Dynamic attention network for flame detection. Issue 2 (16th January 2023)

• Record Type: Journal Article
• Authors: Fang, Long; Zhang, Yunfeng; Li, Hao; Chen, Bo; Sui, Yaguang
• Is Part Of: Electronics letters. Volume 59:Issue 2(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2023-01-16
• Subjects: convolutional neural nets -- image processing -- learning (artificial intelligence) -- object detection; Electronics -- Periodicals; 621.381
• DOI: 10.1049/ell2.12690
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract: Recently, flame detection has attracted great attention. However, existing methods have the issues of low detection rates, high false alarm rates, and lack of smoke anti‐interference ability. In this letter, a novel dynamic attention‐based network (DANet) is proposed for autonomous flame detection in various scenarios. To mitigate the disturbance of smoke in images, a dynamic attention strategy is proposed to discover the potential features among scale‐awareness and spatial‐awareness. Then, based on dynamic attention module, a decoupled detection head is presented, which can predict category, regression, and object score independently to boost the performance. A self‐contained challenging flame dataset, which is multi‐scene, multiscale, and multi‐interference informative is constructed to evaluate the proposed model and organize the experiments. Extensive ablation and comparison studies on self‐labelled dataset reveal the effectiveness of the proposed dynamic attention‐based network. Abstract : Recently, flame detection has attracted great attention. However, existing methods have the issues of low detection rates, high false alarm rates, and lack of smoke anti‐interference ability. In this letter, we propose a novel dynamic attention‐based network (DANet) for autonomous flame detection in various scenarios.