Congested crowd instance localization with dilated convolutional swin transformer

Crowd localization is a new computer vision task, evolved from crowd counting. Different the latter, it provides more precise location information for each instance, not just counting numbers whole scene, which brings greater challenges, especially in extremely congested scenes. In this paper, we focus on how to achieve instance high-density scenes, and alleviate problem that feature extraction ability of traditional model reduced due target occlusion, image blur, etc. To end, propose Dilated Convolutional Swin Transformer (DCST) Specifically, window-based transformer introduced into effectively improves capacity representation learning. Then, well-designed dilated convolutional module inserted some different stages enhance large-range contextual information. Extensive experiments evidence effectiveness proposed methods state-of-the-art performance five popular datasets. Especially, achieves F1-measure 77.5% MAE 84.2 terms performance, respectively.