PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 11, 2026Sensors1 citationsOpen Access

A Lightweight Fire Detection Framework for Edge Visual Sensors Using Small-Sample Domain Adaptation

JHJie HuRYRuitong YaoQYQingyuan Yang

Key Points

  • This research aims to enhance fire detection in visual sensor networks by integrating a novel framework with domain adaptation techniques.
  • Constructed a high-dimensional feature vector using HSI color statistics, LBP dynamic textures, and wavelet transform features.
  • Trained a baseline support vector machine classifier on source domain data.
  • Introduced a small-sample domain adaptation mechanism to fine-tune the model with minimal target domain samples.
  • Improved fire detection by increasing the F1-score by 19% in daytime scenarios and 30% at nighttime compared to traditional methods.
  • Achieved high precision and robustness in cross-scenario fire detection suitable for edge computing.

Abstract

Addressing the challenges in vision-based sensor networks, this study proposes a novel fire detection framework combining Multi-Feature Fusion and Adaptive Support Vector Machine (A-SVM). First, a high-dimensional feature vector is constructed by fusing HSI color space statistics, Local Binary Pattern (LBP) dynamic textures, and Wavelet Transform shape features. A baseline SVM classifier is then trained on source domain data. Second, to overcome the difficulty of acquiring labeled samples in target domains (e.g., strong daytime interference or low nighttime illumination), a small-sample domain adaptation mechanism is introduced. This mechanism fine-tunes the source model parameters using only a few labeled samples from the target domain via regularization constraints. Experimental results demonstrate that, compared with traditional color thresholding methods and unadapted baseline SVMs, the proposed method increases the F1-score by 19% and 30% in typical daytime and nighttime cross-domain scenarios, respectively. This study effectively achieves low-cost, high-precision, and robust cross-scenario fire detection, making it highly suitable for deployment on resource-constrained edge computing nodes within smart sensor networks.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Hu et al. (2026) studied this question.

synapsesocial.com/papers/698c1ca1267fb587c655f33dhttps://doi.org/10.3390/s26041121
Ask AI
Helpful
Bookmark
Share
View Full Paper