We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于无人机三维点云的玉米植株自动计数研究.
- Authors
姜友谊; 张成健; 韩少宇; 杨小冬; 杨贵军; 杨浩
- Abstract
Plant count is one of the most commonly used methods for farmers, breeders, etc. to evaluate crop growth status and management practices throughout the crop growing season, and can be used for reasonable field planning and management. High-throughput acquisition of automatic corn plant counts for high-density planting experimental areas Due to the lack of methods, this study used the UAV remote sensing platform to obtain digital images and LiDAR point cloud data of 314 high-density corn breeding plots of different genotypes in the field, and developed a combination of The fixed window local maximum algorithm based on the three-dimensional spatial information of maize realizes the automatic detection of the number of grown-up plants in high-density maize breeding plots, and compares the detection accuracy based on the two different data sources. The method is based on the canopy height model., CHM), based on the plant height information contained in the maize seed and plant distance as a fixed window, the detection of individual maize seed points is carried out, and the detected seed points are spatially matched with the visually interpreted maize position to evaluate the accuracy. The results show that the comprehensive detection accuracy of CHM with three spatial resolutions based on UAV digital images is 81.30%, 83.11% and 78.93% respectively; the comprehensive accuracy based on UAV LiDAR is 82.33%, 88.66% and 81.46% respectively ; The CHM constructed based on the two data sources achieves the best detection accuracy when the spatial resolution is 0.05 m. In addition, when the spatial resolution is the same, the detection accuracy of LiDAR data is slightly better than that of UAV digital images. Due to its advantages of low cost and easy operation, man-machine digital sensors show greater potential in high-throughput single-plant detection of maize in large-area and high-density breeding plots. The automatic counting of phenotypes provides a basis for phenotypic screening, field management and accurate yield estimation.
- Subjects
CORN breeding; DIGITAL images; REMOTE sensing; CROP growth; SPATIAL resolution; CORN seeds
- Publication
Acta Agriculturae Zhejiangensis, 2022, Vol 34, Issue 9, p2032
- ISSN
1004-1524
- Publication type
Article
- DOI
10.3969/j.issn.1004-1524.2022.09.22