的 MR^-2。