PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting. (arXiv:2111.00406v2 [cs.CV] UPDATED)

Crowd counting aims to learn the crowd density distributions and estimate the
number of objects (e.g. persons) in images. The perspective effect, which
significantly influences the distribution of data points, plays an important
role in crowd counting. In this paper, we propose a novel perspective-aware
approach called PANet to address the perspective problem. Based on the
observation that the size of the objects varies greatly in one image due to the
perspective effect, we propose the dynamic receptive fields (DRF) …

arxiv cv network perspective