当前位置: X-MOL 学术Comput. Electr. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
CNN Inference acceleration using low-power devices for human monitoring and security scenarios
Computers & Electrical Engineering ( IF 4.0 ) Pub Date : 2020-12-01 , DOI: 10.1016/j.compeleceng.2020.106859
Juan Mas , Teodoro Panadero , Guillermo Botella , Alberto A. Del Barrio , Carlos García

Security is currently one of the top concerns in our society. From governmental installations to private companies and medical institutions, they all have to address directly with security issues as: access to restricted information quarantine control, or criminal tracking. As an example, identifying patients is critical in hospitals or geriatrics in order to isolate infected people, which has proven to be a non- trivial issue with the COVID-19 pandemic that is currently affecting all countries, or to locate fled patients. Face recognition is then a non-intrusive alternative for performing these tasks. Although FaceNet from Google has proved to be almost perfect, in a multi-face scenario its performance decays rapidly. In order to mitigate this loss of performance, in this paper a cluster based on the Neural Computer Stick version 2 and OpenVINO by Intel is proposed. A detailed power and runtime study is shown for two programming models, namely: multithreading and multiprocessing. Furthermore, 3 different hosts have been considered. In the most efficient configuration, an average of 6 frames per second has been achieved using the Raspberry Pi 4 as host and with a power consumption of just 11.2W, increasing by a factor of 3.3X the energy efficiency with respect to a PC-based solution in a multi-face scenario.

中文翻译:

使用低功耗设备进行 CNN 推理加速,用于人员监控和安全场景

目前,安全是我们社会最关心的问题之一。从政府设施到私营公司和医疗机构,它们都必须直接解决安全问题,例如:访问受限信息隔离控制或犯罪跟踪。例如,在医院或老年病学中,识别患者对于隔离感染者至关重要,这已被证明是当前影响所有国家/地区的 COVID-19 大流行的一个重要问题,或用于定位逃离的患者。人脸识别是执行这些任务的非侵入式替代方案。虽然谷歌的 FaceNet 已经被证明是近乎完美的,但在多面场景下它的性能会迅速衰减。为了减轻这种性能损失,在本文中,提出了一个基于 Neural Computer Stick 版本 2 和 Intel 的 OpenVINO 的集群。显示了两种编程模型的详细功耗和运行时间研究,即:多线程和多处理。此外,还考虑了 3 个不同的宿主。在最高效的配置中,使用 Raspberry Pi 4 作为主机实现了平均每秒 6 帧,功耗仅为 11.2W,相对于基于 PC 的能效提高了 3.3 倍多面场景下的解决方案。
更新日期:2020-12-01
down
wechat
bug