期刊论文

Self-supervised forest fire recognition based on visual transformation network

中文

中南林业科技大学学报

1673-923X

2023

43

7

32-40

10.14067/j.cnki.1673-923x.2023.07.003

国家自然科学基金项目(31570627)。

本校为第一机构

【目的】森林火灾识别是避免森林火灾大面积蔓延的一项重要研究。随着深度学习的快速发展,基于卷积神经网络的模型因其在图像识别领域的优异表现,被广泛应用到森林火灾识别任务当中。然而,基于卷积神经网络的方法通常在标签数据不充分时...展开更多 【目的】森林火灾识别是避免森林火灾大面积蔓延的一项重要研究。随着深度学习的快速发展,基于卷积神经网络的模型因其在图像识别领域的优异表现,被广泛应用到森林火灾识别任务当中。然而,基于卷积神经网络的方法通常在标签数据不充分时,难以取得令人满意的森林火灾识别结果。【方法】本研究提出了一种基于视觉变换网络的自监督森林火灾识别模型(Se...

【Objective】Forest fire identification is important for avoiding forest fire spreading in a large area.With the rapid development of deep learning,the model based on convolution neural network has been widely used in forest fire recognition tasks because of its excellent...MORE 【Objective】Forest fire identification is important for avoiding forest fire spreading in a large area.With the rapid development of deep learning,the model based on convolution neural network has been widely used in forest fire recognition tasks because of its excelle...