Filters








2 Hits in 2.0 sec

wUUNet: Advanced Fully Convolutional Neural Network for Multiclass Fire Segmentation

Vladimir Sergeevich Bochkov, Liliya Yurievna Kataeva
2021 Symmetry  
The UNet model is used as a baseline for the initial solution because it is the best open-source convolutional neural network. There is no available open dataset for multiclass fire segmentation.  ...  This article describes an AI-based solution to multiclass fire segmentation. The flame contours are divided into red, yellow, and orange areas.  ...  Discussion This article describes a detailed solution to multiclass fire image segmentation using an advanced neural-network architecture known as UNet.  ... 
doi:10.3390/sym13010098 fatcat:ss5tqqk2lza2bd4hp3uajoyllm

СЕГМЕНТАЦИЯ ПЛАМЕНИ НА ИЗОБРАЖЕНИИ С ИСПОЛЬЗОВАНИЕМ СВЁРТОЧНОЙ НЕЙРОННОЙ СЕТИ U-NET

Братухин Д.
2021
The article will consider convolutional neural networks for identifying a flame in an image. The U-net archi-tecture will be used as the main algorithm for implementing flame segmentation.  ...  WUUNet: Advanced fully convolutional neural network for multiclass fire segmentation // Symmetry. -2021. -Vol. 13. -No 1. -P. 1-18. -DOI 10.3390/sym13010098. 9.  ...  Использование свёрточных нейронных сетей (англ. convolutional neural network, CNN) позволяет решить данную задачу. CNN -является подразделом искусственных нейронных сетей.  ... 
doi:10.24412/3453-9875-2021-64-31-33 fatcat:5oxz5to6cfgg5ni77wefargjjm