A method and system for extracting growth parameters of fruit tree leaves based on clustering and segmentation

Abstract

The invention provides a method and system for extracting growth parameters of fruit tree leaves based on clustering and segmentation, comprising: performing super-volume clustering on the point cloud data of branches and leaves in the canopy of the target fruit tree, and performing a super-volume clustering on multiple voxel block sets obtained Perform LCCP clustering on adjacent voxel blocks to obtain the first clustering set; use dynamic K value to perform Kmeans clustering on any point group in the first clustering set to obtain the second clustering set; according to the points in the second clustering set Based on the point cloud data corresponding to the group, the growth parameters of each leaf are obtained based on the boundary extraction. After the point group obtained by super-body clustering is segmented by LCCP clustering, the Kmeans clustering algorithm based on the dynamic K value is further used. The improvement of the clustering Kmeans algorithm can automatically obtain the K value, which overcomes the need for manual setting in the traditional algorithm. The shortcomings of the fixed K value make the point cloud data segmentation of the canopy branches and leaves of the target fruit tree more complete and thorough, and then extract the leaf growth parameters more accurately.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of three-dimensional reconstruction, and more specifically, to a method and system for extracting growth parameters of fruit tree leaves based on clustering and segmentation. Background technique [0002] The canopy of fruit trees is the main place for photosynthesis of fruit trees. The morphological structure and spatial distribution of its branches and leaves directly affect the quality and yield of fruits. Clustering and segmenting the branches and leaves of fruit trees and further extracting the growth parameters of leaves can provide a comprehensive overview of the morphological structure of the canopy of fruit trees. Analysis and calculation of light distribution and fruit tree shaping and pruning provide a theoretical basis. Scholars at home and abroad have carried out a lot of work on tree point cloud data processing and growth parameter extraction. With the increase in the prod...

AI Technical Summary

Problems solved by technology

[0004] At present, there are relatively few studies on the clustering and segmentation of fruit tree leaves with large trees. Most of the clustering and segmentation methods are aimed at the segmentation of independent objects in scene files, or the segmentation of planes and cylinders with regular characteristics. The point cloud segmentation clustering method for fruit tree leaves is also more inclined to fruit trees with larger leaves, fewer numbers, and opposite phyllotaxy. The data complexity is low, and the requirements for the robustness and applicability of the algorithm are relatively low.

For example, for common apple trees, since the leaves of apple trees are smaller and denser and the growth phyllotaxy is spiral, the extraction of growth parameters has higher requirements on the integrity and detailed description of the leaf point cloud. The traditional Kmeans algorithm, DBSCAN density aggregation The results obtained by the class algorithm and the Region-growing algorithm cannot obtain a complete single leaf, and are not suitable for the clustering and segmentation of branch and leaf point clouds with small and compact leaves such as apples and apple trees and whose growth phyllotaxy is spiral, which leads to The extracted leaf growth parameters are inaccurate

[0005] For the extraction of leaf growth parameters, most of the existing technologies use the projection method to reduce the dimension of the 3D point cloud and convert it into a 2D image to solve the longest and shortest distances as the leaf length and leaf width, but ignore the leaf in space. Conditions such as curling occur, resulting in a decrease in the resulting growth parameter compared to the true value

Images