Plant point cloud blade segmentation and phenotypic characteristic measurement method

Abstract

The invention provides a plant point cloud blade segmentation and phenotypic characteristic measurement method, comprising the steps: firstly, performing accurate point cloud three-dimensional reconstruction on potted plants by using a multi-view stereoscopic vision algorithm; secondly, removing non-blade parts in the plant point cloud by using a region and color-based filter and a normal vector difference algorithm; and then realizing single-blade segmentation on the canopy with the blade overlapping phenomenon by means of curvature information and a multi-feature region growth algorithm. Foreach single blade, a 3D bounding box of the blade is estimated by utilizing PCA, and the blade inclination angle can be calculated as an included angle between the height direction of the bounding box and the Z axis of a crop coordinate system, and the blade length and the blade width are the length and the width of the bounding box. The plant point cloud blade segmentation and phenotypic characteristic measurement method can realize automatic blade segmentation of potted plants with overlapped and clustered blades, has high precision and real-time performance for extracting phenotypic information such as blade area, blade length, blade width, blade inclination angle and the like, and is suitable for high-throughput blade phenotypic analysis.

Description

technical field [0001] The invention relates to the technical fields of digital agriculture, agricultural engineering and its automation, botany, etc., and in particular to a method for automatic leaf segmentation and phenotype measurement of plant point clouds based on multi-view three-dimensional reconstruction. Background technique [0002] Plant "phenotype" refers to a set of biological traits that can link the interaction between genotype and environment, intuitively reflect the growth state of the plant, and are the basis of all breeding processes. Plant phenotype is a comprehensive evaluation of complex traits such as plant growth and development, tolerance, resistance, structure, physiology, and yield. Usually, the quantitative analysis of plant phenotype mainly includes the following aspects: leaf characteristics, stem characteristics, fruit traits and root morphology. As the plant organ with the largest surface area, the leaf is the main place for plant photosynth...

AI Technical Summary

Problems solved by technology

On the one hand, these devices are relatively expensive and are not suitable for cost-sensitive agricultural fields

On the other hand, due to the limitation of the imaging angle, the effect is unsatisfactory for large plants with severe shading of leaves or crops with high leaf density

In addition, the existing automatic leaf segmentation methods are not suitable for plant canopies with high density

The industry has not proposed a better set of methods for measuring plant leaf phenotypes

Images