论文标题
边缘有效的异质视频分割
Efficient Heterogeneous Video Segmentation at the Edge
论文作者
论文摘要
我们引入了一个有效的视频分割系统，用于利用异构计算的资源有限的边缘设备。具体而言，我们通过在已经轻巧的骨架上跨越规格的多个规范范围来搜索网络模型，以市场商业可用的边缘推理引擎。我们进一步分析和优化了CPU，GPU和NPU的系统中的异质数据流。从经验上讲，我们的方法已很好地考虑到我们的实时AR系统，通过三倍的有效分辨率使精度更高，但在端到端的延迟较短，帧速率更高，甚至在边缘平台上更低的功耗。
We introduce an efficient video segmentation system for resource-limited edge devices leveraging heterogeneous compute. Specifically, we design network models by searching across multiple dimensions of specifications for the neural architectures and operations on top of already light-weight backbones, targeting commercially available edge inference engines. We further analyze and optimize the heterogeneous data flows in our systems across the CPU, the GPU and the NPU. Our approach has empirically factored well into our real-time AR system, enabling remarkably higher accuracy with quadrupled effective resolutions, yet at much shorter end-to-end latency, much higher frame rate, and even lower power consumption on edge platforms.
