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 is one of the common disasters in daily life. To achieve fast andaccurate detection of fires, this paper proposes a detection network calledFSDNet (Fire Smoke Detection Network), which consists of a feature extractionmodule, a fire classification module, and a fire detection module. Firstly, adense connection structure is introduced in the basic feature extraction moduleto enhance the feature extraction ability of the backbone network and alleviatethe gradient disappearance problem. Secondly, a spatial pyramid poolingstructure is introduced in the fire detection module, and the Mosaic dataaugmentation method and CIoU loss function are used in the training process tocomprehensively improve the flame feature extraction ability. Finally, in viewof the shortcomings of public fire datasets, a fire dataset called MS-FS(Multi-scene Fire And Smoke) containing 11938 fire images was created throughdata collection, screening, and object annotation. To prove the effectivenessof the proposed method, the accuracy of the method was evaluated on twobenchmark fire datasets and MS-FS. The experimental results show that theaccuracy of FSDNet on the two benchmark datasets is 99.82% and 91.15%,respectively, and the average precision on MS-FS is 86.80%, which is betterthan the mainstream fire detection methods.

FSDNet-An efficient fire detection network for complex scenarios based on YOLOv3 and DenseNet