Method and system for dynamic acquisition and analysis of tomato 3D phenotype in the whole growth period

Abstract

The invention discloses a method and system for dynamically acquiring and analyzing tomato 3D phenotypes in the whole growth period. The method includes: obtaining environmental difference distribution maps based on environmental monitoring and determining target individual plants; obtaining multi-view image sequences of the whole growth period based on image acquisition; obtaining local scene point clouds based on 3D reconstruction; obtaining complete Point cloud and lobes point cloud; organ segmentation based on point search based on adjacency relationship to realize the extraction of each node and each leaf; automatic extraction and calculation of phenotypic parameters on the basis of organ segmentation; for the same single plant in different periods Point cloud, using real topological structure to achieve phenotypic parameter registration; data analysis based on environmental differences and phenotypic registration results. The invention combines the environmental difference with the tomato 3D phenotype in the whole growth period, and does not need to set a threshold or manually mark the algorithm, and can adapt to the extraction and registration of tomato phenotype parameters in different periods.

Description

technical field [0001] The invention belongs to the field of agricultural automation, and in particular relates to automatic measurement of tomato phenotype parameters, in particular to a method and system for dynamically acquiring and analyzing tomato 3D phenotypes in the whole growth period. Background technique [0002] Tomato is one of the most valuable vegetable crops in the world. As one of the three major tomato growing regions in the world, my country has a pivotal position in the international market. High yield and high quality are the important goals of tomato cultivation. However, the acquisition of tomato phenotypic data still mainly relies on the traditional phenotypic analysis method, which is time-consuming, labor-intensive, cumbersome, highly subjective and easy to cause damage to tomato, which seriously hinders the development of tomato cultivation technology. [0003] In the prior art, it is proposed to use the laser scanner to obtain the three-dimensiona...

AI Technical Summary

Problems solved by technology

However, the acquisition of tomato phenotypic data still mainly relies on the traditional phenotypic analysis method, which is time-consuming, labor-intensive, cumbersome, highly subjective and easy to cause damage to tomato, which seriously hinders the development of tomato cultivation technology

[0003] In the prior art, it is proposed to use the laser scanner to obtain the three-dimensional information of the plant and the canopy surface to estimate the leaf area, leaf area index and plant height, but the hardware equipment is expensive and the data is redundant; the point cloud data of the plant is obtained by three-dimensional reconstruction Combined with the region growing algorithm, deep learning, etc. to complete the extraction of individual plants or main stems, however, different thresholds and manual labeling are required for different individual plants, and accurate extraction cannot be achieved for the characteristics of the curved main stem of tomato

Images