Field wheat stem tiller number extraction method

Abstract

The invention discloses a field wheat stem tillering number extraction method, which comprises the following steps of obtaining the field wheat point clouds through a laser radar, extracting any row of wheat point clouds in a research area, projecting a Y axis to a plane, keeping the X axis and the Z axis, and applying adaptive layering to obtain the cluster number of the row of wheat; applying the hierarchical clustering analysis to obtain the tillering number of each cluster of wheat, and further obtaining the stem tillering number of the whole row of wheat, so that the field wheat stem tillering number is extracted. The feasibility of the algorithm is verified by comparing the wheat stem tillering number extracted by the method with the field measured stem tillering number, which indicates that the method disclosed by the invention realizes rapid, accurate and nondestructive extraction of the field crop stem tillering number, has higher universality, and provides the theoretical basis and technical support for extraction of the field wheat stem tillering number.

Description

technical field [0001] The invention belongs to the field of non-destructive monitoring of crop life information in precision agriculture, and relates to a method for extracting the number of wheat stems and tillers in the field, in particular to an extraction method for using laser radar point clouds to study the number of wheat stems and tillers under field conditions. Background technique [0002] The tiller number is a powerful indicator of wheat yield and growth status. Too few tillers will reduce the yield, while too many tillers will easily lead to the occurrence of diseases and insect pests. Reasonable wheat tiller number is the basis of high and stable yield, so the change of wheat tiller number must be monitored timely and accurately in actual production. [0003] At present, the methods of obtaining the number of wheat stem tillers mostly adopt the traditional manual counting method, which is labor-intensive, time-consuming and labor-intensive, and highly subject...

AI Technical Summary

Problems solved by technology

[0003] At present, the methods of obtaining the number of wheat stem tillers mostly adopt the traditional manual counting method, which is labor-intensive, time-consuming and labor-intensive, and highly subjective, which is not conducive to obtaining wheat growth information quickly and accurately, and cannot be applied to large-scale farmland in precision agriculture. Acquisition of growth information

However, traditional optical remote sensing is difficult to obtain quantitative information such as the number of wheat tillers, and spectral information is easily affected by external environmental factors such as atmosphere and light conditions.

[0004] Ground-based lidar, as a phenotypic analysis tool for quickly and accurately obtaining 3D structures of object point clouds in large areas, has been successfully applied to obtain crop canopy height and aboveground biomass, but there is a lack of using ground-based lidar to extract wheat stems. The algorithm of tiller number, especially the fast and accurate extraction of field crop tiller number has not been reported yet.

Images