The Library
FusionCount : efficient crowd counting via multiscale feature fusion
Tools
Tools
Tools
Ma, Yiming, Sanchez, Victor and Guha, Tanaya (2022) FusionCount : efficient crowd counting via multiscale feature fusion. In: IEEE International Conference on Image Processing, Bordeaux, France, 16-19 Oct 2022. Published in: 2022 IEEE International Conference on Image Processing (ICIP) ISBN 9781665496216. doi:10.1109/ICIP46576.2022.9897322 ISSN 1522-4880.
|
PDF
WRAP-FusionCount-efficient-crowd-counting-via-multiscale-feature-fusion-Ma-22.pdf - Accepted Version - Requires a PDF viewer. Download (2874Kb) | Preview |
Official URL: https://doi.org/10.1109/ICIP46576.2022.9897322
Abstract
State-of-the-art crowd counting models follow an encoder-decoder approach. Images are first processed by the encoder to extract features. Then, to account for perspective distortion, the highest-level feature map is fed to extra components to extract multiscale features, which are the input to the decoder to generate crowd densities. However, in these methods, features extracted at earlier stages during encoding are underutilised, and the multiscale modules can only capture a limited range of receptive fields, albeit with considerable computational cost. This paper proposes a novel crowd counting architecture (FusionCount), which exploits the adaptive fusion of a large majority of encoded features instead of relying on additional extraction components to obtain multiscale features. Thus, it can cover a more extensive scope of receptive field sizes and lower the computational cost. We also introduce a new channel reduction block, which can extract saliency information during decoding and further enhance the model’s performance. Experiments on two benchmark databases demonstrate that our model achieves state-of-the-art results with reduced computational complexity. PyTorch implementation of the model and weights trained on these two datasets are available at https://github.com/YimingMa/FusionCount.
| Item Type: | Conference Item (Paper) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TK Electrical engineering. Electronics Nuclear engineering |
||||||||
| Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science Faculty of Science, Engineering and Medicine > Science > Mathematics |
||||||||
| Library of Congress Subject Headings (LCSH): | Crowds -- Measurement, Mathematical statistics, Image processing -- Digital techniques, Pattern recognition systems, Computer vision | ||||||||
| Journal or Publication Title: | 2022 IEEE International Conference on Image Processing (ICIP) | ||||||||
| Publisher: | IEEE | ||||||||
| ISBN: | 9781665496216 | ||||||||
| ISSN: | 1522-4880 | ||||||||
| Official Date: | 2022 | ||||||||
| Dates: |
|
||||||||
| DOI: | 10.1109/ICIP46576.2022.9897322 | ||||||||
| Status: | Peer Reviewed | ||||||||
| Publication Status: | Published | ||||||||
| Reuse Statement (publisher, data, author rights): | © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | ||||||||
| Access rights to Published version: | Restricted or Subscription Access | ||||||||
| Copyright Holders: | IEEE | ||||||||
| Date of first compliant deposit: | 3 August 2022 | ||||||||
| Date of first compliant Open Access: | 8 August 2022 | ||||||||
| Conference Paper Type: | Paper | ||||||||
| Title of Event: | IEEE International Conference on Image Processing | ||||||||
| Type of Event: | Conference | ||||||||
| Location of Event: | Bordeaux, France | ||||||||
| Date(s) of Event: | 16-19 Oct 2022 | ||||||||
| 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
