| 刍议服务于深度学习研究的林业遥感数据集建设 |
| |
| 引用本文： | 武红敢,王成波. 刍议服务于深度学习研究的林业遥感数据集建设[J]. 世界林业研究, 2021, 34(3): 58-62. DOI: 10.13348/j.cnki.sjlyyj.2020.0124.y |
| |
| 作者姓名： | 武红敢 王成波 |
| |
| 作者单位： | 中国林业科学研究院资源信息研究所,北京100091;国家林业和草原局林业遥感与信息技术实验室,北京100091;中国科学院空天信息创新研究院,北京100101 |
| |
| 基金项目： | “十三五”国家重点研发计划“野果林病虫害控制技术与监测、预警体系构建”（2016YFC0501503） |
| |
| 摘 要： | 林业遥感数据集是林草行业开展深度学习研究的重要基础,更是林草资源实现自动化、智能化和动态化精准监测的重要保障.文中分析了自然图像和遥感图像数据集建设现状与方法,通过对深度学习算法在林业专题信息识别和分类中最新研究成果的阐述,表明建立林业遥感专用数据集的必要性和紧迫性;基于人工智能在图像处理领域的发展经验,提出林草业遥感...
|
| 关 键 词： | 林草资源 精准监测 深度学习 遥感数据集 资源共享 |
| 收稿时间： | 2020-09-05 |
Construction of Forestry Remote Sensing Dataset for Deep Learning |
| |
| Affiliation: | 1.Research Institute of Forest Resources Information Techniques, Chinese Academy of Forestry, Beijing 100091, China2.Laboratory of Forestry Remote Sensing and Information System, National Forestry and Grassland Administration, Beijing 100091, China3.Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China |
| |
| Abstract: | Forestry remote sensing dataset is the important basis for the forestry and grassland sector to carry out deep learning, and also the vital guarantee for the automatic, intelligent and dynamic monitoring of grassland and forest resources. This paper analyzes the status and methods of the natural images and remote sensing image dataset construction, and then expounds the necessity and urgency of building special forestry remote sensing dataset by introducing the latest research achievements in using the deep learning algorithms for special forestry information recognition and classification. At the end, the paper proposes the ideas and principles to construct the forestry and grassland remote sensing image dataset based on the development of artificial intelligence in image processing field. |
| |
| Keywords: | |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《世界林业研究》浏览原始摘要信息 |
|
点击此处可从《世界林业研究》下载全文 |
|
