Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic Segmentation

Intelligent pruning technology is significant in reducing management costs and improving operational efficiency. In this study, a branch recognition and pruning point localization method was proposed for dormant walnut (<i>Juglans regia</i> L.) trees. First, 3D point clouds of walnut tre...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Zhu, Xiaopeng Bai, Daochun Xu, Wenbin Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Agriculture
Subjects:
Online Access:https://www.mdpi.com/2077-0472/15/8/817
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712230265782272
author Wei Zhu
Xiaopeng Bai
Daochun Xu
Wenbin Li
author_facet Wei Zhu
Xiaopeng Bai
Daochun Xu
Wenbin Li
author_sort Wei Zhu
collection DOAJ
description Intelligent pruning technology is significant in reducing management costs and improving operational efficiency. In this study, a branch recognition and pruning point localization method was proposed for dormant walnut (<i>Juglans regia</i> L.) trees. First, 3D point clouds of walnut trees were reconstructed from multi-view images using Neural Radiance Fields (NeRFs). Second, Walnut-PointNet was improved to segment the walnut tree into Trunk, Branch, and Calibration categories. Next, individual pruning branches were extracted by cluster analysis and pruning rules were adjusted by classifying branches based on length. Finally, Principal Component Analysis (PCA) was used for length extraction, and pruning points were determined based on pruning rules. Walnut-PointNet achieved an OA of 93.39%, an ACC of 95.29%, and an mIoU of 0.912 on the walnut tree dataset. The mean absolute errors in length extraction for the short-growing branch group and the water sprout were 28.04 mm and 50.11 mm, respectively. The average success rate of pruning point recognition reached 89.33%, and the total time for pruning branch recognition and pruning point localization for the entire tree was approximately 16 s. This study provides support for the development of intelligent pruning for walnut trees.
format Article
id doaj-art-4a5e5f91cf4c49bb9899b269b4510f9c
institution DOAJ
issn 2077-0472
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Agriculture
spelling doaj-art-4a5e5f91cf4c49bb9899b269b4510f9c2025-08-20T03:14:20ZengMDPI AGAgriculture2077-04722025-04-0115881710.3390/agriculture15080817Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic SegmentationWei Zhu0Xiaopeng Bai1Daochun Xu2Wenbin Li3School of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaSchool of Technology, Beijing Forestry University, Beijing 100083, ChinaIntelligent pruning technology is significant in reducing management costs and improving operational efficiency. In this study, a branch recognition and pruning point localization method was proposed for dormant walnut (<i>Juglans regia</i> L.) trees. First, 3D point clouds of walnut trees were reconstructed from multi-view images using Neural Radiance Fields (NeRFs). Second, Walnut-PointNet was improved to segment the walnut tree into Trunk, Branch, and Calibration categories. Next, individual pruning branches were extracted by cluster analysis and pruning rules were adjusted by classifying branches based on length. Finally, Principal Component Analysis (PCA) was used for length extraction, and pruning points were determined based on pruning rules. Walnut-PointNet achieved an OA of 93.39%, an ACC of 95.29%, and an mIoU of 0.912 on the walnut tree dataset. The mean absolute errors in length extraction for the short-growing branch group and the water sprout were 28.04 mm and 50.11 mm, respectively. The average success rate of pruning point recognition reached 89.33%, and the total time for pruning branch recognition and pruning point localization for the entire tree was approximately 16 s. This study provides support for the development of intelligent pruning for walnut trees.https://www.mdpi.com/2077-0472/15/8/817walnut treeintelligent pruning3D point cloudsemantic segmentationPointNet++branch recognition
spellingShingle Wei Zhu
Xiaopeng Bai
Daochun Xu
Wenbin Li
Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic Segmentation
Agriculture
walnut tree
intelligent pruning
3D point cloud
semantic segmentation
PointNet++
branch recognition
title Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic Segmentation
title_full Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic Segmentation
title_fullStr Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic Segmentation
title_full_unstemmed Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic Segmentation
title_short Pruning Branch Recognition and Pruning Point Localization for Walnut (<i>Juglans regia</i> L.) Trees Based on Point Cloud Semantic Segmentation
title_sort pruning branch recognition and pruning point localization for walnut i juglans regia i l trees based on point cloud semantic segmentation
topic walnut tree
intelligent pruning
3D point cloud
semantic segmentation
PointNet++
branch recognition
url https://www.mdpi.com/2077-0472/15/8/817
work_keys_str_mv AT weizhu pruningbranchrecognitionandpruningpointlocalizationforwalnutijuglansregiailtreesbasedonpointcloudsemanticsegmentation
AT xiaopengbai pruningbranchrecognitionandpruningpointlocalizationforwalnutijuglansregiailtreesbasedonpointcloudsemanticsegmentation
AT daochunxu pruningbranchrecognitionandpruningpointlocalizationforwalnutijuglansregiailtreesbasedonpointcloudsemanticsegmentation
AT wenbinli pruningbranchrecognitionandpruningpointlocalizationforwalnutijuglansregiailtreesbasedonpointcloudsemanticsegmentation