Video Coding for Deep Learning-Based Machine-to-Machine Communication

基于深度学习的机器对机器通信的视频编码

• 批准号: 426084215
• 负责人: Professor Dr.-Ing. André Kaup
• 金额: --
• 依托单位: Lehrstuhl für Multimediakommunikation und Signalverarbeitung
• 依托单位国家: 德国
• 项目类别: Research Grants
• 财政年份: 2019
• 资助国家: 德国
• 起止时间: 2018-12-31 至 2021-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/426084215?language=en
• 关键词: Video; Coding; Deep; Learning; Based

In this research project, the video coding for machines (VCM) task shall be researched with a strong focus on the recently emerged neural compression networks (NCNs). There, autoencoder networks are trained to reconstruct the input image from a latent space requiring as as little bitrate as possible to transmit. For the follow-up project, state-of-the-art NCNs optimized for the human shall serve as a starting point to base own optimizations and designs for the VCM task on. To that end, the project is divided into two phases. First, intra compression is researched by developing novel training losses representing the evaluation network at the decoder side in order to improve the coding gains for VCM. Thereby, it will be differentiated between generally optimizing for multiple evaluation networks and when the specific evaluation network is known and available before encoding. Second, the found methods from the first phase are supposed to be used to further optimize suitable NCN architectures designed for inter coding. However, suitable pristine labeled video data has to be acquired for an appropriate evaluation before. Besides, also test cases requiring video data such as tracking shall be considered to measure the coding efficiency.

在本研究项目中，机器视频编码(VCM)任务将重点研究最近出现的神经压缩网络(NCN)。在那里，自动编码器网络被训练成从需要传输的尽可能低的比特率的潜在空间重建输入图像。对于后续项目，为人类优化的最先进的网络控制网络将作为自己为VCM任务进行优化和设计的起点。为此，该项目分为两个阶段。首先，为了提高VCM的编码增益，在解码器端提出了一种新的训练损失来表示评估网络，从而对帧内压缩进行了研究。因此，将区分针对多个评价网络的一般优化和在编码之前特定评价网络已知和可用的情况。第二，从第一阶段发现的方法被用来进一步优化为帧间编码设计的合适的NCN结构。然而，在此之前必须获取适当的原始标记视频数据以进行适当的评估。此外，还应考虑需要跟踪等视频数据的测试用例，以衡量编码效率。