English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fire-detection technology is of great importance for successfulfire-prevention measures. Image-based fire detection is one effective method.At present, object-detection algorithms are deficient in performing detectionspeed and accuracy tasks when they are applied in complex fire scenarios. Inthis study, a lightweight fire-detection algorithm, Light-YOLOv5 (You Only LookOnce version five), is presented. First, a separable vision transformer(SepViT) block is used to replace several C3 modules in the final layer of abackbone network to enhance both the contact of the backbone network to globalin-formation and the extraction of flame and smoke features; second, a lightbidirectional feature pyramid network (Light-BiFPN) is designed to lighten themodel while improving the feature extraction and balancing speed and accuracyfeatures during a fire-detection procedure; third, a global attention mechanism(GAM) is fused into the network to cause the model to focus more on the globaldimensional features and further improve the detection accuracy of the model;and finally, the Mish activation function and SIoU loss are utilized tosimultaneously increase the convergence speed and enhance the accuracy. Theexperimental results show that compared to the original algorithm, the meanaverage accuracy (mAP) of Light-YOLOv5 increases by 3.3%, the number ofparameters decreases by 27.1%, and the floating point operations (FLOPs)decrease by 19.1%. The detection speed reaches 91.1 FPS, which can detecttargets in complex fire scenarios in real time.

Light-YOLOv5: A Lightweight Algorithm for Improved YOLOv5 in Complex Fire Scenarios