Machine learning-based crop recognition from aerial remote sensing imagery

作     者：Yanqin TIAN Chenghai YANG Wenjiang HUANG Jia TANG Xingrong LI Qing ZHANG Yanqin TIAN;Chenghai YANG;Wenjiang HUANG;Jia TANG;Xingrong LI;Qing ZHANG

作者机构：Key Laboratory of Digital Earth ScienceAerospace Information Research InstituteChinese Academy of SciencesBeijing 100094China USDA-Agricultural Research ServiceAerial Application Technology Research UnitCollege StationTX 77845USA 

出 版 物：《Frontiers of Earth Science》 (地球科学前沿（英文版）)

年 卷 期：2021年第15卷第1期

页      面：54-69页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 0708[理学-地球物理学] 0704[理学-天文学] 081002[工学-信号与信息处理] 

基　　金：supported by the National Key Research and Development Program(No.2020YFD1100204) the Provincial Key Basic Research Project(No.2019AB002) 

主　　题：machine learning crop recognition aerial imagery dynamic recognition static recognition 

摘      要：Timely and accurate acquisition of crop distribution and planting area information is important for making agricultural planning and management *** study employed aerial imagery as a data source and machine learning as a classification tool to statically and dynamically identify crops over an agricultural cropping *** analysis of pixel-based and object-based classifications was performed and classification results were further refined based on three types of object features(layer spectral,geometry,and texture).Static recognition using layer spectral features had the highest accuracy of 75.4%in object-based classification,and dynamic recognition had the highest accuracy of 88.0%in object-based classification based on layer spectral and geometry *** identification could not only attenuate the effects of variations on planting dates and plant growth conditions on the results,but also amplify the differences between different ***-based classification produced better results than pixel-based classification,and the three feature sets(layer spectral alone,layer spectral and geometry,and all three)resulted in only small differences in accuracy in object-based *** recognition combined with objectbased classification using layer spectral and geometry features could effectively improve crop classification accuracy with high resolution aerial *** methodologies and results from this study should provide practical guidance for crop identification and other agricultural mapping applications.