التفاصيل البيبلوغرافية
| العنوان: |
深度学习与遥感数据分析. |
| العنوان البديل: |
Deep Learning and Remote Sensing Data Analysis. |
| المؤلفون: |
张立强1 zhanglq@bnu.edu.cn, 李 洋1, 侯正阳1, 李新港1, 耿 昊1, 王跃宾2, 李景文3, 朱盼盼1, 梅 杰1, 姜颜笑1, 李帅朋1, 辛 奇1, 崔 颖1, 刘素红1 |
| المصدر: |
Geomatics & Information Science of Wuhan University. Dec2020, Vol. 45 Issue 12, p1857-1864. 8p. |
| مصطلحات موضوعية: |
*REMOTE-sensing images, *REINFORCEMENT learning, *OPTICAL remote sensing, *REMOTE sensing, *ELECTRONIC data processing, *DEEP learning, *POVERTY reduction |
| مصطلحات جغرافية: |
QINGHAI Sheng (China), TIBET (China) |
| الملخص (بالإنجليزية): |
The rapid development of deep learning provides an important technical means for intelligent analysis of remote sensing big data. Firstly, this paper mainly introduces the deep learning modes in remote sensing data recognition and application, and proposes a deep reinforcement learning, multi ⁃ task learning and sub ⁃ pixel ⁃ pixel ⁃ super ⁃ pixel feature learning models for object features recognition from LiDAR point clouds, optical remote sensing images and hyperspectral images. The model parameters are basically ob⁃ tained by learning, and thus the workload of the parameter adjustments is small. The spatial and contextual information, texture and spectral characteristics between ground objects are fully taken into account, so the presented models have good generalization abilities. Then, it describes the progress in terms of the joint deep learning and multi ⁃ source remote sensing data in accurate poverty alleviation assessment, wetland change and spatial analysis in Qinghai ⁃Tibet Plateau in the past 20 years, and corn yield estimation. In or⁃ der to better promote the transformation from remote sensing data to knowledge, it is necessary give full play to the advantages of deep learning in remote sensing big data processing, and develop new data pro⁃ cessing algorithms and technologies. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): |
深度学习的迅猛发展，为遥感大数据的智能分析提供了重要技术手段。首先主要介绍了遥感数据识 别和应用中设计的深度学习模型与方法，提出并实现了面向激光雷达点云、光学遥感图像和高光谱图像等数 据地物识别的深度强化学习、多任务学习和亚像素⁃像素⁃超像素特征学习网络模型。这类模型的参数基本上 由学习得到，调参工作量小，而且充分顾及了地物间的空间和上下文信息以及纹理和光谱特征，泛化能力强。 然后描述了联合深度学习和多源遥感数据在精准扶贫评估、青藏高原 20 a 湿地变化及空间分析和玉米产量估 产等方面的研究进展。从中可以看出，为了更好地促进遥感数据向知识的转化，需要面向应用，充分发挥深度 学习在遥感大数据处理的优势，发展新的数据处理算法与技术。 [ABSTRACT FROM AUTHOR] |
| قاعدة البيانات: |
Academic Search Index |
