<![CDATA[Detecting smoke covering different environmental situations is an explanatory task while mitigating the loss of lives or reducing the fire-based disaster. Various approaches were experimented with to tackle this task. A few of them are convenient, whereas many fail in outcomes. To that end, this research presents a comparative analysis of two region-based detection models based on deep neural networks. Faster R-CNN denotes the Region-based Convolutional Neural Network, and R-FCN, which constitutes the Region-based Fully Convolutional Network, is employed in this research to evaluate detection performance for the smoke detection task. The analysis demonstrates these models with respect to detection accuracy, precision, recall, Intersection over Union, detection speed, and resilience to challenging conditions (e.g., variations in lighting, weather, and complex backgrounds). Research results highlight Faster R-CNN's accuracy, which supports applications in fire-smoke prevention, whereas R-FCN focuses on detection speed, which is relevant to the smoke-monitoring sector. The key issue to consider is the trade-off between computational efficiency and detection accuracy. Performance in extreme environmental conditions can be enhanced through further advances with regard to data variability and typical challenging scenarios. Moreover, Faster R-CNN and R-FCN achieved Precision values of 96.72% and 95.46%, Recall values of 97.66% and 95.73%, and F1-Score values of 97.18% and 95.59%, respectively. This study assumes further assessments to ensure the safety of the living.]]>
Copyrights © 2025
