Quantitative Evaluation of Sugar Beet Plant Height Based on UAV-RGB and UAV-LiDAR

被引：0
|
作者：
Wang Q. [1 ]
Che Y. [1 ]
Chai H. [1 ]
Shao K. [2 ]
Li B. [1 ]
Ma Y. [1 ]
机构：
[1] College of Land Science and Technology, China Agricultural University, Beijing
[2] Agricultural Artificial Intelligence and Crop Phenotype Engineering Research Centre, Inner Mongolia Institute of Biotechnology, Huhhot
来源：
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2021年 / 52卷 / 03期
关键词：
Canopy distribution; Plant height; Sugar beet; Three-dimensional point cloud; UAV-LiDAR;
D O I：
10.6041/j.issn.1000-1298.2021.03.019
中图分类号：
学科分类号：
摘要：
Sugar beet is the world's main sugar production crop and one of the recognized alternative materials for biofuel production. Plant height of sugar beet can be used to estimate root biomass, indicate water stress, and can also be an effective indicator of nitrogen content and yield. It is an important parameter for breeders and farm managers to assess the growth status of sugar beet in the field. The rotary-wing UAV platform has the characteristics of vertical lifting, fixed-point hovering, and strong maneuverability. It is suitable for obtaining multi-scale, multi-repeat, fixed-point, and high-resolution farmland crop information. Totally 186 genotypes of sugar beet were chosen to explore accuracy difference of estimated plant height for UAV-RGB and UAV-LiDAR system, and to do comparison with the measured value. The correlation between estimated plant height by LiDAR and measured value (straight slope was 0.99, R2 was 0.88, rRMSE was 6.6%) was higher than that measured by RGB (straight slope was 0.94, R2 was 0.8, rRMSE was 9%). Further stratification analysis of point clouds was carried out to compare the difference of point clouds distribution in the canopy. For the later growth stage with relative dense canopy, UAV-LiDAR can reconstruct a more complete three-dimensional canopy structure than that of UAV-RGB system. © 2021, Chinese Society of Agricultural Machinery. All right reserved.
引用
收藏
页码：178 / 184
页数：6
相关论文
共 39 条
  • [1] ANAR M J, LIN Z, HOOGENBOOM G, Et al., Modeling growth, development and yield of sugarbeet using DSSAT, Agricultural Systems, 169, pp. 58-70, (2019)
  • [2] HOFFMANN C M, KENTER C., Yield potential of sugar beet-have we hit the ceiling?, Frontiers in Plant Science, 9, pp. 289-294, (2018)
  • [3] BU H, SHARMA L K, DENTON A, Et al., Sugar beet yield and quality prediction at multiple harvest dates using active-optical sensors, Agronomy Journal, 108, 1, pp. 12-23, (2016)
  • [4] HUSSEIN M M, KASSAB O M, ELLIL A A A., Evaluating water stress influence on growth and photosynthetic pigments of two sugar beet varieties, INSInet, 4, 6, pp. 936-941, (2008)
  • [5] MALAMBO L, POPESCU S C, MURRAY S C, Et al., Multitemporal field-based plant height estimation using 3D point clouds generated from small unmanned aerial systems high-resolution imagery, International Journal of Applied Earth Observation and Geoinformation, 64, pp. 31-42, (2018)
  • [6] LI Xia, WANG Weixin, SONG Haitang, Research of cotton altitude measurement based on ultrasonic technology, Journal of Agricultural Mechanization Research, 30, 6, pp. 187-189, (2008)
  • [7] CHANG Y K, ZAMAN Q U, REHMAN T U, Et al., A real-time ultrasonic system to measure wild blueberry plant height during harvesting, Biosystems Engineering, 157, pp. 35-44, (2017)
  • [8] SARBOLAND H., Kinect range sensing: structured-light versus Time-of-Flight Kinect, Computer Vision and Image Understanding, 139, pp. 1-20, (2015)
  • [9] ZONG Ze, GUO Cailing, ZHANG Xue, Et al., Maize plant type parameters extraction based on depth camera, Transactions of the Chinese Society for Agricultural Machinery, 46, pp. 50-56, (2015)
  • [10] SUN S, LI C, PATERSON A H., In-field high-throughput phenotyping of cotton plant height using LiDAR, Remote Sensing, 9, 4, pp. 377-397, (2017)
1234