A method for extracting corn plant leaf inclination angle in the field based on depth camera

By combining a depth camera with multi-dimensional processing, an improved U-Net-ACS model, and the PointNeXt algorithm, the problem of low accuracy of depth cameras in measuring leaf inclination during the corn growth period was solved, and efficient and accurate leaf inclination angle calculation was achieved.

CN120279100BActive Publication Date: 2025-09-30JILIN AGRICULTURAL UNIV
2 Cites 0 Cited by

Patent Information

Application Number
CN202510763983.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-10
Publication Date
2025-09-30
Estimated Expiration
2045-06-10

AI Technical Summary

Technical Problem

The existing depth camera technology has the problem of low measurement accuracy due to the single measurement method in measuring the leaf inclination angle, a phenotypic parameter of corn during the growth period.

Method used

A depth camera is used to collect depth images and 3D point cloud data of corn in the middle growth period. Through multi-dimensional processing and 3D point cloud processing, combined with the improved U-Net-ACS model and PointNeXt algorithm, the leaf inclination angle of corn plants is accurately calculated and optimized when necessary.

Benefits of technology

The detection accuracy and calculation accuracy of the leaf inclination angle of corn plants are improved, adapting to complex environmental conditions, reducing the amount of calculation and improving detection efficiency.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

A method for extracting the leaf inclination angle of corn plants in the field in situ based on a depth camera. This method belongs to the technical field of intelligent phenotyping monitoring of farmland crops in smart agriculture. It solves the defect of low measurement accuracy caused by the single existing method for measuring the leaf inclination angle of corn. While streamlining the amount of calculation, it can still ensure high detection accuracy. The existing U-Net deep learning model has been improved to make it more accurately applicable to the extraction of the skeleton of corn plants, and a technical means of fitting the main stem has been added to fully consider the true morphology of the corn plant and improve the calculation accuracy of the leaf inclination angle. In the method of performing 3D point cloud processing on the 3D point cloud data of the depth image to obtain the leaf inclination angle of each leaf of the corn plant, PCA analysis is performed on the point cloud of each leaf, the flatness of the leaf is redefined, and the processing is carried out according to the situation, so that the calculation of the leaf inclination angle is more accurate.
Need to check novelty before this filing date? Find Prior Art