当前位置: X-MOL 学术J. Exp. Theor. Artif. Intell. › 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.)
Catalysing assistive solutions by deploying light-weight deep learning model on edge devices
Journal of Experimental & Theoretical Artificial Intelligence ( IF 2.2 ) Pub Date : 2023-06-22 , DOI: 10.1080/0952813x.2023.2219286
Kanak Manjari 1 , Madhushi Verma 1 , Gaurav Singal 2 , Vinay Chamola 3
Affiliation  

ABSTRACT

Nowadays, real-time object detection, which is a crucial task, is being performed through image processing and deep learning techniques. As there are several high-performance computing edge devices available, selecting the best-fit device for a particular problem is a tough task and keeping in mind the cost, performance, and weight of the device in mind. One faces several challenges while performing this task in real-time such as a lack of resources in terms of power and mobility. We have provided an insight into the computation power of devices in terms of Frames per Second (FPS) by deploying object detection models on them. This paper will provide insight into selecting the appropriate combination of device and object detection models for real-time applications. Raspberry Pi 3 (RPi3), Raspberry Pi 4 (RPi4), Intel Neural Compute Stick 2 (NCS2), and Nvidia Jetson NANO are popular devices with high computation power used for real-time applications. The memory constraints of devices along with the deployment of different You Only Look Once (YOLO) and Single-Shot Detector (SSD) are the two object detection models that have been explained in this paper. A deep learning inference optimiser, TensorRT, has been used in NANO to achieve high throughput in the performance of object detection. The precision, recall, and F1 score achieved on deploying each tested model have been presented. After observing the devices during experimentation, RPi4+NCS2 showed the best execution with the blend of factors i.e. speed, portability, and user-friendliness.



中文翻译:

通过在边缘设备上部署轻量级深度学习模型来促进辅助解决方案

摘要

如今,实时目标检测是一项至关重要的任务,它是通过图像处理和深度学习技术来执行的。由于有多种高性能计算边缘设备可用,因此为特定问题选择最适合的设备是一项艰巨的任务,并且要牢记设备的成本、性能和重量。人们在实时执行这项任务时面临着一些挑战,例如缺乏电力和移动性方面的资源。我们通过在设备上部署对象检测模型,以每秒帧数 (FPS) 的形式深入了解设备的计算能力。本文将深入探讨如何为实时应用选择适当的设备和对象检测模型组合。Raspberry Pi 3 (RPi3)、Raspberry Pi 4 (RPi4)、英特尔神经计算棒 2 (NCS2)、和 Nvidia Jetson NANO 是用于实时应用程序的具有高计算能力的流行设备。设备的内存限制以及不同的 You Only Look Once (YOLO) 和 Single-Shot Detector (SSD) 的部署是本文解释的两种对象检测模型。NANO 中使用了深度学习推理优化器 TensorRT,以实现目标检测性能的高吞吐量。展示了部署每个测试模型时获得的精确度、召回率和 F1 分数。在实验过程中观察设备后,综合考虑速度、便携性和用户友好性等因素,RPi4+NCS2 显示出最佳执行效果。设备的内存限制以及不同的 You Only Look Once (YOLO) 和 Single-Shot Detector (SSD) 的部署是本文解释的两种对象检测模型。NANO 中使用了深度学习推理优化器 TensorRT,以实现目标检测性能的高吞吐量。展示了部署每个测试模型时获得的精确度、召回率和 F1 分数。在实验过程中观察设备后,综合考虑速度、便携性和用户友好性等因素,RPi4+NCS2 显示出最佳执行效果。设备的内存限制以及不同的 You Only Look Once (YOLO) 和 Single-Shot Detector (SSD) 的部署是本文解释的两种对象检测模型。NANO 中使用了深度学习推理优化器 TensorRT,以实现目标检测性能的高吞吐量。展示了部署每个测试模型时获得的精确度、召回率和 F1 分数。在实验过程中观察设备后,综合考虑速度、便携性和用户友好性等因素,RPi4+NCS2 显示出最佳执行效果。已在 NANO 中使用,以实现目标检测性能的高吞吐量。展示了部署每个测试模型时获得的精确度、召回率和 F1 分数。在实验过程中观察设备后,综合考虑速度、便携性和用户友好性等因素,RPi4+NCS2 显示出最佳执行效果。已在 NANO 中使用,以实现目标检测性能的高吞吐量。展示了部署每个测试模型时获得的精确度、召回率和 F1 分数。在实验过程中观察设备后,综合考虑速度、便携性和用户友好性等因素,RPi4+NCS2 显示出最佳执行效果。

更新日期:2023-06-22
down
wechat
bug