arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.14049eess.SPcs.CV
收藏

面向边缘视频分析的任务导向通信

Task-Oriented Communication for Edge Video Analytics

Hong Kong University of Science and Technology(香港科技大学)

Jiawei Shao, Xinjie Zhang, Jun Zhang

AI总结:

本文提出面向边缘视频分析的任务导向通信框架,通过信息瓶颈提取紧凑任务相关特征,并利用时间熵模型和时空融合模块降低通信开销、提升推理性能,实现了比现有方法更好的率-性能权衡。

摘要:

随着人工智能技术的发展以及配备摄像头设备的日益普及,许多边缘视频分析应用正在兴起,这要求在网络边缘部署计算密集型的人工智能模型。边缘推理是一种很有前景的解决方案,它将计算密集型工作负载从低端设备转移到强大的边缘服务器上进行视频分析,但由于带宽有限,设备与服务器之间的通信仍将是瓶颈。本文提出了一种面向边缘视频分析的任务导向通信框架,其中多个设备采集视觉感知数据,并将信息量丰富的特征传输到边缘服务器进行处理。为了实现低延迟推理,该框架在空间域和时间域上去除视频冗余,传输对下游任务至关重要的最小信息,而不是在边缘服务器上重建视频。具体而言,该框架基于确定性信息瓶颈(IB)原理提取紧凑的任务相关特征,该原理刻画了特征信息量与通信成本之间的权衡。由于连续帧的特征在时间上具有相关性,我们提出了一种时间熵模型(TEM),通过在特征编码中将先前特征作为边信息来降低比特率。为了进一步提高推理性能,我们在服务器端构建了一个时空融合模块,以整合当前帧和先前帧的特征进行联合推理。在视频分析任务上的大量实验证明,所提出的框架能够有效地编码视频数据中的任务相关信息,并实现比现有方法更好的率-性能权衡。

英文摘要:

With the development of artificial intelligence (AI) techniques and the increasing popularity of camera-equipped devices, many edge video analytics applications are emerging, calling for the deployment of computation-intensive AI models at the network edge. Edge inference is a promising solution to move the computation-intensive workloads from low-end devices to a powerful edge server for video analytics, but the device-server communications will remain a bottleneck due to the limited bandwidth. This paper proposes a task-oriented communication framework for edge video analytics, where multiple devices collect the visual sensory data and transmit the informative features to an edge server for processing. To enable low-latency inference, this framework removes video redundancy in spatial and temporal domains and transmits minimal information that is essential for the downstream task, rather than reconstructing the videos at the edge server. Specifically, it extracts compact task-relevant features based on the deterministic information bottleneck (IB) principle, which characterizes a tradeoff between the informativeness of the features and the communication cost. As the features of consecutive frames are temporally correlated, we propose a temporal entropy model (TEM) to reduce the bitrate by taking the previous features as side information in feature encoding. To further improve the inference performance, we build a spatial-temporal fusion module at the server to integrate features of the current and previous frames for joint inference. Extensive experiments on video analytics tasks evidence that the proposed framework effectively encodes task-relevant information of video data and achieves a better rate-performance tradeoff than existing methods.

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。

↑