CCST: crowd counting with swin transformer

• Published in: The Visual computer Vol. 39; no. 7; pp. 2671 - 2682
• Main Authors: Li, Bo, Zhang, Yong, Xu, Haihui, Yin, Baocai
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.07.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Graphics; Computer Science; Density; Design; Image Processing and Computer Vision; Matching; Original Article; Semantics; Supervision; Transformers; Feature adaptive fusion; Transformer; Crowd counting; Uneven distribution of crowd density; Large span of head size

Accurately estimating the number of individuals contained in an image is the purpose of the crowd counting. It has always faced two major difficulties: uneven distribution of crowd density and large span of head size. Focusing on the former, most CNN-based methods divide the image into multiple patc...