English

A-CCNN: adaptive ccnn for density estimation and crowd counting

Computer Vision and Pattern Recognition 2018-04-23 v2

Abstract

Crowd counting, for estimating the number of people in a crowd using vision-based computer techniques, has attracted much interest in the research community. Although many attempts have been reported, real-world problems, such as huge variation in subjects' sizes in images and serious occlusion among people, make it still a challenging problem. In this paper, we propose an Adaptive Counting Convolutional Neural Network (A-CCNN) and consider the scale variation of objects in a frame adaptively so as to improve the accuracy of counting. Our method takes advantages of contextual information to provide more accurate and adaptive density maps and crowd counting in a scene. Extensively experimental evaluation is conducted using different benchmark datasets for object-counting and shows that the proposed approach is effective and outperforms state-of-the-art approaches.

Keywords

Cite

@article{arxiv.1804.06958,
  title  = {A-CCNN: adaptive ccnn for density estimation and crowd counting},
  author = {Saeed Amirgholipour Kasmani and Xiangjian He and Wenjing Jia and Dadong Wang and Michelle Zeibots},
  journal= {arXiv preprint arXiv:1804.06958},
  year   = {2018}
}

Comments

5 pages, 2 figures

R2 v1 2026-06-23T01:28:12.772Z