arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08373eess.IV
收藏

适用于人和机器的可伸缩图像编码

Scalable Image Coding for Humans and Machines

Hyomin Choi, Ivan V. Bajic

摘要:

目前,以及未来越来越多的情况下,大部分捕获的视觉内容将不会被人类看到。相反,它将用于自动化机器视觉分析,可能需要偶尔进行人工观察。此类应用的示例包括交通监控、视觉监控、自主导航和工业机器视觉。为了满足这些要求,我们开发了一个端到端的学习图像编解码器,其潜在空间的设计,以支持从简单到更复杂的任务的可扩展性。最简单的任务被分配给潜在空间的子集(基本层),而更复杂的任务利用潜在空间的附加子集,即,基本层和增强层两者。对于实验,我们建立了一个2层和一个3层模型,每个模型都提供了人类视觉的输入重建,加上机器视觉任务,并将它们与相关的基准进行比较。实验表明,与最佳替代方案相比,我们的可扩展编解码器在机器视觉任务上节省了37%-80%的比特率,同时在输入重建方面与最先进的图像编解码器相当。

英文摘要:

At present, and increasingly so in the future, much of the captured visual content will not be seen by humans. Instead, it will be used for automated machine vision analytics and may require occasional human viewing. Examples of such applications include traffic monitoring, visual surveillance, autonomous navigation, and industrial machine vision. To address such requirements, we develop an end-to-end learned image codec whose latent space is designed to support scalability from simpler to more complicated tasks. The simplest task is assigned to a subset of the latent space (the base layer), while more complicated tasks make use of additional subsets of the latent space, i.e., both the base and enhancement layer(s). For the experiments, we establish a 2-layer and a 3-layer model, each of which offers input reconstruction for human vision, plus machine vision task(s), and compare them with relevant benchmarks. The experiments show that our scalable codecs offer 37%-80% bitrate savings on machine vision tasks compared to best alternatives, while being comparable to state-of-the-art image codecs in terms of input reconstruction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑