A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud
The accurate measurement of orchard canopy volume serves as a crucial foundation for wind regulation and dosage adjustments in precision orchard management. However, existing methods for measuring canopy volume fail to satisfy the high precision and real-time requirements necessary for accurate vari...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/2/130 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589505681424384 |
|---|---|
| author | Na Guo Ning Xu Jianming Kang Guohai Zhang Qingshan Meng Mengmeng Niu Wenxuan Wu Xingguo Zhang |
| author_facet | Na Guo Ning Xu Jianming Kang Guohai Zhang Qingshan Meng Mengmeng Niu Wenxuan Wu Xingguo Zhang |
| author_sort | Na Guo |
| collection | DOAJ |
| description | The accurate measurement of orchard canopy volume serves as a crucial foundation for wind regulation and dosage adjustments in precision orchard management. However, existing methods for measuring canopy volume fail to satisfy the high precision and real-time requirements necessary for accurate variable-rate applications in fruit orchards. To address these challenges, this study develops a canopy volume measurement model for orchard spraying using LiDAR point cloud data. In the domain of point cloud feature extraction, an improved Alpha Shape algorithm is proposed for extracting point cloud contours. This method improves the validity judgment for contour line segments, effectively reducing contour length errors on each 3D point cloud projection plane. Additionally, improvements to the mesh integral volume method incorporate the effects of canopy gaps in height difference calculations, significantly enhancing the accuracy of canopy volume estimation. For feature selection, a random forest-based recursive feature elimination method with cross-validation was employed to filter 10 features. Ultimately, five key features were retained for model training: the number of point clouds, the 2D point cloud contour along the X- and Z-projection directions, the 2D width in the Y-projection direction, and the 2D length in the Z-projection direction. During model construction, the study optimized the hyperparameters of partial least squares regression (PLSR), backpropagation (BP) neural networks, and gradient boosting decision trees (GBDT) to build canopy volume measurement models tailored to the dataset. Experimental results indicate that the PLSR model outperformed other approaches, achieving optimal performance with three principal components. The resulting canopy volume measurement model achieved an R<sup>2</sup> of 0.9742, an RMSE of 0.1879, and an MAE of 0.1161. These results demonstrate that the PLSR model exhibits strong generalization ability, minimal prediction bias, and low average prediction error, offering a valuable reference for precision control of canopy spraying in orchards. |
| format | Article |
| id | doaj-art-da014d452d084e068853bd3a54f8742c |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-da014d452d084e068853bd3a54f8742c2025-01-24T13:15:49ZengMDPI AGAgriculture2077-04722025-01-0115213010.3390/agriculture15020130A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point CloudNa Guo0Ning Xu1Jianming Kang2Guohai Zhang3Qingshan Meng4Mengmeng Niu5Wenxuan Wu6Xingguo Zhang7College of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaCollege of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 252100, ChinaCollege of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo 255000, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 252100, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 252100, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 252100, ChinaShandong Academy of Agricultural Machinery Sciences, Jinan 252100, ChinaThe accurate measurement of orchard canopy volume serves as a crucial foundation for wind regulation and dosage adjustments in precision orchard management. However, existing methods for measuring canopy volume fail to satisfy the high precision and real-time requirements necessary for accurate variable-rate applications in fruit orchards. To address these challenges, this study develops a canopy volume measurement model for orchard spraying using LiDAR point cloud data. In the domain of point cloud feature extraction, an improved Alpha Shape algorithm is proposed for extracting point cloud contours. This method improves the validity judgment for contour line segments, effectively reducing contour length errors on each 3D point cloud projection plane. Additionally, improvements to the mesh integral volume method incorporate the effects of canopy gaps in height difference calculations, significantly enhancing the accuracy of canopy volume estimation. For feature selection, a random forest-based recursive feature elimination method with cross-validation was employed to filter 10 features. Ultimately, five key features were retained for model training: the number of point clouds, the 2D point cloud contour along the X- and Z-projection directions, the 2D width in the Y-projection direction, and the 2D length in the Z-projection direction. During model construction, the study optimized the hyperparameters of partial least squares regression (PLSR), backpropagation (BP) neural networks, and gradient boosting decision trees (GBDT) to build canopy volume measurement models tailored to the dataset. Experimental results indicate that the PLSR model outperformed other approaches, achieving optimal performance with three principal components. The resulting canopy volume measurement model achieved an R<sup>2</sup> of 0.9742, an RMSE of 0.1879, and an MAE of 0.1161. These results demonstrate that the PLSR model exhibits strong generalization ability, minimal prediction bias, and low average prediction error, offering a valuable reference for precision control of canopy spraying in orchards.https://www.mdpi.com/2077-0472/15/2/130precision variable application to fruit treespoint cloud featurescanopy volumemachine learning models |
| spellingShingle | Na Guo Ning Xu Jianming Kang Guohai Zhang Qingshan Meng Mengmeng Niu Wenxuan Wu Xingguo Zhang A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud Agriculture precision variable application to fruit trees point cloud features canopy volume machine learning models |
| title | A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud |
| title_full | A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud |
| title_fullStr | A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud |
| title_full_unstemmed | A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud |
| title_short | A Study on Canopy Volume Measurement Model for Fruit Tree Application Based on LiDAR Point Cloud |
| title_sort | study on canopy volume measurement model for fruit tree application based on lidar point cloud |
| topic | precision variable application to fruit trees point cloud features canopy volume machine learning models |
| url | https://www.mdpi.com/2077-0472/15/2/130 |
| work_keys_str_mv | AT naguo astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT ningxu astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT jianmingkang astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT guohaizhang astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT qingshanmeng astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT mengmengniu astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT wenxuanwu astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT xingguozhang astudyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT naguo studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT ningxu studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT jianmingkang studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT guohaizhang studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT qingshanmeng studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT mengmengniu studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT wenxuanwu studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud AT xingguozhang studyoncanopyvolumemeasurementmodelforfruittreeapplicationbasedonlidarpointcloud |