Crowd Counting Using Scale-Aware Attention Networks
It improves crowd counting accuracy for applications like surveillance and event management, but is incremental as it builds on existing attention mechanisms.
The paper tackles crowd counting in images by addressing scale variation, proposing a scale-aware attention network that outperforms state-of-the-art methods on benchmark datasets.
In this paper, we consider the problem of crowd counting in images. Given an image of a crowded scene, our goal is to estimate the density map of this image, where each pixel value in the density map corresponds to the crowd density at the corresponding location in the image. Given the estimated density map, the final crowd count can be obtained by summing over all values in the density map. One challenge of crowd counting is the scale variation in images. In this work, we propose a novel scale-aware attention network to address this challenge. Using the attention mechanism popular in recent deep learning architectures, our model can automatically focus on certain global and local scales appropriate for the image. By combining these global and local scale attention, our model outperforms other state-of-the-art methods for crowd counting on several benchmark datasets.