基于深度学习的多源遥感影像输电线路通道地物智能提取研究

Research on Intelligent Feature Extraction of Transmission Line Channel From Multi-Source Remote Sensing Images Based on Deep Learning

随着深度学习技术的发展,其在遥感领域的应用也越来越广泛。深度学习已被应用于遥感影像地表覆盖分类、变化检测、建筑物提取、道路提取、遥感影像场景识别等任务的处理中。鉴于深度学习在影像处理方面的优异表现,选择将深度学习用于输电线路通道典型地物智能识别提取任务中。实验结果表明:深度学习网络用于通道典型地物智能提权,具有良好的准确度和鲁棒性,从而可为输电线路工程提供有力的技术支持。

In recent years,with the development of deep learning technology,it is more and more widely used in the field of remote sensing.Deep learning has been applied to remote sensing image surface coverage classification,change detection,building extraction,road extraction,remote sensing image scene recognition and other tasks.In view of the excellent performance of deep learning in image processing,deep learning is selected to be used in the task of intelligent recognition and extraction of typical ground features of transmission line channel.The experimental results show that the deep learning network has good accuracy and robustness,which provides strong technical support for transmission line engineering.