ACCURATE GIGAPIXEL CROWD COUNTING BY ITERATIVE ZOOMING AND REFINEMENT

Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Abstract

The increasing prevalence of gigapixel resolutions has presented new challenges for crowd counting. Such resolutions are far beyond the memory and computation limits of current GPUs, and available deep neural network architectures and training procedures are not designed for such massive inputs. Although several methods have been proposed to address these challenges, they are either limited to downsampling the input image to a small size, or borrowing from other gigapixel tasks, which are not tailored for crowd counting. In this paper, we propose a novel method called GigaZoom, which iteratively zooms into the densest areas of the image and refines coarser density maps with finer details. We show that GigaZoom obtains the state-of-the-art for gigapixel crowd counting and improves the accuracy of the next best method by 42%.

Original languageEnglish
Title of host publicationICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Number of pages5
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication date2024
Pages6510-6514
ISBN (Print)979-8-3503-4486-8
ISBN (Electronic)9798350344851
DOIs
Publication statusPublished - 2024
Event49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Seoul, Korea, Republic of
Duration: 14 Apr 202419 Apr 2024

Conference

Conference49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Country/TerritoryKorea, Republic of
CitySeoul
Period14/04/202419/04/2024
SponsorThe Institute of Electrical and Electronics Engineers Signal Processing Society
SeriesICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN1520-6149

Keywords

  • Computer Vision
  • Crowd Counting
  • Gigapixel Deep Learning
  • High-Resolution Deep Learning

Fingerprint

Dive into the research topics of 'ACCURATE GIGAPIXEL CROWD COUNTING BY ITERATIVE ZOOMING AND REFINEMENT'. Together they form a unique fingerprint.

Cite this