Early Fire Detection System by Using Automatic Synthetic Dataset Generation Model Based on Digital Twins

被引:3
|
作者
Kim, Hyeon-Cheol [1 ]
Lam, Hoang-Khanh [1 ]
Lee, Suk-Hwan [1 ]
Ok, Soo-Yol [1 ]
机构
[1] Dong A Univ, Dept Comp Engn, Busan 49315, South Korea
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 05期
基金
新加坡国家研究基金会;
关键词
digital twin smart city; particle system; synthetic learning data; early fire detection; object detection;
D O I
10.3390/app14051801
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Fire is amorphous and occurs differently depending on the space, environment, and material of the fire. In particular, the early detection of fires is a very important task in preventing large-scale accidents; however, there are currently almost no learnable early fire datasets for machine learning. This paper proposes an early fire detection system optimized for certain spaces using a digital-twin-based automatic fire learning data generation model for each space. The proposed method first automatically generates realistic particle-simulation-based synthetic fire data on an RGB-D image matched to the view angle of a monitoring camera to build a digital twin environment of the real space. In other words, our method generates synthetic fire data according to various fire situations in each specific space and then performs transfer learning using a state-of-the-art detection model with these datasets and distributes them to AIoT devices in the real space. Synthetic fire data generation optimized for a space can increase the accuracy and reduce the false detection rate of existing fire detection models that are not adaptive to space.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Synthetic dataset generation system for vehicle detection
    Oric, Mihaela
    Galic, Vlatko
    Novoselnik, Filip
    SOFTWARE IMPACTS, 2025, 23
  • [2] Automatic Model Based Dataset Generation for Fast and Accurate Crop and Weeds Detection
    Di Cicco, Maurilio
    Potena, Ciro
    Grisetti, Giorgio
    Pretto, Alberto
    2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2017, : 5188 - 5195
  • [3] Automatic Early Forest Fire Detection Based on Gaussian Mixture Model
    Qian, Jiye
    Fu, Jin
    Qian, Jide
    Yang, Weibin
    Wang, Ke
    Cao, Pan
    2018 IEEE 18TH INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY (ICCT), 2018, : 1192 - 1196
  • [4] An Intelligent Automatic Early Detection System of Forest Fire Smoke Signatures using Gaussian Mixture Model
    Yoon, Seok-Hwan
    Min, Joonyoung
    JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2013, 9 (04): : 621 - 632
  • [5] A Method for Target Detection Based on Synthetic Samples of Digital Twins
    Dong, Zhe
    Yang, Yue
    Wang, Anqi
    Wu, Tianxu
    IEEE ACCESS, 2024, 12 : 66833 - 66844
  • [6] An Automatic Defect Detection System for Synthetic Shuttlecocks Using Transformer Model
    Lin, Ching-Sheng
    Hsieh, Han-Yi
    IEEE ACCESS, 2022, 10 : 37412 - 37421
  • [7] Synthetic Training Dataset Generation Using a Digital Twin-based Autonomous Driving Simulator
    Jang, In-Sung
    Li, Ki-Joune
    Joo, Eun-Oh
    Kim, Min-Soo
    SENSORS AND MATERIALS, 2024, 36 (09)
  • [8] Bin Picking System using Object Recognition based on Automated Synthetic Dataset Generation
    Jo, Hyun-Jun
    Min, Cheol-Hui
    Song, Jae-Bok
    2018 15TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS (UR), 2018, : 886 - 890
  • [9] A Synthetic Dataset Generation for the Uveitis Pathology Based on MedWGAN Model
    Sliman, Heithem
    Megdiche, Imen
    Yangui, Sami
    Drira, Aida
    Drira, Ines
    Lamine, Elyes
    38TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2023, 2023, : 559 - 566
  • [10] Automatic Generation of Simulation-based Digital Twins of Industrial Process Plants
    Martinez, Gerardo Santillan
    Karhela, Tommi
    Ruusu, Reino
    Kortelainen, Juha
    ERCIM NEWS, 2018, (115): : 16 - 17