Litcius/Paper detail

Video-based Fire Smoke Detection Using Temporal-spatial Saliency Features

Zili Zhang, Qingyong Jin, Lina wang, Zhiguo Liu

2022Procedia Computer Science18 citationsDOIOpen Access PDF

Abstract

In this paper, we propose a video based spatial-temporal convolutional neural network for fire smoke recognition. The model concatenates the appearance features and the motion features followed by a convolution layer to implement spatial-temporal feature fusion. To reduce the influence of background of no-smoke, we use an attention module to capture salience features from the input image. Experiments on the self-created dataset show that the presented method is valid, which achieves a detection rate of 97.5% and accuracy rate of 96.8%.

Topics & Concepts

Computer scienceArtificial intelligenceConvolutional neural networkSalience (neuroscience)SmokeConvolution (computer science)Pattern recognition (psychology)Feature (linguistics)Computer visionOptical flowFire detectionImage (mathematics)Artificial neural networkMeteorologyPhysicsThermodynamicsLinguisticsPhilosophyFire Detection and Safety SystemsVideo Surveillance and Tracking MethodsImage Enhancement Techniques
Video-based Fire Smoke Detection Using Temporal-spatial Saliency Features | Litcius