Artificial Intelligence Research Laboratory, ETRI, Daejeon 34129, Republic of Korea.
Sensors (Basel). 2023 May 12;23(10):4712. doi: 10.3390/s23104712.
The demand for deep learning frameworks capable of running in edge computing environments is rapidly increasing due to the exponential growth of data volume and the need for real-time processing. However, edge computing environments often have limited resources, necessitating the distribution of deep learning models. Distributing deep learning models can be challenging as it requires specifying the resource type for each process and ensuring that the models are lightweight without performance degradation. To address this issue, we propose the Microservice Deep-learning Edge Detection (MDED) framework, designed for easy deployment and distributed processing in edge computing environments. The MDED framework leverages Docker-based containers and Kubernetes orchestration to obtain a pedestrian-detection deep learning model with a speed of up to 19 FPS, satisfying the semi-real-time condition. The framework employs an ensemble of high-level feature-specific networks (HFN) and low-level feature-specific networks (LFN) trained on the MOT17Det dataset, achieving an accuracy improvement of up to and on MOT20Det data.
由于数据量的指数级增长和实时处理的需求，能够在边缘计算环境中运行的深度学习框架的需求正在迅速增加。然而，边缘计算环境通常资源有限，需要对深度学习模型进行分布式处理。分布式深度学习模型可能具有挑战性，因为需要为每个进程指定资源类型，并确保模型在不降低性能的情况下保持轻量级。为了解决这个问题，我们提出了 Microservice Deep-learning Edge Detection（MDED）框架，旨在为边缘计算环境中的轻松部署和分布式处理而设计。MDED 框架利用基于 Docker 的容器和 Kubernetes 编排来获得行人检测深度学习模型，其速度高达 19 FPS，满足半实时条件。该框架采用在 MOT17Det 数据集上训练的高层特征特定网络（HFN）和底层特征特定网络（LFN）的集成，在 MOT20Det 数据上实现了高达 和 的精度提高。
