Deep Neural Network with Walsh-Hadamard Transform Layer for Ember Detection During a Wildfire
Abstract
In this article, we describe an ember detection method in infrared (IR) video. Embers, also called firebrands, can act as wildfire super-spreaders. We develop a novel neural network with a Walsh-Hadamard Transform (WHT) layer to process the IR video. The WHT layer is used to process the temporal dimension of the video data to model the high-frequency activity due to ember movements. We insert the WHT layer to ResNet-18 and obtained higher accuracy compared to the standard single slice ResNet-18 and the ResNet-18 processing the entire video block. We also repeat the experiments on ResNet-34, but we found that ResNet-18 is sufficient for this task. Therefore, we choose the ResNet-18 with the WHT layer as the proposed model.
Cite
Text
Pan et al. "Deep Neural Network with Walsh-Hadamard Transform Layer for Ember Detection During a Wildfire." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022. doi:10.1109/CVPRW56347.2022.00040Markdown
[Pan et al. "Deep Neural Network with Walsh-Hadamard Transform Layer for Ember Detection During a Wildfire." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022.](https://mlanthology.org/cvprw/2022/pan2022cvprw-deep/) doi:10.1109/CVPRW56347.2022.00040BibTeX
@inproceedings{pan2022cvprw-deep,
title = {{Deep Neural Network with Walsh-Hadamard Transform Layer for Ember Detection During a Wildfire}},
author = {Pan, Hongyi and Badawi, Diaa and Chen, Chang and Watts, Adam C. and Koyuncu, Erdem and Çetin, Ahmet Enis},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2022},
pages = {256-265},
doi = {10.1109/CVPRW56347.2022.00040},
url = {https://mlanthology.org/cvprw/2022/pan2022cvprw-deep/}
}