Cross-sensor transfer learning for fire smoke scene detection using variable-bands multi-spectral satellite imagery aided by spectral patterns

IF 3 3区地球科学 Q2 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY

International Journal of Remote Sensing Pub Date : 2024-05-07 DOI:10.1080/01431161.2024.2343430

Liang Zhao, Jixue Liu, Stefan Peters, Jiuyong Li, Norman Mueller, Simon Oliver

引用次数: 0

Abstract

This paper addresses the challenge of training deep learning models for fire smoke scene detection from multi-sensor, multi-spectral satellite imagery, where spectral bands vary and training data i...

查看原文本刊更多论文

利用光谱模式辅助变波段多光谱卫星图像进行火灾烟雾场景探测的跨传感器迁移学习

本文探讨了从多传感器、多光谱卫星图像中训练深度学习模型进行火灾烟雾场景检测所面临的挑战。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Remote Sensing 工程技术-成像科学与照相技术

CiteScore

7.00

自引率

5.90%

发文量

219

审稿时长

4.8 months

期刊介绍： The International Journal of Remote Sensing ( IJRS) is concerned with the theory, science and technology of remote sensing and novel applications of remotely sensed data. The journal’s focus includes remote sensing of the atmosphere, biosphere, cryosphere and the terrestrial earth, as well as human modifications to the earth system. Principal topics include: • Remotely sensed data collection, analysis, interpretation and display. • Surveying from space, air, water and ground platforms. • Imaging and related sensors. • Image processing. • Use of remotely sensed data. • Economic surveys and cost-benefit analyses. • Drones Section: Remote sensing with unmanned aerial systems (UASs, also known as unmanned aerial vehicles (UAVs), or drones).