The Library
Shallow feature based dense attention network for crowd counting
Tools
Miao, Yun, Lin, Zijia, Ding, Guiguang and Han, Jungong (2020) Shallow feature based dense attention network for crowd counting. In: AAAI-20 34th Conference on Artificial Intelligence, New York, New York, 7-12 Feb 2020. Published in: Proceedings of the AAAI Conference on Artificial Intelligence, 34 (07). pp. 11765-11772. doi:10.1609/aaai.v34i07.6848
|
PDF
WRAP-shallow-feature-dense-attention-crowd-counting-Han-2019.pdf - Unspecified Version - Requires a PDF viewer. Download (4Mb) | Preview |
Official URL: https://doi.org/10.1609/aaai.v34i07.6848
Abstract
While the performance of crowd counting via deep learning has been improved dramatically in the recent years, it remains an ingrained problem due to cluttered backgrounds and varying scales of people within an image. In this paper, we propose a Shallow feature based Dense Attention Network (SDANet) for crowd counting from still images, which diminishes the impact of backgrounds via involving a shallow feature based attention model, and meanwhile, captures multi-scale information via densely connecting hierarchical image features. Specifically, inspired by the observation that backgrounds and human crowds generally have noticeably different responses in shallow features, we decide to build our attention model upon shallow-feature maps, which results in accurate background-pixel detection. Moreover, considering that the most representative features of people across different scales can appear in different layers of a feature extraction network, to better keep them all, we propose to densely connect hierarchical image features of different layers and subsequently encode them for estimating crowd density. Experimental results on three benchmark datasets clearly demonstrate the superiority of SDANet when dealing with different scenarios. Particularly, on the challenging UCF CC 50 dataset, our method outperforms other existing methods by a large margin, as is evident from a remarkable 11.9% Mean Absolute Error (MAE) drop of our SDANet.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | H Social Sciences > HM Sociology Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TA Engineering (General). Civil engineering (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||
Library of Congress Subject Headings (LCSH): | Crowds, Computer simulation, Computer vision, Content-based image retrieval , Image processing -- Digital techniques, Pattern recognition systems | ||||||
Journal or Publication Title: | Proceedings of the AAAI Conference on Artificial Intelligence | ||||||
Publisher: | AAAI Press | ||||||
Official Date: | 2020 | ||||||
Dates: |
|
||||||
Volume: | 34 | ||||||
Number: | 07 | ||||||
Page Range: | pp. 11765-11772 | ||||||
DOI: | 10.1609/aaai.v34i07.6848 | ||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | AAAI-20 34th Conference on Artificial Intelligence | ||||||
Type of Event: | Conference | ||||||
Location of Event: | New York, New York | ||||||
Date(s) of Event: | 7-12 Feb 2020 | ||||||
Related URLs: | |||||||
Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year