Real-time smoke detection method of battery-powered ship based on improved DETR model
CSTR:
Author:
Affiliation:

Marine Engineering College, Dalian Maritime University, Dalian 116026, China

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    Early fires on battery-powered ships manifest as smoke, posing higher requirements for detection accuracy, latency, and real-time detection of video streams. A real-time smoke detection model based on an improved detection transformer (DETR) is proposed. Smoke simulation experiments are conducted in maritime engine room scenes to construct smoke datasets. Subsequently, by using a lightweight convolutional structure and improving parameter propagation, the model’s smoke feature extraction capability is optimized. In the encoder part, a cross-scale feature fusion structure is constructed to achieve the self-attention mechanism model for detecting streaming videos. During the testing phase with smoke videos, a detection speed of 29 frames per second (FPS) at a resolution of 1 080 pixels is achieved by our proposed method, and detection accuracy metrics of average precision at 0.5:0.95 (AP0.5:0.95) and AP0.5 reach 80.5% and 96.9%. The experimental results demonstrate that excellent performance in real-time smoke detection for battery-powered ships is exhibited by this method.

    Reference
    Related
    Cited by
Get Citation

Shixiang LIU?, Yichen LIU?, Bin ZHANG, Yiming LI, Wanying YUE, Jiapeng TONG. Real-time smoke detection method of battery-powered ship based on improved DETR model[J]. Optoelectronics Letters,2026,22(11):677-683

Copy
Related Videos

Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:May 04,2025
  • Revised:April 25,2026
  • Adopted:
  • Online: November 06,2026
  • Published:
Article QR Code