Crop phenotypic parameter extraction method and device

Abstract

The invention discloses a crop phenotypic parameter extraction method and device. The method comprises the steps of obtaining group point cloud data of crops; identifying root positions of all crops according to the group point cloud data; extracting single plant point cloud data corresponding to a single plant crop from the group point cloud data according to the root position; performing stem and leaf segmentation based on the single plant point cloud data, and segmenting each leaf and stem into independent point cloud data; respectively fitting the segmented independent point cloud data toobtain crop phenotypic parameters which comprise stalk height, stalk diameter, leaf length, leaf width, leaf inclination angle and leaf area. According to the technical scheme, the automation degree is high, the crop phenotypic parameter extraction method and device can adapt to crop phenotypic parameter extraction under the condition of irregular leaf shapes, and the extraction precision is high.

Description

technical field [0001] The invention relates to the technical field of agricultural meteorology, in particular to a method and device for extracting crop phenotypic parameters. Background technique [0002] Informatization is an important feature of modern agriculture, and information technology is becoming more and more important to the development of agricultural economy. Efficient use of agricultural resources requires a full understanding of the growth of crops. To study crop growth, parameters such as leaf length, leaf width, leaf inclination, and leaf area are usually obtained. In the early days, the leaves were extracted by manual measurement. In recent years, it has been developed to take pictures of crops and use image processing algorithms to process leaf images, and combine contour tracking, seed filling and other methods to complete leaf extraction. However, the above extraction methods of crop phenotype parameters have the following problems: [0003] First of...

AI Technical Summary

Problems solved by technology

[0003] First of all, the efficiency of manual measurement is low, and at the same time, due to the irregular shape of the blade, the error caused by naked eye observation is also relatively large;

[0004] Secondly, the extraction of crop phenotypic parameters by taking pictures will seriously affect the classification effect due to the diversity, similarity, illumination difference, background factors and other problems of leaf shape.

It would take a lot of time and effort to manually extract the features of the leaves and mark and measure the leaves. At the same time, errors will be generated during manual operations, which will affect the accuracy of the final recognition;

[0005] Finally, the crop photos obtained by taking pictures are two-dimensional data. Due to the problem of shooting angle, it is difficult to guarantee the extraction of accurate leaf length, width, area and other parameters, and it is impossible to extract the leaf inclination angle.

Images