An Improved Normed-Deformable Convolution for Crowd Counting. (arXiv:2206.08084v1 [cs.CV])

Web: http://arxiv.org/abs/2206.08084

In recent years, crowd counting has become an important issue in computer
vision. In most methods, the density maps are generated by convolving with a
Gaussian kernel from the ground-truth dot maps which are marked around the
center of human heads. Due to the fixed geometric structures in CNNs and
indistinct head-scale information, the head features are obtained incompletely.
Deformable convolution is proposed to exploit the scale-adaptive capabilities
for CNN features in the heads. By learning the coordinate offsets of …

arxiv convolution cv