具備邊緣運算演算法之超聲感測陣列應用於智能工廠人像安全識別

Project Details

Description

In the era of AIIoT, the layout optimization of smart factories is an inevitable process for the manufacturing industry. However, it is accompanied by the transition issues of human safety between the traditional manual management and the new type in a smart technology factory. Therefore, the purpose of this proposal is to combine artificial intelligence algorithms with sensor fusion technology and to implement real-time human recognition and the adaptive protection of human safety in smart factories. Technically, the human-machine collaboration in fixed-point mode and the personnel safety protection program of the station-based mobile automated guided vehicle will be used as two main scenarios to develop (1) the physical behavior model of sensing module and its design optimization, (2) the physical sensor fusion technology and circuit design, development and their verification, (3) the development and design of edge computing algorithm, (4) data streaming transmission with a confidential protocol in smart factories, and (5) the integration, execution, and verification of the proposed smart sensing system. The goal of this three-year proposal is to design, develop, and plan a human-sensing security protection system that can be flexibly installed in various scenarios of modern smart factories.
StatusFinished
Effective start/end date1/06/2131/05/22

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 8 - Decent Work and Economic Growth
  • SDG 11 - Sustainable Cities and Communities
  • SDG 17 - Partnerships for the Goals

Keywords

  • AIIoT
  • Smart factory
  • Personnel safety protection
  • Human recognition

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.