EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transform-Based Feature Map Compression Method for Video Coding for Machines (VCM)

Minhun Lee, Seungjin Park, Seoung-Jun Oh, Younhee Kim, Se Yoon Jeong, Jooyoung Lee, Donggyu Sim

Electronics · 26.09.2023 · 12 (19) · 4042

DOI: 10.3390/electronics12194042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 26.09.2023. Verfasst von Minhun Lee und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information and Communications Technology Planning and Evaluation (IITP), Basic Science Research Program, MSIT & Future Planning.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The burgeoning field of machine vision has led to the development by the Moving Picture Experts Group (MPEG) of a new type of compression technology called video coding for machines (VCM), to enhance machine recognition through video information compression. This research proposes a principal component analysis (PCA)-based compression methodology for multi-level feature maps extracted from the feature pyramid network (FPN) structure. Unlike current PCA-based studies that independently carry out PCA for each feature map, our approach employs a generalized basis matrix and mean vector derived from channel correlations by a generalized PCA process to eliminate the need for a PCA process. Further compression is achieved by amalgamating high-dimensional feature maps, capitalizing on the spatial redundancy within these multi-level feature maps. As a result, the proposed VCM encoder forgoes the PCA process, and the generalized data do not incur any compression loss. It only requires compressing the coefficients for each feature map using versatile video coding (VVC). Experimental results demonstrate superior performance by our method over all feature anchors for each machine vision task, as specified by the MPEG-VCM common test conditions, outperforming previous PCA-based feature map compression methods. Notably, it achieved an 89.3% BD-rate reduction for instance segmentation tasks.

Förderung

  • Institute of Information and Communications Technology Planning and Evaluation (IITP)
  • Basic Science Research Program
  • MSIT & Future Planning
  • MSIT, Korea

Zitieren

APA

Lee, M., Park, S., Oh, S., Kim, Y., Jeong, S. Y., Lee, J., & Sim, D. (2023). Transform-Based Feature Map Compression Method for Video Coding for Machines (VCM). Electronics, 12(19), 4042. https://doi.org/10.3390/electronics12194042

Vancouver

Lee M, Park S, Oh S, Kim Y, Jeong SY, Lee J, et al. Transform-Based Feature Map Compression Method for Video Coding for Machines (VCM). Electronics. 2023;12(19):4042. doi:10.3390/electronics12194042

BibTeX
@article{Lee2023,
  author = {Lee, Minhun and Park, Seungjin and Oh, Seoung-Jun and Kim, Younhee and Jeong, Se Yoon and Lee, Jooyoung and Sim, Donggyu},
  title = {Transform-Based Feature Map Compression Method for Video Coding for Machines (VCM)},
  journal = {Electronics},
  year = {2023},
  volume = {12},
  number = {19},
  pages = {4042},
  doi = {10.3390/electronics12194042}
}
Kostenlos starten →