基于无人机三维点云的玉米植株自动计数研究. (Chinese)
In: Acta Agriculturae Zhejiangensis, Jg. 34 (2022-09-01), Heft 9, S. 2032-2042
academicJournal
Zugriff:
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. [ABSTRACT FROM AUTHOR]
植株计数是农民、育种专家等在整个作物生长季评估作物生长状况和管理实践的最常用方法之一, 可用来进行合理的田间规划以及管理. 针对高密度种植试验区高通量获取玉米自动株数方法匮乏的问题, 本研究利用无人机遥感平台, 获取田间 314 个不同基因型的玉米高密度育种小区的数码影像和激光雷达 (light detection and ranging, LiDAR) 点云数据, 发展了一种结合玉米三维空间信息的固定窗口局部最大值算法, 实现了高密度玉米育种小区成株数的自动检测, 并对比了基于此两种不同数据源的检测精度. 该方法以冠层高度模型 (canopy height model, CHM) 中包含的株高信息为基础, 以玉米种植株距为固定窗口进行单株玉米种子点检测, 并将检测到的种子点与目视解译的玉米位置进行空间匹配来进行精度的评估. 结果表明, 基于无人机数码影像构建 3 种空间分辨率 CHM 的综合检测精度分别为 81.30%、83.11%和78.93%; 基于无人机 LiDAR 的综合精度分别为 82.33%、88.66% 和 81.46%; 基于两种数据源构建的 CHM, 均在空间分辨率为 0.05 m 时, 获得最佳的检测精度. 此外, 当空间分辨率相同时, LiDAR 数据检测精度略优于无人机数码影像, 无人机数码传感器由于其成本低、易于操作等优势, 在大面积、高密度育种小区的玉米高通量单株检测中表现出更大的潜力. 本研究实现了对密植玉米育种试验区玉米株数的自动计数, 为表型筛选、田间管理和精准估产等提供依据. [ABSTRACT FROM AUTHOR]
Copyright of Acta Agriculturae Zhejiangensis is the property of Acta Agriculturae Zhejiangensis Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Titel: |
基于无人机三维点云的玉米植株自动计数研究. (Chinese)
|
---|---|
Autor/in / Beteiligte Person: | 姜友谊 ; 张成健 ; 韩少宇 ; 杨小冬 ; 杨贵军 ; 杨浩 |
Zeitschrift: | Acta Agriculturae Zhejiangensis, Jg. 34 (2022-09-01), Heft 9, S. 2032-2042 |
Veröffentlichung: | 2022 |
Medientyp: | academicJournal |
ISSN: | 1004-1524 (print) |
DOI: | 10.3969/j.issn.1004-1524.2022.09.22 |
Schlagwort: |
|
Sonstiges: |
|