기계를 위한 비디오 부호화 표준화 동향

  • Published : 2023.01.30

Abstract

오늘날 인터넷 트래픽의 80% 이상은 이미지와 비디오와 같은 영상 정보가 차지하고 있으며, 딥러닝 기술의 발전과 더불어 영상을 사람이 아닌 머신이 처리하는 경우가 점점 늘어가고 있다. 사람의 시각적 특성과 머신이 처리하는 특징이 다를 수 있다는 점을 고려하여 MPEG을 비롯한 표준화 단체에서 딥러닝 네트워크를 포함한 기계(머신)를 위한 비디오 부호화에 대하여 표준화를 진행 중에 있다. 본 기고에서는 MPEG에서 진행되고 있는 머신 비전을 위한 영상 부호화 표준화 동향에 대해 정리한다.

Keywords

Acknowledgement

본 논문은 과학기술정보통신부의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임(No. 2020-0-00011, 기계를 위한 영상 부호화 기술)

References

  1. Use cases and requirements for Video Coding for Machines, ISO/IEC JTC1/SC29/WG2 N190, 2022.04 
  2. Evaluation Framework for Video Coding for Machines, ISO/IEC JTC1/SC29/WG2 N193, 2022.04. 
  3. Common Test Conditions and Evaluation Methodology for Video Coding for Machines, ISO/IEC JTC1/SC29/WG2 N193, 2022.04. 
  4. Call for Evidence for Video Coding for Machines, ISO/IEC JTC1/SC29/WG2 N42, 2021.01. 
  5. Call for Proposals for Video Coding for Machines, ISO/IEC JTC 1/SC 29/WG 2 N191, 2022.04 
  6. Call for Evidence on Video Coding for Machines, ISO/IEC JTC 1/SC29/WG2 N215, 2022.07. 
  7. Marek Domanski et. al., [VCM] Poznan University of Technology Proposal A in response to CfP on Video Coding for Machines, ISO/IEC JTC1/SC29/WG2/m60727, 2022. 10. 
  8. Marek Domanski et. al., [VCM] Poznan University of Technology Proposal B in response to CfP on Video Coding for Machines, ISO/IEC JTC1/SC29/WG2/m60728, 2022. 10. 
  9. Marek Domanski et. al., [VCM] Poznan University of Technology Proposal C in response to CfP on Video Coding for Machines, ISO/IEC JTC1/SC29/WG2/m60729, 2022. 10. 
  10. Sang-Kyun Kim et. al., [VCM] CfP response: Region-of-interest based video coding for machine, ISO/IEC JTC1/SC29/WG2/m60758, 2022. 10. 
  11. S. Wang et. al., [VCM] Video Coding for Machines CfP Response from Alibaba and City University of Hong Kong, ISO/IEC JTC1/SC29/WG2/m60737, 2022. 10. 
  12. Hari Kalva et. al., [VCM] Response to VCM CfP from the Florida Atlantic University and OP Solutions, ISO/IEC JTC1/SC29/WG2/m60743, 2022. 10. 
  13. Christopher Hollmann et. al., [VCM] Response to Call for Proposals from Ericsson, ISO/IEC JTC1/SC29/WG2/m60757, 2022. 10. 
  14. Yegi Lee et. al., [VCM] Response to CfE: Object detection results with the FLIR dataset, ISO/IEC JTC1/SC29/WG11/M56572, 2021.04. 
  15. Yegi Lee et. al., [VCM Track2] Response to VCM CfP: Video Coding with machine-attention, ISO/IEC JTC1/SC29/WG2/m60738, 2022. 10. 
  16. Jianran Liu et. al., [VCM] Video Coding for Machines CfP Response from Institute of Computing Technology, Chinese Academy of Sciences (CAS-ICT) and China Telecom, ISO/IEC JTC1/SC29/WG2/ m60773, 2022. 10. 
  17. ZIzheng Liu et. al., [VCM] Response to VCM Call for Proposals - an EVC based solution, ISO/IEC JTC1/SC29/WG2/ m60779, 2022. 10.. 
  18. ZIzheng Liu et. al., [VCM] Response to VCM Call for Proposals from Tencent and Wuhan University - an ECM based solution, ISO/IEC JTC1/SC29/WG2/ m60780, 2022. 10.. 
  19. Ke Jia et. al., [VCM] Response to the CfP on Video Coding for Machine from Zhejiang University, ISO/IEC JTC1/SC29/WG2/m60741, 2022. 10. 
  20. Wen Gao et. al., [VCM ]Response to VCM Call for Proposals from Tencent - an End-to-end Learning based Solution, ISO/IEC JTC1/SC29/WG2/m60777, 2022. 10. 
  21. Cheng, Z., et. al., Learned image compression with discretized gaussian mixture likelihoods and attention modules. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7939-7948), 2020 
  22. E. Agustsson, et. al., Scale-space flow for end-to-end optimized video compression, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020) 
  23. Honglei Zhang et. al., [VCM] Response to the CfP of the VCM by Nokia (A), ISO/IEC JTC1/SC29/WG2/m60753, 2022. 10. 
  24. Honglei Zhang et. al., [VCM] Response to the CfP of the VCM by Nokia (B), ISO/IEC JTC1/SC29/WG2/m60754, 2022. 10. 
  25. C. Rosewarne, [VCM Track 2] CfP test report, ISO/IEC JTC1/SC29/WG2/m61010, 2022. 10.. 
  26. CfP response report for Video Coding for Machines, ISO/IEC JTC1/SC29/WG2/N248, 2022. 10. 
  27. Heeji Han et. al.,, [VCM] Response from Hanbat National University and ETRI to CfE on Video Coding for Machines, ISO/IEC JTC1/SC29/WG2/m60761, 2022.10. 
  28. Yong-Uk Yoon et. al.,, [VCM] Response to VCM CfE: Multi-scale feature compression with QP-adaptive feature channel truncation, ISO/IEC JTC1/SC29/WG2/m60799, 2022.10. 
  29. C. Rosewarne, R. Nguyen, [VCM Track 1] Response to CfE on Video Coding for Machine from Canon, ISO/IEC JTC1/SC29/WG2/m60821, 2022.10. 
  30. Minhun Lee, et. al.,, [VCM Track 1] Response to CfE: A transformation-based feature map compression method, ISO/IEC JTC1/SC29/WG2/m60788, 2022.10. 
  31. Yong Zhang et. al.,, [VCM] Response to VCM Call for Evidence from Tencent and Wuhan University - a Learning-based Feature Compression Framework, ISO/IEC JTC1/SC29/WG2/m60925, 2022.10. 
  32. CfE response report for Video Coding for Machines, ISO/IEC JTC 1/SC29/WG2 N247, 2022.10 
  33. Hanming Wang, Zijun Wu, Tao Han, Yuan Zhang, [VCM][Response to CfE] An End-to-End Image Feature Compressing Method with Feature Fusion Module, ISO/IEC JTC1/SC29/WG2/m60802, 2022.10. 
  34. Hanming Wang, Zijun Wu, Tao Han, Yuan Zhang, [VCM][Response to CfE] An End-to-End Video Feature Compressing Method with Feature Fusion Module, ISO/IEC JTC1/SC29/WG2/m60803, 2022.10.