The content of this article comes from the "Surveying and Mapping Bulletin" No. 3 of 2024, drawing review number: GS Jing (2024) No. 0499
Extraction of maize lodging range from remote sensing images based on canopy height model
Zhao Lian1, Yu Yajie1, Liang Zhihua2
1. The Second Institute of Surveying and Mapping of Hebei Province, Shijiazhuang 050031, China; 2. Beijing Aiers Times Technology Co., Ltd., Beijing 100000, China
Keywords: unmanned aerial vehicle, remote sensing imagery, lodging, canopy height model, SVM, OSTU
Citation format: Zhao Lian, Yu Yajie, Liang Zhihua. Extraction of lodging range of maize from remote sensing images based on canopy height model[J]. Bulletin of Surveying and Mapping, 2024(3): 127-133. DOI: 10.13474/j.cnki.11-2246.2024.0322
Abstract:Accurate extraction of maize lodging range is the basis for accurate field management and maize yield loss estimation, and UAV acquisition of remote sensing images is flexible and flexible, which is a popular means for crop lodging measurement. In this paper, we propose a method for extracting the lodging range of maize based on canopy height difference by using unmanned technology. Firstly, the background soil distribution of maize was extracted by the difference vegetation index in the visible band. The height of the corn is then extracted; Finally, based on the height of maize, the lodging range of maize was extracted by SVM and OSTU automatic threshold method. The experimental results show that the classification accuracy of the three samples using the SVM method is 88.84%, 89.52% and 90.80%, respectively. The OSTU automatic threshold method was 94.61%, 89.74% and 97.20%, respectively, which was slightly better than the former. In this paper, crop lodging is extracted based on crop height as the structural characteristic parameter, and the mechanism is clear and the influence of UAV imaging instability is eliminated to a certain extent.
About author:ZHAO Lian (1987—), female, master, senior engineer, mainly engaged in remote sensing and natural resource system development research. E-mail:[email protected]
First trial: Ji Yinxiao review: Song Qifan
Final Judge: Jin Jun
information