基于深度学习的遥感影像数据库构建分析

Research on Construction of Database of Remote-sensing Image Based on Deep Learning

基于深度学习遥感影像目标识别前提在于构建大规模高质量影像识别基准库,以便模拟,识别算法快速准确地提取图像特征。本文详细分析了深度卷积网络驱动下遥感影像数据库的整体构建方法、规模、属性等信息,同时展望了遥感影像数据构建的趋势。

The premise of object of remote-sensing image based on deep learning is construction of reference library of large-scale and high quality image recognition in order to quickly and precisely extracts image features by mode and algorithm.In this paper,the authors expounded integral construction methods,scale and property under condition of internet-driven of deep convolution,and prospected trend of building data of remote-sensing image.