Study on extraction of apple tree crown width at different flight altitudes using multi-spectral UAV
[Objective]The objective of this study is to segment and extract the crown information by u-sing the multi-spectral image of the UAV,so as to realize the monitoring of the apple tree crown information,and analyze the influence of the UAV flight height on the extraction accuracy of the crown.[Methods]The DJI Phantom 4 multi-spectral UAV was used to capture multi-spectral images of apple trees at flight alti-tudes of 30,60,and 90 m.The acquired images were processed using DJI Terra software to generate Digital Orthophoto Maps(DOM)and Digital Surface Models(DSM).The multi-scale segmentation method and threshold-based classification were utilized to segment the apple tree crowns and extract the east-west and north-south crown width values of the target trees.The accuracy of the segmentation and extraction results was validated by comparing them with visual interpretation of segmented crowns and field measurements of crown widths for 100 apple trees.[Results]At a flight altitude of 30 m,the accuracy of individual crown seg-mentation was 84.00%.The average extraction accuracy of the east-west and north-south crown widths was 91.15%.The average R-squared value(R2)was 0.7859,and the average root mean square error(RMSE)was 0.216 6 m.At a flight altitude of 60m,the accuracy of individual crown segmentation was 81.00%.The average extraction accuracy of the crown widths was 90.31%.The average R2 was 0.7376,and the average RMSE was 0.241 6 m.At a flight altitude of 90m,the accuracy of individual crown segmentation was 73.00%.The average extraction accuracy of the crown widths was 88.88%.The average R2 was 0.710 2,and the average RMSE was 0.267 6 m.[Conclusion]The study concludes that the use of multi-spectral UAV remote sensing technology enables the monitoring of apple tree crown information possible.The results al-so indicate that flight altitude has a certain impact on the extraction accuracy.As the UAV flight altitude in-creases,the accuracy of individual crown segmentation and extraction of crown widths gradually decrease.UAV remote sensing technology offers the advantages of low cost,rapid data acquisition,and high accuracy,which can significantly improve the efficiency of orchard management for fruit growers.
国家科技期刊平台
NSTL
万方数据
