SA-DCPNet: Scale-aware deep convolutional pyramid network for crowd counting

Crowd counting is one of the most complex research topics in the field of computer vision. There are many challenges associated with this task, including severe occlusion, scale variation, and complex background. Multi-column networks are commonly used for crowd counting, but they suffer from scale variation and feature similarity, which leads to poor analysis of crowd sequences. To address these issues, we propose a scale-aware deep convolutional pyramid network for crowd counting. We have introduced a scale-aware deep convolutional pyramid module by integrating message passing and global attention mechanisms into a multi-column network. The proposed network minimizes the problem of scale variation using SA-DPCM and uses a multi-column variance loss function to handle issues with feature similarity. Experiments have been performed over the ShanghaiTech and UCF-CC-50 datasets, which show the better performance of the proposed method in terms of mean absolute error and root mean square error.