[论文解读] Recent Standard Development Activities on Video Coding for Machines

Wen Gao, Shan Liu+4 more|arXiv (Cornell University)|May 26, 2021

Visual Attention and Saliency Detection参考文献 7被引用 31

一句话总结

本文综述 MPEG VCM 的近期活动，概述用于机器视觉任务的视频编码的用例、需求、处理流水线、评估框架，以及提出的面向机器的视频编码技术解决方案。

ABSTRACT

In recent years, video data has dominated internet traffic and becomes one of the major data formats. With the emerging 5G and internet of things (IoT) technologies, more and more videos are generated by edge devices, sent across networks, and consumed by machines. The volume of video consumed by machine is exceeding the volume of video consumed by humans. Machine vision tasks include object detection, segmentation, tracking, and other machine-based applications, which are quite different from those for human consumption. On the other hand, due to large volumes of video data, it is essential to compress video before transmission. Thus, efficient video coding for machines (VCM) has become an important topic in academia and industry. In July 2019, the international standardization organization, i.e., MPEG, created an Ad-Hoc group named VCM to study the requirements for potential standardization work. In this paper, we will address the recent development activities in the MPEG VCM group. Specifically, we will first provide an overview of the MPEG VCM group including use cases, requirements, processing pipelines, plan for potential VCM standards, followed by the evaluation framework including machine-vision tasks, dataset, evaluation metrics, and anchor generation. We then introduce technology solutions proposed so far and discuss the recent responses to the Call for Evidence issued by MPEG VCM group.

研究动机与目标

• 概述 MPEG VCM 组在机器视频编码方面的范围、用例与需求。
• 呈现 VCM 的处理流水线与计划的标准。
• 描述评估框架，包括机器视觉任务、数据集、衡量指标和锚点生成。
• 总结迄今为止提出的技术解决方案，以及对征求证据的回应。

提出的方法

• 对 MPEG VCM 文档和征求证据的回应进行评审。
• 描述 VCM 的用例、需求与处理流水线。
• 提供包含机器视觉任务、数据集和衡量指标的评估框架大纲。
• 对提出的技术解决方案及其与潜在标准化的一致性进行概述。
• 讨论潜在 VCM 标准及锚点生成的计划。

实验结果

研究问题

• RQ1 推动 MPEG VCM 中机器视频编码的发展用例和需求有哪些？
• RQ2 为 VCM 标准化设想的处理流水线是什么？
• RQ3 为 VCM 提出的评估框架元素（任务、数据集、衡量指标、锚点）有哪些？
• RQ4 为 VCM 提出哪些技术解决方案，以及它们如何回应征求证据？

主要发现

• VCM 满足以机器为中心的视频压缩需求，与以人为中心的用例不同。
• 提出了一个包含机器视觉任务、数据集、指标和锚点生成的结构化评估框架。
• 迄今提出的技术解决方案在 MPEG VCM 的征求证据回应中进行了讨论。
• 有一个明确的潜在 VCM 标准及已勾勒的处理流水线计划。