APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 6

Human-Machine Collaborative Image and Video Compression: A Survey

Huanyang Li, University of Chinese Academy of Sciences, China AND Pengcheng Laboratory, China, Xinfeng Zhang, University of Chinese Academy of Sciences, China, xfzhang@ucas.ac.cn , Shiqi Wang, City University of Hong Kong, Hong Kong, Shanshe Wang, Information Technology R&D Innovation Center of Peking University, China, Jingshan Pan, Shandong Computer Science Center, China
 
Suggested Citation
Huanyang Li, Xinfeng Zhang, Shiqi Wang, Shanshe Wang and Jingshan Pan (2024), "Human-Machine Collaborative Image and Video Compression: A Survey", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 6, e502. http://dx.doi.org/10.1561/116.20240052

Publication Date: 30 Oct 2024
© 2024 H. Li, X. Zhang, S. Wang, S. Wang and J. Pan
 
Subjects
Coding theory and practice,  Data compression,  Source coding,  Speech and image compression,  Signal processing for communications,  Deep learning
 
Keywords
Bit rate controlresidual networkvideo coding
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 215 times

In this article:
Introduction 
Foundations of Human-Machine Collaborative Image and Video Compression 
Human-Machine Collaborative Image Compression 
Human-Machine Collaborative Video Compression 
Comparative Analysis of Techniques 
Conclusion and Future Directions 
References 

Abstract

Traditional image and video compression methods are designed to maintain the quality of human visual perception, which makes it necessary to reconstruct the image or video before machine analysis. Compression methods oriented towards machine vision tasks make it possible to use the bit stream directly for machine vision tasks, but it is difficult for them to decode high quality images. To bridge the gap between machine vision tasks and signal-level representation, researchers present plenty of the human-machine collaborative compression methods. In order to provide researchers with a comprehensive understanding of this field and promote the development of image and video compression, we present this survey. In this work, we give a problem definition and explore the relationship and application scenarios of different methods. In addition, we provide a comparative analysis of existing methods on compression and machine vision tasks performance. Finally, we provide a discussion of several directions that are most promising for future research.

DOI:10.1561/116.20240052

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Deep Learning-Based Data Compression
See the other articles that are part of this special issue.