.png){kind=icon}
Return
A deep learning framework for autonomous flame detection
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2021.03.019.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper proposes a novel framework of flame region-based convolutional neural network for autono-mous flame detection. The task of flame detection is especially challenging since flames have greater diversity in colour, texture, and shape than regular rigid objects. To cope with these difficulties due to the various appearances and unclear edges of flames, a proposal generation approach is developed to effectively select candidate flame regions based on two crucial properties of flames, i.e., their dynamics and colours. The candidate flame regions together with a convolutional feature map are further processed by additional layers to output detected flames. The diversity in flame colours is well represented by approximating the distribution using a Dirichlet Process Gaussian mixture model with variational infer-ence. The proposed framework is evaluated on publicly available videos and achieves an average frame-wise accuracy higher than 88%, which outperforms the state-of-the-art methods.& nbsp; (c) 2021 Elsevier B.V. All rights reserved.
Keywords:
Flame detection
Flame R-CNN
Dirichlet process Gaussian mixture model
Variational inference
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
ShareSaveA dividing-based many-objective evolutionary algorithm for large-scale feature selection.png)
SOFT COMPUTING
SOFT COMPUTINGIF2.5
PREAI
ShareSaveShareSaveShareSaveShareSaveFaster R-CNN for marine organisms detection and recognition using data augmentationNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
ShareSaveShareSave
View more