A Review of Remote Sensing in Sugarcane Mapping
A Review of Remote Sensing in Sugarcane Mapping
复制标题
DOI：
10.1109/agro-geoinformatics59224.2023.10233506
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Hui Li;L. Di;Chen Zhang;Li Lin;Liying Guo;Haoteng Zhao;Claire Guo;Ryan Hong
中科院分区：
文献类型：
--
作者：
Hui Li;L. Di;Chen Zhang;Li Lin;Liying Guo;Haoteng Zhao;Claire Guo;Ryan Hong
甘蔗是制糖产品、生物乙醇和纤维材料的重要经济作物，种植在世界各地的热带地区，如巴西、印度、中国和泰国。甘蔗空间分布数据有效地支持甘蔗管理的各种应用。越来越多的学术文章开始讨论甘蔗制图问题。此外，各种机器学习算法已用于基于不同地球观测（EO）数据的甘蔗制图，这些算法取得了可观的分类性能。本文对近年来甘蔗制图工作进行了综述。具体而言，本文旨在：(1)总结和比较不同传感器的遥感平台；(2)综述了不同机器学习方法下的甘蔗制图技术；(3)描述了当前遥感技术下甘蔗分类面临的主要挑战，并尝试探索一种高效的甘蔗制图方法。
Sugarcane, a significant essential economic crop for sugar products, bioethanol, and fiber material, is cultivated around the world near tropical regions, such as Brazil, India, China, and Thailand. The sugarcane spatial distribution data efficiently supports various applications of sugarcane management. A greater number of academic articles are heading to address sugarcane mapping. Furthermore, various machine learning algorithms have been used in sugarcane mapping based on diverse Earth Observation (EO) data that achieve considerable classification performance. This paper provides a brief review of sugarcane mapping in recent years. Specifically, this paper aims to: (1) summarizing and comparing remote sensing flatform depending on the various sensors; (2) reviewing different sugarcane mapping techniques with different machine learning methods; (3) describing the essential challenges in sugarcane classification under current remote sensing techniques and trying to discover a patient method for efficient sugarcane mapping.