Real-Time Video Smoke Detection Based on Deep Domain Adaptation for Injection Molding Machines

Leakage with smoke is often accompanied by fire and explosion hazards. Detecting smoke helps gain time for crisis management. This study aims to address this issue by establishing a video smoke detection system, based on a convolutional neural network (CNN), with the help of smoke synthesis, auto-an...

Full description

Saved in:
Bibliographic Details
Published in:Mathematics (Basel) 2023-09, Vol.11 (17), p.3728
Main Authors: Chen, Ssu-Han, Jang, Jer-Huan, Youh, Meng-Jey, Chou, Yen-Ting, Kang, Chih-Hsiang, Wu, Chang-Yen, Chen, Chih-Ming, Lin, Jiun-Shiung, Lin, Jin-Kwan, Liu, Kevin Fong-Rey
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Annotations
Artificial neural networks
Assembly lines
automatic labeling
Automation
Classification
Codes
Confusion
convolutional neural networks
Datasets
deep domain adaptation
Factories
False alarms
Fire alarms
Fire hazards
Fire prevention
Injection molding
Injection molding machines
Methods
motion detection
Neural networks
Plastics machinery
Raw materials
Smoke
smoke detection
Surveillance
Training
Unmanned aerial vehicles
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Leakage with smoke is often accompanied by fire and explosion hazards. Detecting smoke helps gain time for crisis management. This study aims to address this issue by establishing a video smoke detection system, based on a convolutional neural network (CNN), with the help of smoke synthesis, auto-annotation, and an attention mechanism by fusing gray histogram image information. Additionally, the study incorporates the domain adversarial training of neural networks (DANN) to investigate the effect of domain shifts when adapting the smoke detection model from one injection molding machine to another on-site. It achieves the function of domain confusion without requiring labeling, as well as the automatic extraction of domain features and automatic adversarial training, using target domain data. Compared to deep domain confusion (DDC), naïve DANN, and the domain separation network (DSN), the proposed method achieves the highest accuracy rates of 93.17% and 91.35% in both scenarios. Furthermore, the experiment employs t-distributed stochastic neighbor embedding (t-SNE) to facilitate fast training and smoke detection between machines by leveraging domain adaption features.
ISSN:2227-7390
2227-7390
DOI:10.3390/math11173728